Evaluation of screening parameters and machine learning models for the prediction of neonatal sepsis: A systematic review

Evaluation of screening parameters and machine learning models for the prediction of neonatal sepsis: A systematic review | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Help Center Sign In Submit a Preprint Cite Share Download PDF Systematic Review Evaluation of screening parameters and machine learning models for the prediction of neonatal sepsis: A systematic review Dennis Peace Ezeobi, Dr. Angella Musiimenta, Dr. William Wasswa, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-1354764/v2 This work is licensed under a CC BY 4.0 License Status: Posted Version 2 posted You are reading this latest preprint version Show more versions Abstract About 2.9 million neonates die every year worldwide, and most of these deaths occur in low-resource settings. Neonatal sepsis occurs when there is a bacterial invasion in the bloodstream; the immune system begins a systemic inflammatory response syndrome (SIRS) damaging to the body and can quickly advance to severe sepsis, multi-organ failure, and finally, death. Sepsis in neonates can progress more rapidly than in adults; therefore, a timely diagnosis is critical. The standard gold test for diagnosing neonatal sepsis is blood culture, which takes at least 72 hours. Hence, identifying key predictor variables and models that work best can help reduce neonatal morbidity and mortality. The matching articles were identified by searching the PubMed, IEEE, and Cochrane bibliography databases. For the inclusion of articles, the abstract and titles were first screened based on some predetermined criteria and then, the full-text articles were screened. Thirty-one studies met the full inclusion criteria. The duration of ROM was found to be more significant than other maternal risk factors. Heart rate and heart rate variability were found to be more significant than other neonatal clinical signs. C reactive protein and I/T ratio were found to be more significant than other laboratory tests. The main limitation is the variation in the performance measures used in the studies, which made it difficult to perform a quantitative assessment. A combination of predictor variables has been shown to strengthen neonatal sepsis prediction, as shown by some of the reviewed studies. Predictive algorithms that combine multiple variables are urgently needed to improve models for early detection, prognosis, and treatment of neonatal sepsis. Bioinformatics Computational Biology Neonatal sepsis screening parameters algorithms models Figures Figure 1 Introduction About 2.4 million neonates die every year worldwide, and most of these deaths occur in low resource settings [1] [2]. The third Sustainable Development Goal (SDG) for child health aims to end the mortality of newborns and children under five years of age, which is preventable by 2030. However, this may not be achieved if there is no significant reduction of neonatal deaths directly related to infection in developing countries [3]. Sepsis is a significant cause of neonatal mortality and morbidity around the world [4] [5] [6] and most of the morbidity and mortality from sepsis is preventable. Neonatal sepsis is classified as early-onset ( 48–72h), and this depends on the age at onset [7] [8]. About 30–50% of neonatal sepsis survivors obtain significant long-term impairments, including prolonged hospitalization, chronic lung disease, and neurodevelopmental disabilities [9] [10] [11]. Sepsis remains one of the most expensive causes of hospitalization, as recent data highlight its costs and burdens [12] [13] [14] [15]. Physicians caring for infected neonates are faced with multiple challenges in diagnostic and treatment decisions. Despite the increased understanding of its pathophysiology and efforts to improve clinical decision support in intensive care, there have been just fair improvements in neonatal sepsis outcomes [16]. Neonatal sepsis occurs when there is a bacterial invasion in the bloodstream; the immune system begins a systemic inflammatory response syndrome (SIRS), which is damaging to the body and can quickly advance to severe sepsis, multi-organ failure, and finally, death [17] [18]. However, early recognition and prompt treatment have been predicted to improve the clinical management of sepsis and serve as the key to reducing morbidity and mortality [19] [20] [21] [22] [23]. Delays in recognition and treatment of sepsis is still a challenge despite the explored importance of early intervention [6] [16] [24] [25] [26] [27] [28]. Neonatal clinical presentation is non-specific and overlaps with other newborn disease processes. The laboratory tests have limited diagnostic accuracy, which makes rapid diagnosis for neonatal sepsis difficult. The standard gold test for neonatal sepsis diagnosis, blood culture, faces the challenge of insufficient blood volume for blood culture and low amount of invading microorganisms in the blood, which usually generates false-negative results [29] [30]. Infants suspected of having sepsis are subjected to prolonged antibiotic therapy despite negative cultures. In other to tackle the challenges associated with sepsis recognition and care management studies are making use of machine learning and statistical modeling approaches [31] [32] [33] [34]. Compared to other significant conditions, neonatal sepsis receives less substantial international investment as a public health priority despite the heavy burden of newborn deaths related to neonatal sepsis [3]. Knowledge of neonatal sepsis's predictor variables, early identification, and early interventions can reduce neonatal mortality and morbidity rates. This study aims to review the existing screening parameters and models based on their diagnostic performance, strength, and weaknesses to better understand the algorithm development process. Materials And Methods Selection of screening parameters for analysis A preliminary examination of the available literature was carried out, after which a list of parameters was consolidated for further review. These parameters were selected based on their publication and their potential for diagnosing and prognosis of neonatal sepsis. The parameters include; Maternal risk factors (which include; intrapartum fever, chorioamnionitis, postnatal distress, duration of ROM, GBS colonization, and intrapartum antibiotics). Neonatal clinical signs (which include; gestational age, birth weight, heart rate, and feeding difficulty). Laboratory tests (which include; absolute neutrophil count, C reactive protein, I/T ratio, micro-ESR, platelet count, and total leukocyte count). Search Strategies In order to carry out a landscape analysis to identify studies with the diagnostic performance of the previously mentioned parameters, PubMed, IEEE, and Cochrane's bibliography database were searched. The search strategies for the databases were carefully made to give maximum output. A combination of text words was used to develop the search strategy, which includes; "neonatal sepsis" AND "prediction" AND "machine learning", "neonatal sepsis" AND "prediction" AND "EHR", "neonatal sepsis" AND "prediction" AND "model", "neonatal sepsis" AND "prediction" AND "algorithm", "neonatal sepsis" AND "diagnostic algorithm" AND "machine learning", "neonatal sepsis" AND "screening parameters" AND "models", "neonatal sepsis" AND "screen" AND "models". The search strategy was restricted to the subject (humans) and the time period (January 2000 to April 2020). A total of 463 PubMed, 305 citations from IEEE, and 86 Cochrane citations from Cochrane were retrieved. These references were imported as separate files into an excel sheet except for the Cochrane database's references; it was imported only as CSV file. The duplicates were removed, the titles and abstracts of the retrieved citations were screened to find the articles relevant to the study. Additional relevant studies were retrieved by scrutinizing the bibliography of searched studies. Inclusion Criteria For the inclusion of articles, the abstract and titles were screened based on the following predetermined criteria: The subject population are neonates. Subjects have culture-proved sepsis or suspected sepsis based on a clinical algorithm. The article evaluated any of the consolidated screening parameters and algorithms/models for neonatal sepsis diagnosis or prognosis. The exhaustive search based on the titles and abstracts returned a broad spectrum of infection-related studies from which only cases of neonatal sepsis were considered. Finally, full-text articles with the following criteria were included for analysis: The subject population are neonates. The study provided a clear definition of neonatal sepsis. The study provides neonatal sepsis onset definition (i.e., time of onset). The study clearly described the predictor variables used. The study clearly described the machine learning models used or evaluated in any of the consolidated screening parameters. The study must have provided diagnostic performance results (i.e., AUROC results). Exclusion Criteria It was a great challenge trying to select the relevant articles for this review from the large number of papers retrieved (n=854) based on the selection criteria. To make a comprehensive list of appropriate papers, articles that did not deal with neonates, duplicates, reviews, meta-analyses, abstracts, editorials, and commentaries were excluded. Data Extraction The available full papers were downloaded from PubMed, IEEE, and Cochrane sources. The data was extracted and compiled in an Excel spreadsheet. The following information was extracted from all the studies: Publication characteristics (author’s name, year of publication). Study design (retrospective, prospective data collection and analysis). Selection of cohorts (sex, age, number of patients with sepsis, prevalence of sepsis). Neonatal sepsis definition. Neonatal sepsis onset definition. Specifics on analyzed data (the type of variables, number of screening parameters). Model selection (ML algorithm, platforms, software, packages, and hyperparameters). Statistics for the performance model (methods for evaluating the model, statistical significance, handling of missing data). Methods to avoid overfitting and also any additional external validation approaches. For a point of reference, the leading hospital in Mbarara, Uganda, was contacted to learn what tests/algorithms are currently being used in their clinical settings. Quality Assessment of the Included Studies Table 1: Quality assessment of the included studies. Categories Items Description Reported Unmet needs Limits in current machine learning or non-machine learning Applications Low diagnostic accuracy, low human-level prediction accuracy, or prolonged diagnostic procedure. Yes/No Reproducibility Prevalence of Neonatal sepsis The proportion of neonates who suffered sepsis out of the entire study cohort. Yes/No Data availability Is the data used in the study publicly available? Yes/No Feature engineering methods How features were generated before model training Yes/No Code for data wrangling and analysis Code describing the details of the cleaning, preprocessing, and analysis of the data. Yes/No Code of label Code describing neonatal sepsis label generation Yes/No Platforms/packages Both platforms and packages should be reported Yes/No Hyperparameters All hyperparameters which are needed for study replication Yes/No Robustness Sample size > 50 Neonatal sepsis case sample size >50 is required for the interpretation, power, and validity of machine learning methods. Yes/No Valid methods for over-fitting Valid methods for unbiased performance assessment (or methods "against" overfitting) Yes/No Stability of results Calculated variation in the validation statistics Yes/No Generalizability External data validation Validation in settings different from the research framework Yes/No Clinical significance Predictor’s explanation Explanation (biological or quantification) of the importance of each predictor Yes/No Suggested clinical use Clinical usability and requirements (e.g. what are still necessary for making deployment possible) Yes/No The quality of the selected ML studies was assessed based on 14 criteria relevant to the objectives of the review, which was adopted from [35]. The assessment consists of five categories described in table 1 above. A quality assessment table was provided by listing "yes" or "no" for each category's items using the provided criteria. Results Out of 854 studies, 31 studies met the inclusion criteria. The literature search results with reasons for exclusions at each stage are presented in figure 1 above. Study Characteristics Of the 31 included studies, 16 employed solely prospective analyses, 13 employed solely retrospective analyses, while 2 studies used both retrospective and prospective analyses [37, 38]. The most frequent data sources used in the studies were the University of Virginia Hospital (n = 8; 26%), followed by MIMIC-III (n = 3; 10%). In terms of neonatal sepsis definition, the majority of the studies employed Blood culture (n = 26; 84%) or Observational condition (use of clinical signs) (n = 16; 52%) or combination of Blood culture and Observational condition (n = 12; 39%). The studies modified observational and Laboratory definitions based on available data and the predetermined neonatal sepsis onset time; this is mainly due to the absence of a consensus definition of neonatal sepsis. The prevalence of neonates with sepsis ranged between 0.27% and 87.0%. Five studies did not report the prevalence [39, 40, 41, 42, 43]. Regarding the category of neonatal sepsis of interest, the category with a high focus is late-onset (n = 18; 58%) and early-onset (n = 4; 13%). While 9 studies [39, 44, 45, 46, 47, 48, 49, 50, 51] did not report the category of focus. In demographics, 6 studies reported the median or mean age of the neonates, 11 reported the prevalence of male neonates, 2 reported the prevalence of female neonates, and only 3 reported the investigated cohorts' ethnicity (see supplementary table 1). Overview of Machine Learning Algorithms and Variables A wide range of ML algorithms has been employed to build models for the early detection of neonatal sepsis, with some models being specific to the study population. Regression was the most used model of which various types (n = 25; 81%) were used. This includes Logistic Regression or Linear Regression [52]. Furthermore, boosted tree models were the second most used model (n = 6; 19%), including gradient boosting CITATION Placeholder4 \l 1033 [42] , or random forest [43]. And lastly SVM CITATION Placeholder4 \l 1033 [42] (n = 5; 16%). Most of the studies (n = 24; 77%) arbitrarily chose one- or two-ML models without arguing the reasons. Seven studies (23%) [53, 54, 55, 42, 43, 50, 56] compared several models and identified the one with the best performance. As for the analyzed variables, the most common variable used was neonatal clinical signs (n = 28; 90%), followed by laboratory tests (n = 10; 32%), and maternal risk characteristics (n = 5; 19%). Sixteen studies (52%) were found to use one variable, while the remaining fifteen studies (48%) were found to combine these variables, which includes neonatal clinical signs and laboratory tests (n = 10; 32%), maternal risk characteristics, and neonatal clinical signs (n = 5; 16%). None of the studies were found to explore the combination of maternal risk characteristics, neonatal clinical signs, and laboratory tests. The number of screening parameters included in the respective models ranged between 2 [57] and 22 CITATION Mas19 \l 1033 [50] . Concerning the features for detecting neonatal sepsis, the reviewed studies show that duration of ROM was found to be more significant than other maternal risk factors [46, 58, 50, 59]. Heart rate and heart rate variability were found to be more significant than other neonatal clinical signs [40, 43]. C reactive protein and I/T ratio were found to be more significant than other laboratory tests [45, 57]. Table 2: Pseudo code for the HRV monitoring algorithm HRV Monitoring Algorithm for Neonatal sepsis CITATION Placeholder3 \l 1033 [43] Step 1: Create a set H of 17 heart rate variability, H = (v 0 …v d ), 1 ≤ d ≤ 17 Step 2: Initialize elements of set H; T = (c 0 … c ⅈ ), 1 ≤ ⅈ ≤ 17 Step 3: Check result of the time, frequency and non-linear analysis in elements of set T IF ⅈ is defined as “Absolute” THEN RETURN True ELSE RETURN False END IF Step 4: IF number of Absolute is defined as “High” THEN RETURN “Neonatal Sepsis” ELSE RETURN “Normal” END IF Table 3: Phase I: Pseudo code for the observational condition Medical Decision Support Algorithm for Neonatal sepsis [54] The algorithm consists of three phases: observational condition, laboratory condition, and neonatal sepsis. Step 1: Create a tuple Z of 4 neonatal clinical signs, Z = (w 0 …w x ), 1 ≤ x ≤ 4 Step 2: Initialize elements of tuple Z; U = (d 0 … d j ), 1 ≤ j ≤ 4 Step 3: FOR each j in U DO IF j = = condition THEN RETURN True ELSE RETURN False END IF END FOR Step 4: IF True ≥ 1 RETURN “Observational Condition” ELSE RETURN “No Observational Condition” END IF Table 4: Phase II: Pseudo code for the laboratory condition Step 1: Create a tuple Q of 5 laboratory tests, Q = (p 0 … p c ), 1 ≤ c ≤ 5 Step 2: Initialize elements of tuple Q; X = (f 0 … f k ), 1 ≤ k ≤ 5 Step 3: FOR each k in X DO IF k = = condition THEN RETURN True ELSE RETURN False END IF END FOR Step 4: IF True ≥ 1 RETURN “Laboratory Condition” ELSE RETURN “No Laboratory Condition” END IF Table 5: Phase III: Pseudo code for the neonatal sepsis Step 1: Create a set R of 3 neonatal sepsis variables, R = (d 0 … d a ), 1 ≤ a ≤ 3 Step 2: Initialize elements of set R; L = (g 0 … g y ), 1 ≤ y ≤ 3 Step 3: FOR each yin L DO IF y = = “Yes” THEN RETURN True ELSE RETURN False END IF END FOR Step 4: IF True = = 3 RETURN “Septic” ELSE RETURN “Not Septic” END IF Some of the existing neonatal sepsis prediction algorithms using neonatal clinical signs and maternal risk factors are shown below in tables 2, 3, 4, and 5. Model Validation Approximately 58% of the studies did not report what valid methods were used to prevent overfitting, while 29% employed cross-validation technique (e.g., 4-fold, 5-fold, 10-fold, or leave-one-out cross-validation), and 19% employed bootstrap to avoid overfitting. Concerning the models' limitations, 13% of the studies recommend that the models require additional variables to optimize their performance. Additional external validation of the models was only performed in seven studies [60, 44, 40, 58, 61, 48, 38]. Particularly, Fairchild & O'Shea (2010) used datasets from University of Virginia NICU and Wake Forest University NICU to train, test, and validate the use of neonatal heart rate characteristics (HRC) to detect late-onset (LOS) neonatal sepsis. In another study, Fairchild et al. (2017) explored the use of vital signs to build models that predict neonatal sepsis using datasets from the University of Virginia, UVA, and Columbia University. Gur et al. (2015) trained, tested, and validated the RALIS algorithm's ability to detect LOS before clinical suspicion with datasets from neonatal intensive care units (NICU) of three hospitals in Israel. Aiming to develop and validate a nomogram for assessing the individual prior probability of LOS based on maternal risk factors and neonatal clinical signs in preterm infants, Huang et al. (2020) created a validation cohort using data from three neonatal critical care centers in Guangdong province of China. Lastly, the study by Popowski et al. (2011) investigated the predictive value of maternal risk factors for early-onset (EOS) neonatal sepsis using a dataset from two French tertiary university referral centers. Quality Assessment of Included Studies [Table 6 is in the supplementary files section.] Table 6 above shows the results of the quality assessment of the studies. The 31 studies' quality ranged from poor (meeting≤ 40% of the criteria) to very good (meeting≥ 90% of the criteria). None of the studies fulfilled all 14 criteria as none of the studies met ≥ 90%of the criteria. Few studies made the data used in their study available (n = 3; 10%). Only ten studies (32%) explained how features were generated before model training. Only two studies (6%) provided the code used for data cleaning and analysis. Only one study (3%) provided code to reproduce the exact sepsis labels [58]. Few studies reported the hyperparameters needed for study replication (n = 5; 16%). Finally, only seven studies (23%) validated their study result on an external data set. With the exception of two studies CITATION Gri01 \l 1033 \m Sta13 [64, 53] , all other studies had sample sizes larger than 50, which is a requirement for the interpretation, power, and validity of machine learning methods. [Tables 7-10 are in the supplementary files section.] Table 11: Strength and weaknesses of the existing screening parameters Screening Parameters Strength Weakness Duration of ROM Has strong and nearly linear association with neonatal sepsis. Association is stronger with EOS than LOS. Maternal age Neonatal sepsis is common among infants of older mothers and maternal age < 20 can be associated with EOS risk factors. Not validated or considered as a determining risk factor for neonatal sepsis. Parity Has strong association with neonatal sepsis. Association with neonatal sepsis is controversial. Antibiotic treatment Reduces the risk of infection to a mother and neonate. Increases other health risks to newborn infants. Maternal CRP It is associated with neonatal sepsis and a significant risk factor for neonatal sepsis. CRP values are also affected by other factors. GBS status Strongly associated with neonatal sepsis. Even though GBS remains the most frequent pathogen for EOS, there has been a shift in this as Escherichia coli (E. coli) becomes the most important pathogen causing EOS in preterm and very low birth weight infants. Intrapartum fever It’s generally considered a major risk factor for EOS. The risk of neonatal sepsis in newborns delivered by mothers with intrapartum fever is low. Heart rate variability It is a significant risk factor for neonatal sepsis, and neonates have reduced heart rate variability (HRV) before clinical signs of sepsis. Its main drawback for early diagnosis of neonatal sepsis is the high false-positive rate. Birth weight It is one of the determining factors for neonatal sepsis as newborns with less than 2.5 kg are 1.42 times more likely to develop neonatal sepsis than newborns born with 2.5 kg and above. Infants with low birth weights are at increased risk for other forms of infection and infection-related mortality. Respiratory rate Its variability can be an indicator of sepsis. The variability in respiratory rate is also associated with other respiratory problems. Heart rate It is one of the most important clinical indicators to evaluate sepsis. An elevated score is not specific for sepsis and may occur in other conditions associated with nonspecific inflammation. SpO2 Performs well for preclinical detection of sepsis. High altitudes and other factors may affect what is considered normal for a given neonate. Poor feeding It appears to be crucial in a diagnosis of sepsis. It is a nonspecific symptom seen in newborn Temperature Its variability can be an indicator of sepsis. Newborns cannot regulate their body temperature well, causing instability. Apnea It can be a clinical sign of neonatal sepsis It is common in infant breathing and can be caused by other factors. Lethargy It can be a sign of infection It can be a sign of other conditions. Duration of umbilical venous catheters A long duration of use is associated with bloodstream infection in newborn It is not significant in the diagnosis of sepsis. Use of antibiotics on newborns Are administered to target most types of bacteria that cause an infection Because infants have a higher risk of complications, pediatricians often prescribe antibiotics even if they aren't positive that it's a bacterial infection. Blood pressure It can be associated with newborn infection. It can be affected by other conditions. Gestational age Preterm babies are more likely to develop neonatal sepsis than term babies. It is a risk factor for other conditions. Gender It influences both the incidence and the outcomes of sepsis. It is not a strong indicator of sepsis. Platelets It's beneficial to predict mortality or to diagnose the sepsis It is not very sensitive for the diagnosis of neonatal sepsis and is not very helpful in monitoring the response to therapy. WBC It is highly predictive of infection. Multiple variables can affect the various components of WBC. CRP It increases significantly in cases with infection. It may not be elevated in the early stages of infection due to the time taken for its synthesis in the liver and, eventually, appear in the blood. Leucocyte count It can aid in clinical decision-making in cases where a low-to-moderate clinical suspicion for sepsis is present. It has low sensitivity in diagnosing neonatal sepsis. I/T ratio It is highly predictive of infection. It is not particularly useful as an independent test in identifying the majority of septic infants. pH It can be significantly lower in newborns with sepsis It can be caused by other conditions. Glucose Its level can be significantly affected by neonatal sepsis. Low blood sugar can happen for many reasons HCO3 It can be significantly lower in newborns with sepsis It can be caused by other conditions. [Table 12 is in the supplementary files section.] Discussion The review summarized studies on neonatal sepsis with ML algorithms to facilitate early prediction. Looking at ML methods, which includes cohort selections, predictor variables, outcomes, the building of models, and validation methods. A wide range of ML algorithms was chosen for analysis in the studies to leverage neonates' digital health data to predict sepsis. Based on the findings from the reviewed studies, this section outlines three major challenges that studies on neonatal sepsis prediction leveraging machine learning are currently facing: (i) asynchronicity, (ii) comparability, and (iii) reproducibility. Asynchronicity Studies focused on predicting neonatal sepsis with ML have shown to have the advantage of increasing the prediction power and have promising results [43, 50]. But so far, the reports on which of the open challenges are the most pressing challenges that need to be addressed are diverging, which poses difficulty in achieving the goal of early neonatal sepsis detection. On one hand, the blood culture test, which is the standard gold test, has been stated as the most reliable test for confirming neonatal sepsis [62]. While on the other hand, recent findings have cast doubt on the validity and meaningfulness of the blood culture test. As it has been stated to be unreliable due to the longer time (48-72 hours), it takes to obtain the result and the insufficient amount of blood obtained from neonates, which produces false-negative results [54, 50]. Also, it was stated that neonatal clinical signs (e.g., the use of heart rate variability) alone are sufficient in detecting neonatal sepsis [40, 61]. However, recent studies are posing doubts to this as they state that a combination of predictor variables yield better results in the detection of neonatal sepsis [48, 57, 43, 50]. The developed ML models need to be explored in clinical trials to ascertain their clinical settings usage as most of the models are developed retrospectively, facing multiple obstacles. Comparability In terms of comparability of the reviewed studies, several challenges were identified that are yet to be overcome; (i) neonatal sepsis definition, (ii) implementation of a given neonatal sepsis definition, and (iii) performance measures of the models. Each of these challenges is discussed below. Defining and Implementing Neonatal Sepsis The choice of neonatal sepsis definition is an obstacle that affects the comparison of studies in terms of septic neonates' prevalence. A various set of neonatal sepsis definitions (and modifications) were used in the reviewed studies. Having a large set of septic neonates is anticipated to be useful in training ML models (most especially the deep neural networks). However, having a high number of septic neonates could make it difficult to differentiate the septic neonates from the non-septic neonates. Neonatal sepsis is inherently hard to define as, over the years, there has not been a consensus definition for it. The previous study shows that the use of different sepsis definitions on the same dataset gives a largely dissimilar cohort [68]. This study found that blood culture is less inclusive, leading to a small cohort showing severe symptoms, which has been reported in several studies [54, 43, 50]. It was also seen that even the use of the same definition on the same dataset gives dissimilar cohorts. This can be confirmed from studies carried out at the University of Virginia and studies that used the MIMIC-III dataset (see Table 9 above). The underlying problem cannot be easily discovered, as the code for assigning the labels are not available in 30 studies out of 31 (97%) studies. The diversity of neonatal sepsis prevalence is another factor that is increasing the problem of comparability. Some studies balance their datasets to improve the training of the ML models, but this training setup can partly affect the study [56]. While other studies keep the observed case counts to see how their approach will work in clinical settings. From this study findings, it has been identified that the neonatal sepsis definition used and the data pre-processing steps affect the prediction of sepsis and also the prevalence [68]. The maximum prevalence reported is 87.0% [64]. Performance Measures of the Models The choice of performance measures is the last obstacle to be discussed that is obstructing comparability. This obstacle is largely affected by the prevalence of neonatal sepsis in the study. Accuracy is a simple performance metric directly influenced by class prevalence; comparing two studies with different prevalence values is problematic. Some studies report the area under the receiver operating characteristic curve (AUROC, also known as AUC) to improve the performance metrics report. However, AUROC also depends on class prevalence and can be less informative on highly imbalanced classes [69]. The area under the precision-recall curve (AUPRC, also known as average precision) is preferable in such a situation. Both AUPRC and AUROC are affected by prevalence. However, AUPRC allows comparison with a random baseline that just "guesses" the neonate label, and it's useful when considering the positive class. While AUROC can be high even for classifiers that could not classify the minority class of septic neonates. The effect of the choice of performance metrics is greatly seen with highly imbalanced classes. Recent research recommends reporting the AUPRC of models, particularly in clinical studies [70], which is a good recommendation. Comparing Studies of Low Comparability Based on this review study's findings, comparing the reviewed studies quantitatively is currently a challenging task to accomplish, which was also seen in a study by (Moor, et al., 2020). The studies were assessed qualitatively to identify underlying biases that could lead to unduly optimistic results. This was done as the best-performing methods could not be ascertained by just evaluating the performance measures' numeric values. A meta-analysis will be preferable to sum up, an overall trend in the performance of the models. Reproducibility Reproducibility, which is the ability to obtain consistent results using the same data and code as the original experiment, is the means for scientific accountability. There have been failures of this accountability in several disciplines, including ML [35]. The use of sensitive data makes it difficult to make available the dataset used in studies, which is one of the challenges digital medicine poses to reproducibility. Another challenge is the failure to provide detailed preprocessing methods used in ML papers. Based on the quality assessment carried out, important areas were outlined that need to be improved. As it was seen, only two studies [50, 66] made available their analysis code. Only one study [58] made available their code for generating a “label.” Both cases amount to less than 10% of the eligible studies. In addition, only three studies [57, 50, 66] made available the dataset used for their study. Only eight studies were found to share the hyperparameters used in their studies. However, a positive finding of this analysis is that a considerable number of studies (n = 10) shared the preprocessing methods used in their studies, which is useful information in the reproducibility of computational experiments. This review focused on publications that studied the prediction of neonatal sepsis implementing ML algorithms. The majority of the reviewed studies investigating neonatal sepsis prediction defined neonatal sepsis as having positive blood culture or observational condition (i.e., the use of neonatal clinical signs). None of the 31 included studies reflects an African cohort, which shows a significant dataset bias in the publications and insufficient research in Africa (see Supplemental table 1 for an overview of demographical information). The review found a lot of room for improvement, which will benefit the comparability of different models, most importantly, when ML models are going to be evaluated prospectively. Limitations This review was carried out with some shortcomings. The reviewed studies had certain inherent limitations, as previously mentioned. The diagnostic performance evaluation report of the models was suboptimal. The studies were assessed qualitatively due to the variation in the performance measures used. A meta-analysis will be preferable to evaluate the performance of the models. Some studies may have been omitted from the review as English language restrictions were applied. Conclusion Combination of these variables have been predicted to strengthen the prediction of neonatal sepsis which was shown in some of the studies above. This study seeks to inform researchers on what predictor variables are required to develop algorithms/models with better diagnostic performance which will improve the detection of neonatal sepsis. The parameters and machine learning models used in the reviewed studies were largely different, so diagnostic performance was different. It should be considered that neonatal sepsis is consistent with other symptoms as well as underlying conditions. What is important here is the weight assigned to a variable. Suggestions for risk stratification based on maternal risk factors (such as; intrapartum fever, chorioamnionitis, duration of ROM, GBS colonization and intrapartum antibiotics), neonatal clinical signs (such as; gestational age, birth weight, heart rate, postnatal distress and feeding difficulty), and laboratory tests (such as; absolute neutrophil count, C reactive protein, I/T ratio, micro-ESR, platelet count and total leukocyte count) could be considered for future studies. List Of Abbreviations ANC Absolute Neutrophil Count AR-HMM Autoregressive hidden Markov model AUROC Area Under the Receiver Operating Characteristics CNNs Convolutional neural networks CRP C-reactive protein CSF Cerebrospinal Fluid ECG Electrocardiogram EMR Electronic Medical Record EOS Early onset sepsis GA Gestational age GBS Group B Streptococcus HELLP syndrome Hemolysis elevated liver enzymes low platelet count HRC Heart rate characteristics HR Heart rate HRV Heart Rate Variability I/T ratio Immature to Total Neutrophil Ratio LNS Late-neonatal sepsis LOCF Last observation carried forward LOS Late-onset sepsis M-ESR Micro Erythrocyte Sedimentation Rate MIMIC Medical Information Mart for Intensive care III ML Machine Learning NICUs Neonatal Intensive Care Units NPV Negative Predictive Value PPROM Preterm Premature Rupture of the Membranes PPROMEXIL Preterm pre-labor rupture of the membrane expectant management or induction of labor study Pro Prospective PR Pulse rate PPV Positive Predictive Value Retro Retrospective ROC curve Receiver-operating characteristic curve ROM Rupture of Membranes RR Respiratory rate SDG Sustainable Development Goals SIRS Systemic Inflammatory Response Syndrome SO Oxygen saturation SpO2 Blood oxygen level SSA Sub-Saharan Africa TC Core temperature TLC Total Leukocyte Count TP Peripheral temperature WBC White blood cell Declarations The work presented in this Manuscript is the result of our original research work. Where we have used the works of other persons, due acknowledgements are clearly stated. This work has not been submitted for publication in any journal before. Ethical approval and consent to participate Not applicable; as the study reviewed only published data. Consent for publication Not applicable Availability of data and materials Not applicable. Competing Interests The authors declare that they have no competing interests. Funding No external funding was obtained for this study. Author’s contributions EDP, WW and AM carried out the preliminary literature search following the PRISMA guidelines, tabulated and analyzed the collected data and developed the first draft of the manuscript. KS contributed the neonatology expertise and edited the manuscript accordingly. All the authors reviewed and approved the final manuscript. Acknowledgement Not applicable. Authors information EDP Department: Information Technology Course: Masters in Health Information Technology Authors' qualifications: BS.c, MS.c Institution: Mbarara University of Science and Technology (MUST) Position: Post-Graduate Student WW Authors' qualifications: BS.c, MS.c, PhD Department: Biomedical Sciences and Engineering Institution: Mbarara University of Science and Technology (MUST) Position: Head of Department (HOD) AM Authors' qualifications: BS.c, MS.c, PhD Department: Information Technology Institution: Mbarara University of Science and Technology (MUST) Position: Deputy Dean of the Faculty Location: Mbarara, Uganda KS Authors' qualifications: MBChB, MMed Department: Pediatrics and Child Health MRRH Hospital: Mbarara Regional Referral Hospital (MRRH) Position: Head of Department (HOD), Neonatology division Supplementary Material The supplementary file contains the filled PRISMA statement checklist for the study. Table 1: The table contain an overview of trial designs, demographical information and machine learning details of the studies. References [1] WHO, "Newborn death and illness," Partnership for Maternal, Newborn & Child Health, Geneva, Switzerland, 2011. [2] UNICEF, "Levels and Trends in Child Mortality Report 2017.," United Nations Children’s Fund, New York, 2017. [3] S. W. B. Ranjeva and S. Schiff, "Economic burden of neonatal sepsis in sub-Saharan Africa.," BMJ global health, vol. 3, no. 1, p. e000347, 2018. [4] L. Liu, S. Oza, D. Hogan, J. Perin, I. Rudan, J. Lawn, S. Cousens, C. Mathers and R. Black, "Global, regional, and national causes of child mortality in 2000–13, with projections to inform post-2015 priorities: an updated systematic analysis.," Lancet, vol. 385, pp. 430-440, 2015. [5] A. Sarkar, G. Dhar, M. Sarkar, T. Ghosh and S. Ghosh, "Early diagnosis of neonatal sepsis in primary health care unit.," Bangladesh J. Med. Sci., vol. 14, no. 2, pp. 5-8, 2015. [6] M. V. M. Stephannie and J. M. M. Patrick, "Neonatal Sepsis.," Clin. Pediatr. Emerg. Med., vol. 17, pp. 129-133, 2016. [7] Z.-V. Alonso and J. O. Theresa, "Challenges in the diagnosis and management of neonatal sepsis," Journal of Tropical Pediatrics, vol. 61, p. 1–13, 2015. [8] A. Shane, P. Sánchez and B. Stoll, "Neonatal sepsis.," Lancet, 2017. [9] J. S. M. Barbara, I. H. M. Nellie, A.-C. M. Ira, A. F. M. Avroy, R. H. M. Susan, V. M. Betty and D. H. M. Rosemary, "Neurodevelopmental and Growth Impairment Among Extremely Low-Birth-Weight Infants With Neonatal Infection," JAMA., vol. 292, no. 19, pp. 2357-2365, 2004. [10] E. S. M. Bonnie and R. M. Betty, "Neurodevelopmental Outcome of the Premature Infant," Pediatric Clinics of North America, vol. 56, no. 3, p. 631–646., 2009. [11] J. S. M. Barbara, I. H. M. Nellie, F. B. M. Edward, S. M. Seetha, R. L. M. Abbot, C. W. M. M. Michele and B. R. Nancy S. Newman, "Neonatal Outcomes of Extremely Preterm Infants From the NICHD Neonatal Research Network," Pediatrics, vol. 126, no. 3, p. 443–456, 2010. [12] C. Jonathan, V. Jean-Louis, K. J. A. Neill, R. M. Flavia, C. A. Derek, C. Thierry, J. Katia, G. Stefano, D. Julie, O. Steven, T. Kevin, v. d. P. Tom and P. Eric, "Sepsis: a roadmap for future research," The Lancet Infectious Diseases Commission, vol. 15, no. 5, p. 581–614., 2015. [13] G. M. M. Elsie, S. M. P. Lisa, F. R. P. Lynn and M. M. M. Paul, "A Nurse-Driven Screening Tool for the Early Identification of Sepsis in an Intermediate Care Unit Setting," J Hosp Med , vol. 10, no. 2, p. 97–103, 2015. [14] J. P. P. M. Carly, P. Mark A. Reynolds, M. Meenal Sinha, P. Matthew Gitlin and M. Elliott Crouser, "Epidemiology and Costs of Sepsis in the United States—An Analysis Based on Timing of Diagnosis and Severity Level," Critical Care Medicine, vol. 46, no. 12, 2018. [15] H. Jihane, B. Natalie, S. Jola and J. Douglas, "The “Centrality of Sepsis”: A Review on Incidence, Mortality, and Cost of Care," Healthcare, vol. 6, no. 3, 2018. [16] L. W. James, "Defining Neonatal Sepsis," Curr Opin Pediatr. , vol. 28, no. 2, p. 135–140, 2016. [17] R. Konrad, B. Michael, C. R. Niels and S. H. Christiane, "New Approaches to Sepsis: Molecular Diagnostics and Biomarkers," Clinical Microbiology Reviews , vol. 25, no. 4, p. 609 – 634, 2012. [18] B. M. P. M. Fran, R. A. M. M. Elizabeth, K. A. M. R. Mary, H. B. Katie, S. P. Aileen, L. M. Jane, M. P. Julie C. Fitzgerald, L. W. M. M. Scott and J. Z. M. M. Joseph, "Improving Recognition of Pediatric Severe Sepsis in the Emergency Department: Contributions of a Vital Sign Based Electronic Alert and Bedside Clinician Identification," Ann Emerg Med. , vol. 70, no. 6, p. 759–768., 2017. [19] L. J. M. M. Stephen, M. A. M. M. Carol, K. M. Lisa, G. N. Elizabeth, B.-G. D. R. F.-C. C. N.-B. Charyl, D. R. C. Maureen, M. M. F. F. Faisal, A. S. P. Beverly and M. M. Nelda P. Wray, "Reductions in Sepsis Mortality and Costs After Design and Implementation of a Nurse-Based Early Recognition and Response Program," Jt Comm J Qual Patient Saf, vol. 41, no. 11, p. 483–491, 2015. [20] O. Lori, "Early Recognition and Management of Maternal Sepsis," Nursing for Women’s Health , 2016. [21] A. S. Michael, J. B.-M. Samantha and D. P. Gavin, "Identification of adults with sepsis in the prehospital environment: a systematic review," BMJ Open , 2016. [22] B. F. Deshayne, H. Steven, A. W. Coralie, A. W. Lindsay, S. Q. M. Malia, C. Pranesh, L.-M. Thierry, K. P. Beth and W. Kumanan, "Using newborn screening analytes to identify cases of neonatal sepsis," SCIENTIFIC REPORTS , 2017. [23] B. Mercedes, P. S. Joao, A. Edgardo, F. Bukola, K. Marian, K. Seni, L. Pisake, N. Ashraf, N. Ruta, B. Vanessa and G. A. Metin, "The global maternal sepsis study and awareness campaign (GLOSS): study protocol," Reproductive Health, 2018. [24] A. S. Birju and F. P. James, "Neonatal sepsis An old problem with new insights," Virulence, vol. 5, no. 1, p. 170–178, 2014. [25] D. M. Clarissa, S. M. Karen and K. J. M. Sunil, "Biomarkers of Neonatal Sepsis.," Neoreviews, vol. 16, no. 5, p. e297–e308, 2015. [26] F. Aline, B. Julia, M. Shrey, S. Mike and N. V. D. A. Johannes, "Antibiotic Use for Sepsis in Neonates and Children: 2016 Evidence Update," WHO, 2016. [27] K. Claus, F. K. René, B. Giuseppe, F. M. Rolf and S. Martin, "Culture-Negative Early-Onset Neonatal Sepsis — At the Crossroad Sepsis Care and Antimicrobial Stewardship," Front. Pediatr., 2018. [28] J. T. Priti, O. Anjumanara and M. Rachel, "Audit of Antibiotic Prescribing Practices for Neonatal Sepsis and Measurement of Outcome in New Born Unit at Kenyatta National Hospital," International Journal of Pediatrics, 2019. [29] R. Kartik, M. Sahana, D. Prathiba and J. Malavika, "Evaluation of screening of neonatal sepsis," International Journal of Contemporary Pediatrics, vol. 5, no. 2, pp. 580-583, 2018. [30] J. M. Aaron, C. H. Mary, F. Daniel, O. Svetlana, S. Lakshmi, P. B. Christopher, B. Fran, S. Melissa and W. G. Robert, "Machine learning models for early sepsis recognition in the neonatal intensive care unit using readily available electronic health record data," PLoS ONE , vol. 14, no. 2, 2019. [31] E. H. Katharine, N. H. David, J. P. Peter and S. Suchi, "A targeted real-time early warning score (TREWScore) for septic shock," Science Translational Medicine, vol. 7 , no. 299, 2015. [32] R. Taylor, J. Pare and A. Venkatesh, "Prediction of In-hospital Mortality in Emergency Department Patients With Sepsis: A Local Big Data–Driven, Machine Learning Approach," Acad Emerg Med. , vol. 23, no. 3, p. 269–278., 2016. [33] T. Desautels, J. Calvert and J. Hoffman, "Prediction of Sepsis in the Intensive Care Unit With Minimal Electronic Health Record Data: A Machine Learning Approach," JMIR Med Inform. , vol. 4, no. 3, 2016. [34] J. K. Hye and Y. K. Ha, "Learning representations for the early detection of sepsis with deep neural networks," Computers in Biology and Medicine, 2017. [35] M. Moor, B. Rieck, M. Horn, C. Jutzeler and K. Borgwardt, "Early Prediction of Sepsis in the ICU using Machine Learning: A Systematic Review," medRxiv, vol. 8, no. 7, pp. 952-960, 2020. [36] A. A. D. T. J. M. C. G. P. I. J. C. M. Liberati and P. Devereaux, "The PRISMA statement for reporting systematic and meta-analyses of studies that evaluate interventions: explanation and elaboration.," PLoS Medicine, vol. 6, no. 7, pp. 1-28, 2009. [37] L. Mahieu, A. De Muynck, J. De Dooy, S. Laroche and K. Van Acker, "Prediction of nosocomial sepsis in neonates by means of a computer-weighted bedside scoring system (NOSEP score)," Critical care medicine, vol. 28, no. 6, pp. 2026-2033, 2000. [38] Y. Huang, X. Yu, W. Li, Y. Li, J. Yang, Z. Hu, Y. Wang, P. Chen, W. Li and Y. Chen, "Development and validation of a nomogram for predicting late-onset sepsis in preterm infants on the basis of thyroid function and other risk factors: Mixed retrospective and prospective cohort study," Journal of Advanced Research, vol. 24, pp. 43-51, 2020. [39] D. Lake, J. Richman, M. Griffin and J. Moorman, "Sample entropy analysis of neonatal heart rate variability," American Journal of Physiology-Regulatory, Integrative and Comparative Physiology, vol. 283, no. 3, pp. R789-R797, 2002. [40] K. Fairchild and T. O'Shea, "Heart rate characteristics: physiomarkers for detection of late-onset neonatal sepsis," Clinics in perinatology, vol. 37, no. 3, pp. 581-598, 2010. [41] Y. Xiao, M. Griffin, D. Lake and J. Moorman, "Nearest-neighbor and logistic regression analyses of clinical and heart rate characteristics in the early diagnosis of neonatal sepsis," Medical Decision Making, vol. 30, no. 2, pp. 258-266, 2010. [42] Y. Hu, V. Lee and K. Tan, "Prediction of clinicians' treatment in preterm infants with suspected late-onset sepsis—An ML approach. In 2018 13th IEEE conference on industrial electronics and applications (ICIEA)," IEEE, pp. 1177-1182, 2018. [43] R. Gómez, N. García, G. Collantes, F. Ponce and P. Redon, "Development of a non-invasive procedure to early detect neonatal sepsis using HRV monitoring and machine learning algorithms. In 2019 IEEE 32nd International Symposium on Computer-Based Medical Systems (CBMS)," IEEE, pp. 132-137, 2019. [44] M. Griffin, D. Lake and J. Moorman, "Heart rate characteristics and laboratory tests in neonatal sepsis," Pediatrics, vol. 115, no. 4, pp. 937-941, 2005. [45] M. Griffin, D. Lake, T. O'Shea and J. Moorman, "Heart rate characteristics and clinical signs in neonatal sepsis," Pediatric research, vol. 61, no. 2, pp. 222-227, 2007. [46] A. Herbst and K. Källén, "Time between membrane rupture and delivery and septicemia in term neonates," Obstetrics & gynecology, vol. 110, no. 3, pp. 612-618, 2007. [47] D. H. D. Van, S. Van Kuijk, B. Opmeer, C. Willekes, J. Van Beek, A. Mulder, A. Van Loon, M. Groenewout, G. Mantel, K. Bloemenkamp and M. Porath, "Can neonatal sepsis be predicted in late preterm premature rupture of membranes? Development of a prediction model," European Journal of Obstetrics & Gynecology and Reproductive Biology, vol. 176, pp. 90-95, 2014. [48] K. Fairchild, D. Lake, J. Kattwinkel, J. Moorman, D. Bateman, P. Grieve, J. Isler and R. Sahni, "Vital signs and their cross-correlation in sepsis and NEC: a study of 1,065 very-low-birth-weight infants in two NICUs," Pediatric research, vol. 81, no. 2, pp. 315-321, 2017. [49] J. Thakur, S. Pahuja and R. Pahuja, "Neonatal sepsis prediction model for resource-poor developing countries. In 2018 2nd International Conference on Electronics, Materials Engineering & Nano-Technology (IEMENTech)," IEEE., pp. 1-5, 2018. [50] A. Masino, M. Harris, D. Forsyth, S. Ostapenko, L. Srinivasan, C. Bonafide, F. Balamuth, M. Schmatz and R. Grundmeier, "Machine learning models for early sepsis recognition in the neonatal intensive care unit using readily available electronic health record data," PloS one, vol. 14, no. 2, p. e0212665, 2019. [51] J. Thakur, S. Pahuja and R. Pahuja, "Non-invasive prediction model for developing countries to predict SEPSIS in neonates," Biomedical Engineering: Applications, Basis and Communications, vol. 31, no. 1, p. 1950001, 2019. [52] L. Mithal, R. Yogev, H. Palac, D. Kaminsky, I. Gur and K. Mestan, "Vital signs analysis algorithm detects inflammatory response in premature infants with late onset sepsis and necrotizing enterocolitis.," Early human development, vol. 117, pp. 83-89, 2018. [53] I. Stanculescu, C. Williams and Y. Freer, "Autoregressive hidden Markov models for the early detection of neonatal sepsis," IEEE journal of biomedical and health informatics, vol. 18, no. 5, pp. 1560-1570, 2013. [54] S. Mani, A. Ozdas, C. Aliferis, H. Varol, Q. Chen, R. Carnevale, Y. Chen, J. Romano-Keeler, H. Nian and J. Weitkamp, "Medical decision support using machine learning for early detection of late-onset neonatal sepsis.," Journal of the American Medical Informatics Association, vol. 2, no. 21, pp. 326-336, 2014. [55] I. Güzey and Ö. Uçar, "Machine Learning Based Non-Invasive Vital Signs Analysis for Preterm Sepsis Risk Prediction," International Journal of Research in Engineering and Applied Sciences (IJREAS), vol. 8, no. 12, 2018. [56] W. Song, S. Jung, H. Baek, C. Choi, Y. Jung and S. Yoo, "A Predictive Model Based on Machine Learning for the Early Detection of Late-Onset Neonatal Sepsis: Development and Observational Study.," JMIR Medical Informatics, vol. 8, no. 7, p. 15965, 2020. [57] M. Beltempo, I. Viel-Thériault, R. Thibeault, A. Julien and B. Piedboeuf, "C-reactive protein for late-onset sepsis diagnosis in very low birth weight infants," BMC pediatrics, vol. 18, no. 1, p. 16, 2018. [58] T. Popowski, F. Goffinet, F. Maillard, T. Schmitz, S. Leroy and G. Kayem, "Maternal markers for detecting early-onset neonatal infection and chorioamnionitis in cases of premature rupture of membranes at or after 34 weeks of gestation: a two-center prospective study," BMC pregnancy and childbirth, vol. 11, no. 1, p. 26, 2011. [59] A. Palatnik, L. Liu, A. Lee and L. Yee, "Predictors of early-onset neonatal sepsis or death among newborns born at< 32 weeks of gestation," Journal of Perinatology, vol. 39, no. 7, pp. 949-955, 2019. [60] M. Griffin, T. O'Shea, E. Bissonette, F. Harrell, D. Lake and J. Moorman, "Abnormal heart rate characteristics preceding neonatal sepsis and sepsis-like illness," Pediatric research, vol. 53, no. 6, pp. 920-926, 2003. [61] I. Gur, A. Riskin, G. Markel, D. Bader, Y. Nave, B. Barzilay, F. Eyal and A. Eisenkraft, "Pilot study of a new mathematical algorithm for early detection of late-onset sepsis in very low-birth-weight infants," American journal of perinatology, vol. 32, no. 04, pp. 321-330, 2015. [62] J. Bekhof, J. Reitsma, J. Kok and I. Van Straaten, "Clinical signs to identify late-onset sepsis in preterm infants," European journal of pediatrics, vol. 172, no. 4, pp. 501-508, 2013. [63] S. Dutta, R. Reddy, S. Sheikh, J. Kalra, P. Ray and A. Narang, "Intrapartum antibiotics and risk factors for early onset sepsis," Archives of Disease in Childhood-Fetal and Neonatal Edition, vol. 95, no. 2, pp. 99-103, 2010. [64] M. Griffin and J. Moorman, "Toward the early diagnosis of neonatal sepsis and sepsis-like illness using novel heart rate analysis," Pediatrics, vol. 107, no. 1, pp. 97-104, 2001. [65] Y. Hu, V. Lee and K. Tan, "An application of convolutional neural networks for the early detection of late-onset neonatal sepsis. In 2019 International Joint Conference on Neural Networks (IJCNN)," IEEE., pp. 1-8, 2019. [66] D. Husada, P. Chanthavanich, U. Chotigeat, P. Sunttarattiwong, C. Sirivichayakul, K. Pengsaa, W. Chokejindachai and J. Kaewkungwal, "Predictive model for bacterial late-onset neonatal sepsis in a tertiary care hospital in Thailand," BMC infectious diseases, vol. 20, no. 1, pp. 1-11, 2020. [67] R. Rosenberg, A. Ahmed, S. Saha, M. Chowdhury, S. Ahmed, P. Law, R. Black, M. Santosham and G. Darmstadt, "Nosocomial sepsis risk score for preterm infants in low-resource settings," Journal of tropical pediatrics, vol. 56, no. 2, pp. 82-89, 2010. [68] A. Johnson, J. Aboab, J. Raffa, T. Pollard, R. Deliberato, L. Celi and D. Stone, "A comparative analysis of sepsis identification methods in an electronic database," Critical care medicine, vol. 46, no. 4, p. 494, 2018. [69] T. Saito and M. Rehmsmeier, "The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets," PloS one, vol. 10, no. 3, p. e0118432, 2015. [70] E. Pinker, "Reporting accuracy of rare event classifiers," NPJ digital medicine, vol. 1, no. 1, pp. 1-2, 2018. Tables Tables 6-10 and 12 are in the supplementary files section. Supplementary Files Tables.docx Tables 6-10, 12 Cite Share Download PDF Status: Posted Version 2 posted You are reading this latest preprint version Show more versions Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-1354764","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Systematic Review","associatedPublications":[],"authors":[{"id":84889471,"identity":"ae6e0827-eae0-45a7-93d0-73a359737f94","order_by":0,"name":"Dennis Peace Ezeobi","email":"data:image/png;base64,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","orcid":"https://orcid.org/0000-0003-2573-3414","institution":"Mbarara University of Science and Technology","correspondingAuthor":true,"submittingAuthor":false,"prefix":"","firstName":"Dennis","middleName":"Peace","lastName":"Ezeobi","suffix":""},{"id":84889473,"identity":"1d6095ab-b40b-464e-9dec-f5cabf4e5d98","order_by":1,"name":"Dr. Angella Musiimenta","email":"","orcid":"","institution":"Mbarara University of Science and Technology","correspondingAuthor":false,"submittingAuthor":false,"prefix":"Dr.","firstName":"Angella","middleName":"","lastName":"Musiimenta","suffix":""},{"id":84889472,"identity":"cb596b47-c185-4eca-a63d-34a92067896b","order_by":2,"name":"Dr. William Wasswa","email":"","orcid":"","institution":"Mbarara University of Science and Technology","correspondingAuthor":false,"submittingAuthor":false,"prefix":"Dr.","firstName":"William","middleName":"","lastName":"Wasswa","suffix":""},{"id":84889474,"identity":"d1ea3749-7f59-40c5-a501-7881b4ca75ef","order_by":3,"name":"Dr. Stella Kyoyagala","email":"","orcid":"","institution":"Mbarara Regional Referral Hospital","correspondingAuthor":false,"submittingAuthor":false,"prefix":"Dr.","firstName":"Stella","middleName":"","lastName":"Kyoyagala","suffix":""}],"badges":[],"createdAt":"2022-02-13 07:54:17","currentVersionCode":2,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false,"coiExplicitlySet":false},"doi":"10.21203/rs.3.rs-1354764/v2","doiUrl":"https://doi.org/10.21203/rs.3.rs-1354764/v2","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":30995573,"identity":"ddbce016-804b-4dba-a706-f6dc3ced01a8","added_by":"auto","created_at":"2023-01-03 01:38:40","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":87510,"visible":true,"origin":"","legend":"\u003cp\u003ePRISMA flow diagram showing the search strategy and identified articles [36]\u003c/p\u003e","description":"","filename":"1.png","url":"https://assets-eu.researchsquare.com/files/rs-1354764/v2/e7108bdad12559647b01de59.png"},{"id":30995793,"identity":"290bc64a-fa33-4b38-9a21-1f583cada235","added_by":"auto","created_at":"2023-01-03 01:46:51","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":564377,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-1354764/v2/3accdb97-ffd6-425d-888b-2947a569248b.pdf"},{"id":30995792,"identity":"ee628592-1cf1-4f68-8853-317d99f19a3a","added_by":"auto","created_at":"2023-01-03 01:46:40","extension":"docx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":188538,"visible":true,"origin":"","legend":"\u003cp\u003eTables 6-10, 12\u003c/p\u003e","description":"","filename":"Tables.docx","url":"https://assets-eu.researchsquare.com/files/rs-1354764/v2/f0cf9f64cf175b0c452597e5.docx"}],"financialInterests":"","formattedTitle":"\u003cp\u003eEvaluation of screening parameters and machine learning models for the prediction of neonatal sepsis: A systematic review\u003c/p\u003e","fulltext":[{"header":"Introduction","content":"\u003cp\u003eAbout 2.4\u0026nbsp;million neonates die every year worldwide, and most of these deaths occur in low resource settings [1] [2]. The third Sustainable Development Goal (SDG) for child health aims to end the mortality of newborns and children under five years of age, which is preventable by 2030. However, this may not be achieved if there is no significant reduction of neonatal deaths directly related to infection in developing countries [3]. Sepsis is a significant cause of neonatal mortality and morbidity around the world [4] [5] [6] and most of the morbidity and mortality from sepsis is preventable.\u003c/p\u003e \u003cp\u003eNeonatal sepsis is classified as early-onset (\u0026lt;\u0026thinsp;48\u0026ndash;72h) and late-onset sepsis (\u0026gt;\u0026thinsp;48\u0026ndash;72h), and this depends on the age at onset [7] [8]. About 30\u0026ndash;50% of neonatal sepsis survivors obtain significant long-term impairments, including prolonged hospitalization, chronic lung disease, and neurodevelopmental disabilities [9] [10] [11]. Sepsis remains one of the most expensive causes of hospitalization, as recent data highlight its costs and burdens [12] [13] [14] [15]. Physicians caring for infected neonates are faced with multiple challenges in diagnostic and treatment decisions. Despite the increased understanding of its pathophysiology and efforts to improve clinical decision support in intensive care, there have been just fair improvements in neonatal sepsis outcomes [16]. Neonatal sepsis occurs when there is a bacterial invasion in the bloodstream; the immune system begins a systemic inflammatory response syndrome (SIRS), which is damaging to the body and can quickly advance to severe sepsis, multi-organ failure, and finally, death [17] [18]. However, early recognition and prompt treatment have been predicted to improve the clinical management of sepsis and serve as the key to reducing morbidity and mortality [19] [20] [21] [22] [23].\u003c/p\u003e \u003cp\u003eDelays in recognition and treatment of sepsis is still a challenge despite the explored importance of early intervention [6] [16] [24] [25] [26] [27] [28]. Neonatal clinical presentation is non-specific and overlaps with other newborn disease processes. The laboratory tests have limited diagnostic accuracy, which makes rapid diagnosis for neonatal sepsis difficult. The standard gold test for neonatal sepsis diagnosis, blood culture, faces the challenge of insufficient blood volume for blood culture and low amount of invading microorganisms in the blood, which usually generates false-negative results [29] [30]. Infants suspected of having sepsis are subjected to prolonged antibiotic therapy despite negative cultures. In other to tackle the challenges associated with sepsis recognition and care management studies are making use of machine learning and statistical modeling approaches [31] [32] [33] [34].\u003c/p\u003e \u003cp\u003eCompared to other significant conditions, neonatal sepsis receives less substantial international investment as a public health priority despite the heavy burden of newborn deaths related to neonatal sepsis [3]. Knowledge of neonatal sepsis's predictor variables, early identification, and early interventions can reduce neonatal mortality and morbidity rates. This study aims to review the existing screening parameters and models based on their diagnostic performance, strength, and weaknesses to better understand the algorithm development process.\u003c/p\u003e"},{"header":"Materials And Methods","content":"\u003cp\u003e\u003cstrong\u003eSelection of screening parameters for analysis\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eA preliminary examination of the available literature was carried out, after which a list of parameters was consolidated for further review. These parameters were selected based on their publication and their potential for diagnosing and prognosis of neonatal sepsis. The parameters include;\u003c/p\u003e\n\u003cul\u003e\n \u003cli\u003eMaternal risk factors (which include; intrapartum fever, chorioamnionitis, postnatal distress, duration of ROM, GBS colonization, and intrapartum antibiotics).\u003c/li\u003e\n \u003cli\u003eNeonatal clinical signs (which include; gestational age, birth weight, heart rate, and feeding difficulty).\u003c/li\u003e\n \u003cli\u003eLaboratory tests (which include; absolute neutrophil count, C reactive protein, I/T ratio, micro-ESR, platelet count, and total leukocyte count).\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eSearch Strategies\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eIn order to carry out a landscape analysis to identify studies with the diagnostic performance of the previously mentioned parameters, PubMed, IEEE, and Cochrane\u0026apos;s bibliography database were searched. The search strategies for the databases were carefully made to give maximum output. A combination of text words was used to develop the search strategy, which includes; \u0026quot;neonatal sepsis\u0026quot; AND \u0026quot;prediction\u0026quot; AND \u0026quot;machine learning\u0026quot;, \u0026quot;neonatal sepsis\u0026quot; AND \u0026quot;prediction\u0026quot; AND \u0026quot;EHR\u0026quot;, \u0026quot;neonatal sepsis\u0026quot; AND \u0026quot;prediction\u0026quot; AND \u0026quot;model\u0026quot;, \u0026quot;neonatal sepsis\u0026quot; AND \u0026quot;prediction\u0026quot; AND \u0026quot;algorithm\u0026quot;, \u0026quot;neonatal sepsis\u0026quot; AND \u0026quot;diagnostic algorithm\u0026quot; AND \u0026quot;machine learning\u0026quot;, \u0026quot;neonatal sepsis\u0026quot; AND \u0026quot;screening parameters\u0026quot; AND \u0026quot;models\u0026quot;, \u0026quot;neonatal sepsis\u0026quot; AND \u0026quot;screen\u0026quot; AND \u0026quot;models\u0026quot;. The search strategy was restricted to the subject (humans) and the time period (January 2000 to April 2020). A total of 463 PubMed, 305 citations from IEEE, and 86 Cochrane citations from Cochrane were retrieved. These references were imported as separate files into an excel sheet except for the Cochrane database\u0026apos;s references; it was imported only as CSV file. The duplicates were removed, the titles and abstracts of the retrieved citations were screened to find the articles relevant to the study. Additional relevant studies were retrieved by scrutinizing the bibliography of searched studies.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eInclusion Criteria\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eFor the inclusion of articles, the abstract and titles were screened based on the following predetermined criteria:\u0026nbsp;\u003c/p\u003e\n\u003cul\u003e\n \u003cli\u003eThe subject population are neonates.\u003c/li\u003e\n \u003cli\u003eSubjects have culture-proved sepsis or suspected sepsis based on a clinical algorithm.\u003c/li\u003e\n \u003cli\u003eThe article evaluated any of the consolidated screening parameters and algorithms/models for neonatal sepsis diagnosis or prognosis.\u0026nbsp;\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003eThe exhaustive search based on the titles and abstracts returned a broad spectrum of infection-related studies from which only cases of neonatal sepsis were considered. Finally, full-text articles with the following criteria were included for analysis:\u0026nbsp;\u003c/p\u003e\n\u003cul\u003e\n \u003cli\u003eThe subject population are neonates.\u003c/li\u003e\n \u003cli\u003eThe study provided a clear definition of neonatal sepsis.\u003c/li\u003e\n \u003cli\u003eThe study provides neonatal sepsis onset definition (i.e., time of onset).\u003c/li\u003e\n \u003cli\u003eThe study clearly described the predictor variables used.\u003c/li\u003e\n \u003cli\u003eThe study clearly described the machine learning models used or evaluated in any of the consolidated screening parameters.\u003c/li\u003e\n \u003cli\u003eThe study must have provided diagnostic performance results (i.e., AUROC results).\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003e\u003cstrong\u003eExclusion Criteria\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eIt was a great challenge trying to select the relevant articles for this review from the large number of papers retrieved (n=854) based on the selection criteria. To make a comprehensive list of appropriate papers, articles that did not deal with neonates, duplicates, reviews, meta-analyses, abstracts, editorials, and commentaries were excluded.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eData Extraction\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe available full papers were downloaded from PubMed, IEEE, and Cochrane sources. The data was extracted and compiled in an Excel spreadsheet. The following information was extracted from all the studies:\u0026nbsp;\u003c/p\u003e\n\u003col start=\"1\" style=\"list-style-type: lower-alpha;\"\u003e\n \u003cli\u003ePublication characteristics (author\u0026rsquo;s name, year of publication).\u003c/li\u003e\n \u003cli\u003eStudy design (retrospective, prospective data collection and analysis).\u003c/li\u003e\n \u003cli\u003eSelection of cohorts (sex, age, number of patients with sepsis, prevalence of sepsis).\u003c/li\u003e\n \u003cli\u003eNeonatal sepsis definition.\u003c/li\u003e\n \u003cli\u003eNeonatal sepsis onset definition.\u003c/li\u003e\n \u003cli\u003eSpecifics on analyzed data (the type of variables, number of screening parameters).\u003c/li\u003e\n \u003cli\u003eModel selection (ML algorithm, platforms, software, packages, and hyperparameters).\u003c/li\u003e\n \u003cli\u003eStatistics for the performance model (methods for evaluating the model, statistical significance, handling of missing data).\u003c/li\u003e\n \u003cli\u003eMethods to avoid overfitting and also any additional external validation approaches.\u003c/li\u003e\n\u003c/ol\u003e\n\u003cp\u003eFor a point of reference, the leading hospital in Mbarara, Uganda, was contacted to learn what tests/algorithms are currently being used in their clinical settings.\u003c/p\u003e\n\u003cp\u003e\u003cstrong id=\"isPasted\"\u003eQuality Assessment of the Included Studies\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cbr\u003e\u003c/p\u003e\n\u003cp id=\"isPasted\" style='margin-top:0in;margin-right:0in;margin-bottom:8.0pt;margin-left:0in;line-height:115%;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cspan style='font-size:16px;line-height:115%;font-family:\"Times New Roman\",serif;'\u003eTable 1: Quality assessment of the included studies.\u003c/span\u003e\u003c/p\u003e\n\u003ctable style=\"width: 5.0e+2pt;margin-left:-.25pt;border-collapse:collapse;border:none;\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 88.1pt;border: 1pt solid windowtext;padding: 0in 5.4pt;height: 14pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eCategories\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 150.4pt;border-color: windowtext windowtext windowtext currentcolor;border-style: solid solid solid none;border-width: 1pt 1pt 1pt medium;border-image: none 100% / 1 / 0 stretch;padding: 0in 5.4pt;height: 14pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eItems\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 202.5pt;border-color: windowtext windowtext windowtext currentcolor;border-style: solid solid solid none;border-width: 1pt 1pt 1pt medium;border-image: none 100% / 1 / 0 stretch;padding: 0in 5.4pt;height: 14pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eDescription\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 58.5pt;border-color: windowtext windowtext windowtext currentcolor;border-style: solid solid solid none;border-width: 1pt 1pt 1pt medium;border-image: none 100% / 1 / 0 stretch;padding: 0in 5.4pt;height: 14pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eReported\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 88.1pt;border-color: currentcolor windowtext windowtext;border-style: none solid solid;border-width: medium 1pt 1pt;border-image: none 100% / 1 / 0 stretch;padding: 0in 5.4pt;height: 14pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eUnmet needs\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 150.4pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 14pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eLimits in current machine learning or non-machine learning\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eApplications\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 202.5pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 14pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eLow diagnostic accuracy, low human-level prediction accuracy, or prolonged diagnostic procedure.\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 58.5pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 14pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eYes/No\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"7\" style=\"width: 88.1pt;border-color: currentcolor windowtext windowtext;border-style: none solid solid;border-width: medium 1pt 1pt;border-image: none 100% / 1 / 0 stretch;padding: 0in 5.4pt;height: 14pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eReproducibility\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 150.4pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 14pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003ePrevalence of Neonatal sepsis\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 202.5pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 14pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eThe proportion of neonates who suffered sepsis out of the entire study cohort.\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 58.5pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 14pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eYes/No\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 150.4pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 14pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eData availability\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 202.5pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 14pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eIs the data used in the study publicly available?\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 58.5pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 14pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eYes/No\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 150.4pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 14pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eFeature engineering methods\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 202.5pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 14pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eHow features were generated before model training\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 58.5pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 14pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eYes/No\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 150.4pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 14pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eCode for data wrangling and analysis\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 202.5pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 14pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eCode describing the details of the cleaning, preprocessing, and analysis of the data.\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 58.5pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 14pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eYes/No\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 150.4pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 14pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eCode of label\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 202.5pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 14pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eCode describing neonatal sepsis label generation\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 58.5pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 14pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eYes/No\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 150.4pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 14pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003ePlatforms/packages\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 202.5pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 14pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eBoth platforms and packages should be reported\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 58.5pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 14pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eYes/No\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 150.4pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 14pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eHyperparameters\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 202.5pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 14pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eAll hyperparameters which are needed for study replication\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 58.5pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 14pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eYes/No\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"3\" style=\"width: 88.1pt;border-color: currentcolor windowtext windowtext;border-style: none solid solid;border-width: medium 1pt 1pt;border-image: none 100% / 1 / 0 stretch;padding: 0in 5.4pt;height: 14pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eRobustness\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 150.4pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 14pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eSample size \u0026gt; 50\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 202.5pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 14pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eNeonatal sepsis case sample size \u0026gt;50 is required for the interpretation, power, and validity of machine learning methods.\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 58.5pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 14pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eYes/No\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 150.4pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 14pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eValid methods for over-fitting\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 202.5pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 14pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eValid methods for unbiased performance assessment (or methods \u0026quot;against\u0026quot; overfitting)\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 58.5pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 14pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eYes/No\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 150.4pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 14pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eStability of results\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 202.5pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 14pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eCalculated variation in the validation statistics\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 58.5pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 14pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eYes/No\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 88.1pt;border-color: currentcolor windowtext windowtext;border-style: none solid solid;border-width: medium 1pt 1pt;border-image: none 100% / 1 / 0 stretch;padding: 0in 5.4pt;height: 14pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eGeneralizability\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 150.4pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 14pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eExternal data validation\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 202.5pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 14pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eValidation in settings different from the research framework\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 58.5pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 14pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eYes/No\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"2\" style=\"width: 88.1pt;border-color: currentcolor windowtext windowtext;border-style: none solid solid;border-width: medium 1pt 1pt;border-image: none 100% / 1 / 0 stretch;padding: 0in 5.4pt;height: 14pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eClinical significance\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 150.4pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 14pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003ePredictor\u0026rsquo;s explanation\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 202.5pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 14pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eExplanation (biological or quantification) of the importance of each predictor\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 58.5pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 14pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eYes/No\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 150.4pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 14pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eSuggested clinical use\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 202.5pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 14pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eClinical usability and requirements (e.g. what are still necessary for making deployment possible)\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 58.5pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 14pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cspan style='font-size:16px;font-family: \"Times New Roman\",serif;'\u003eYes/No\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003e\u003cbr\u003e\u003c/p\u003e\n\u003cp\u003eThe quality of the selected ML studies was assessed based on 14 criteria relevant to the objectives of the review, which was adopted from [35]. The assessment consists of five categories described in table 1 above. A quality assessment table was provided by listing \u0026quot;yes\u0026quot; or \u0026quot;no\u0026quot; for each category\u0026apos;s items using the provided criteria.\u003c/p\u003e"},{"header":"Results","content":"\u003cp\u003eOut of 854 studies, 31 studies met the inclusion criteria. The literature search results with reasons for exclusions at each stage are presented in figure 1 above.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eStudy Characteristics\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eOf the 31 included studies, 16 employed solely prospective analyses, 13 employed solely retrospective analyses, while 2 studies used both retrospective and prospective analyses [37, 38]. The most frequent data sources used in the studies were the University of Virginia Hospital (n = 8; 26%), followed by MIMIC-III (n = 3; 10%). In terms of neonatal sepsis definition, the majority of the studies employed Blood culture (n = 26; 84%) or Observational condition (use of clinical signs) (n = 16; 52%) or combination of Blood culture and Observational condition (n = 12; 39%). The studies modified observational and Laboratory definitions based on available data and the predetermined neonatal sepsis onset time; this is mainly due to the absence of a consensus definition of neonatal sepsis. The prevalence of neonates with sepsis ranged between 0.27% and 87.0%. Five studies did not report the prevalence [39, 40, 41, 42, 43]. Regarding the category of neonatal sepsis of interest, the category with a high focus is late-onset (n = 18; 58%) and early-onset (n = 4; 13%). While 9 studies [39, 44, 45, 46, 47, 48, 49, 50, 51] did not report the category of focus. In demographics, 6 studies reported the median or mean age of the neonates, 11 reported the prevalence of male neonates, 2 reported the prevalence of female neonates, and only 3 reported the investigated cohorts\u0026apos; ethnicity (see supplementary table 1).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eOverview of Machine Learning Algorithms and Variables\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eA wide range of ML algorithms has been employed to build models for the early detection of neonatal sepsis, with some models being specific to the study population. Regression was the most used model of which various types (n = 25; 81%) were used. This includes Logistic Regression or Linear Regression [52]. Furthermore, boosted tree models were the second most used model (n = 6; 19%), including gradient boosting\n \u003c!--[if supportFields]\u003e\u003cspan\n style='mso-bookmark:_Hlk53404614'\u003e\u003c/span\u003e\u003cspan style='mso-element:field-begin'\u003e\u003c/span\u003e\u003cspan\n style='mso-bookmark:_Hlk53404614'\u003e\u003cspan style='mso-no-proof:yes'\u003eCITATION\n Placeholder4 \\l 1033 \u003cspan style='mso-element:field-separator'\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c![endif]--\u003e[42]\n \u003c!--[if supportFields]\u003e\u003cspan\n style='mso-bookmark:_Hlk53404614'\u003e\u003c/span\u003e\u003cspan style='mso-element:field-end'\u003e\u003c/span\u003e\u003c![endif]--\u003e, or random forest\u0026nbsp;[43]. And lastly SVM\n \u003c!--[if supportFields]\u003e\u003cspan\n style='mso-element:field-begin'\u003e\u003c/span\u003eCITATION Placeholder4 \\l 1033 \u003cspan\n style='mso-element:field-separator'\u003e\u003c/span\u003e\u003c![endif]--\u003e [42]\n \u003c!--[if supportFields]\u003e\u003cspan\n style='mso-element:field-end'\u003e\u003c/span\u003e\u003c![endif]--\u003e (n = 5; 16%). Most of the studies (n = 24; 77%) arbitrarily chose one- or two-ML models without arguing the reasons. Seven studies (23%) [53, 54, 55, 42, 43, 50, 56] compared several models and identified the one with the best performance.\u003c/p\u003e\n\u003cp\u003eAs for the analyzed variables, the most common variable used was neonatal clinical signs (n = 28; 90%), followed by laboratory tests (n = 10; 32%), and maternal risk characteristics (n = 5; 19%). Sixteen studies (52%) were found to use one variable, while the remaining fifteen studies (48%) were found to combine these variables, which includes neonatal clinical signs and laboratory tests (n = 10; 32%), maternal risk characteristics, and neonatal clinical signs (n = 5; 16%). None of the studies were found to explore the combination of maternal risk characteristics, neonatal clinical signs, and laboratory tests. The number of screening parameters included in the respective models ranged between 2 [57] and 22\n \u003c!--[if supportFields]\u003e\u003cspan style='mso-element:\n field-begin'\u003e\u003c/span\u003eCITATION Mas19 \\l 1033 \u003cspan style='mso-element:field-separator'\u003e\u003c/span\u003e\u003c![endif]--\u003e[50]\n \u003c!--[if supportFields]\u003e\u003cspan\n style='mso-element:field-end'\u003e\u003c/span\u003e\u003c![endif]--\u003e. Concerning the features for detecting neonatal sepsis, the reviewed studies show that duration of ROM was found to be more significant than other maternal risk factors [46, 58, 50, 59]. Heart rate and heart rate variability were found to be more significant than other neonatal clinical signs [40, 43]. C reactive protein and I/T ratio were found to be more significant than other laboratory tests [45, 57].\u003c/p\u003e\n\u003cp\u003e\u003cbr\u003e\u003c/p\u003e\n\u003cp id=\"isPasted\" style='margin-top:0in;margin-right:0in;margin-bottom:8.0pt;margin-left:0in;line-height:115%;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cspan style='font-size:16px;line-height:115%;font-family:\"Times New Roman\",serif;'\u003eTable 2: Pseudo code for the HRV monitoring algorithm\u003c/span\u003e\u003c/p\u003e\n\u003cp style='margin-top:0in;margin-right:0in;margin-bottom:8.0pt;margin-left:0in;line-height:107%;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cstrong\u003e\u003cspan style='font-size:16px;line-height:107%;font-family:\"Times New Roman\",serif;'\u003eHRV Monitoring Algorithm for Neonatal sepsis\u003c/span\u003e\u003c/strong\u003e\u003cspan style='font-size:16px;line-height:107%;font-family:\"Times New Roman\",serif;'\u003e\n \u003c!--[if supportFields]\u003e\u003cspan style='mso-element:field-begin'\u003e\u003c/span\u003eCITATION\n Placeholder3 \\l 1033 \u003cspan style='mso-element:field-separator'\u003e\u003c/span\u003e\u003c![endif]--\u003e [43]\n \u003c!--[if supportFields]\u003e\u003cspan\n style='mso-element:field-end'\u003e\u003c/span\u003e\u003c![endif]--\u003e\u003c/span\u003e\u003c/p\u003e\n\u003ctable style=\"margin-left:.75pt;border-collapse:collapse;border:none;\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 466.5pt;border-color: windowtext currentcolor;border-style: solid none;border-width: 1.5pt medium;padding: 0in 5.4pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cstrong\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eStep 1:\u0026nbsp;\u003c/span\u003e\u003c/strong\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eCreate a set H of 17 heart rate variability, H = (v\u003csub\u003e0\u003c/sub\u003e\u0026hellip;v\u003csub\u003ed\u003c/sub\u003e), 1 \u0026le; d \u0026le; 17\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cstrong\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eStep 2:\u0026nbsp;\u003c/span\u003e\u003c/strong\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eInitialize elements of set H; T = (c\u003csub\u003e0\u003c/sub\u003e\u0026hellip; c\u003cstrong\u003e\u003csub\u003eⅈ\u003c/sub\u003e\u003c/strong\u003e), 1 \u0026le; \u003cstrong\u003eⅈ\u003c/strong\u003e\u0026le; 17\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cstrong\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eStep 3:\u003c/span\u003e\u003c/strong\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;Check result of the time, frequency and non-linear analysis in elements of set T\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:.5in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;text-indent:.5in;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eIF \u003cstrong\u003eⅈ\u0026nbsp;\u003c/strong\u003eis defined as \u0026ldquo;Absolute\u0026rdquo; THEN\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:1.0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;text-indent:.5in;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eRETURN True\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:.5in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;text-indent:.5in;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eELSE\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:1.0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;text-indent:.5in;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eRETURN False\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:.5in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;text-indent:.5in;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eEND IF\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cstrong\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eStep 4:\u003c/span\u003e\u003c/strong\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;IF number of Absolute is defined as \u0026ldquo;High\u0026rdquo; THEN\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:.5in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;text-indent:.5in;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eRETURN \u0026ldquo;Neonatal Sepsis\u0026rdquo;\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;text-indent: .5in;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eELSE\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:.5in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;text-indent:.5in;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eRETURN \u0026ldquo;Normal\u0026rdquo;\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-indent:.5in;'\u003e\u003cspan style='font-size:16px;font-family: \"Times New Roman\",serif;'\u003eEND IF\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003e\u003cbr\u003e\u003c/p\u003e\n\u003cp id=\"isPasted\" style='margin-top:0in;margin-right:0in;margin-bottom:8.0pt;margin-left:0in;line-height:107%;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:16px;line-height:107%;font-family:\"Times New Roman\",serif;'\u003eTable 3: Phase I: Pseudo code for the observational condition\u003c/span\u003e\u003c/p\u003e\n\u003cp style='margin-top:0in;margin-right:0in;margin-bottom:8.0pt;margin-left:0in;line-height:107%;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cstrong\u003e\u003cspan style='font-size:16px;line-height:107%;font-family:\"Times New Roman\",serif;'\u003eMedical Decision Support Algorithm for Neonatal sepsis \u003cspan style=\"font-weight: normal;\"\u003e[54]\u003c/span\u003e\u003c/span\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp style='margin-top:0in;margin-right:0in;margin-bottom:8.0pt;margin-left:0in;line-height:107%;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cspan style='font-size:16px;line-height:107%;font-family:\"Times New Roman\",serif;'\u003eThe algorithm consists of three phases: observational condition, laboratory condition, and neonatal sepsis.\u003c/span\u003e\u003c/p\u003e\n\u003ctable style=\"margin-left:.75pt;border-collapse:collapse;border:none;\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 466.5pt;border-color: windowtext currentcolor;border-style: solid none;border-width: 1.5pt medium;padding: 0in 5.4pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cstrong\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eStep 1:\u0026nbsp;\u003c/span\u003e\u003c/strong\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eCreate a tuple Z of 4 neonatal clinical signs, Z = (w\u003csub\u003e0\u003c/sub\u003e\u0026hellip;w\u003csub\u003ex\u003c/sub\u003e), 1 \u0026le; x \u0026le; 4\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cstrong\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eStep 2:\u0026nbsp;\u003c/span\u003e\u003c/strong\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eInitialize elements of tuple Z; U = (d\u003csub\u003e0\u003c/sub\u003e\u0026hellip; d\u003csub\u003ej\u003c/sub\u003e), 1 \u0026le; j \u0026le; 4\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cstrong\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eStep 3:\u003c/span\u003e\u003c/strong\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;FOR each j in U DO\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:.5in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;text-indent:.5in;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eIF j \u003cstrong\u003e= =\u003c/strong\u003e condition THEN\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:1.0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;text-indent:.5in;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eRETURN True\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:.5in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;text-indent:.5in;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eELSE\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:1.0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;text-indent:.5in;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eRETURN False\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:.5in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;text-indent:.5in;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eEND IF\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;text-indent: .5in;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eEND FOR\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cstrong\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eStep 4:\u003c/span\u003e\u003c/strong\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;IF True \u0026ge; 1\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:.5in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;text-indent:.5in;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eRETURN \u0026ldquo;Observational Condition\u0026rdquo;\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;text-indent: .5in;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eELSE\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:.5in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;text-indent:.5in;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eRETURN \u0026ldquo;No Observational Condition\u0026rdquo;\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;text-indent: .5in;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eEND IF\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp style='margin-top:0in;margin-right:0in;margin-bottom:8.0pt;margin-left:0in;line-height:107%;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:16px;line-height:107%;font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n\u003cp style='margin-top:0in;margin-right:0in;margin-bottom:8.0pt;margin-left:0in;line-height:107%;font-size:15px;font-family:\"Calibri\",sans-serif;text-indent:.5in;'\u003e\u003cspan style='font-size:16px;line-height:107%;font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n\u003cp style='margin-top:0in;margin-right:0in;margin-bottom:8.0pt;margin-left:0in;line-height:107%;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:16px;line-height:107%;font-family:\"Times New Roman\",serif;'\u003eTable 4: Phase II: Pseudo code for the laboratory condition\u003c/span\u003e\u003c/p\u003e\n\u003ctable style=\"margin-left:.75pt;border-collapse:collapse;border:none;\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 466.5pt;border-color: windowtext currentcolor;border-style: solid none;border-width: 1.5pt medium;padding: 0in 5.4pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cstrong\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eStep 1:\u0026nbsp;\u003c/span\u003e\u003c/strong\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eCreate a tuple Q of 5 laboratory tests, Q = (p\u003csub\u003e0\u003c/sub\u003e\u0026hellip; p\u003csub\u003ec\u003c/sub\u003e), 1 \u0026le; c \u0026le; 5\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cstrong\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eStep 2:\u0026nbsp;\u003c/span\u003e\u003c/strong\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eInitialize elements of tuple Q; X = (f\u003csub\u003e0\u003c/sub\u003e\u0026hellip; f\u003csub\u003ek\u003c/sub\u003e), 1 \u0026le; k \u0026le; 5\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cstrong\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eStep 3:\u003c/span\u003e\u003c/strong\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;FOR each k in X DO\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:.5in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;text-indent:.5in;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eIF k \u003cstrong\u003e= =\u003c/strong\u003e condition THEN\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:1.0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;text-indent:.5in;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eRETURN True\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:.5in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;text-indent:.5in;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eELSE\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:1.0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;text-indent:.5in;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eRETURN False\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:.5in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;text-indent:.5in;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eEND IF\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;text-indent: .5in;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eEND FOR\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cstrong\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eStep 4:\u003c/span\u003e\u003c/strong\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;IF True \u0026ge; 1\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:.5in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;text-indent:.5in;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eRETURN \u0026ldquo;Laboratory Condition\u0026rdquo;\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;text-indent: .5in;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eELSE\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:.5in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;text-indent:.5in;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eRETURN \u0026ldquo;No Laboratory Condition\u0026rdquo;\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-indent:.5in;'\u003e\u003cspan style='font-size:16px;font-family: \"Times New Roman\",serif;'\u003eEND IF\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp style='margin-top:0in;margin-right:0in;margin-bottom:8.0pt;margin-left:0in;line-height:107%;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:16px;line-height:107%;font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n\u003cp style='margin-top:0in;margin-right:0in;margin-bottom:8.0pt;margin-left:0in;line-height:107%;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:16px;line-height:107%;font-family:\"Times New Roman\",serif;'\u003eTable 5: Phase III: Pseudo code for the neonatal sepsis\u003c/span\u003e\u003c/p\u003e\n\u003ctable style=\"margin-left:.75pt;border-collapse:collapse;border:none;\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 466.5pt;border-color: windowtext currentcolor;border-style: solid none;border-width: 1.5pt medium;padding: 0in 5.4pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cstrong\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eStep 1:\u0026nbsp;\u003c/span\u003e\u003c/strong\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eCreate a set R of 3 neonatal sepsis variables, R = (d\u003csub\u003e0\u003c/sub\u003e\u0026hellip; d\u003csub\u003ea\u003c/sub\u003e), 1 \u0026le; a \u0026le; 3\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cstrong\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eStep 2: \u0026nbsp;\u003c/span\u003e\u003c/strong\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eInitialize elements of set R; L = (g\u003csub\u003e0\u003c/sub\u003e\u0026hellip; g\u003csub\u003ey\u003c/sub\u003e), 1 \u0026le; y \u0026le; 3\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cstrong\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eStep 3:\u003c/span\u003e\u003c/strong\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;FOR each yin L DO\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:.5in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;text-indent:.5in;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eIF y = = \u0026ldquo;Yes\u0026rdquo; THEN\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:1.0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;text-indent:.5in;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eRETURN True\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:.5in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;text-indent:.5in;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eELSE\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:1.0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;text-indent:.5in;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eRETURN False\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:.5in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;text-indent:.5in;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eEND IF\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;text-indent: .5in;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eEND FOR\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;'\u003e\u003cstrong\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eStep 4:\u003c/span\u003e\u003c/strong\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;IF True = = 3\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:.5in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;text-indent:.5in;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eRETURN \u0026ldquo;Septic\u0026rdquo;\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;text-indent: .5in;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eELSE\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:.5in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-align:justify;text-indent:.5in;'\u003e\u003cspan style='font-size:16px;font-family:\"Times New Roman\",serif;'\u003eRETURN \u0026ldquo;Not Septic\u0026rdquo;\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height: normal;font-size:15px;font-family:\"Calibri\",sans-serif;text-indent:.5in;'\u003e\u003cspan style='font-size:16px;font-family: \"Times New Roman\",serif;'\u003eEND IF\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003e\u003cbr\u003e\u003c/p\u003e\n\u003cp id=\"isPasted\"\u003eSome of the existing neonatal sepsis prediction algorithms using neonatal clinical signs and maternal risk factors are shown below in tables 2, 3, 4, and 5.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eModel Validation\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eApproximately 58% of the studies did not report what valid methods were used to prevent overfitting, while 29% employed cross-validation technique (e.g., 4-fold, 5-fold, 10-fold, or leave-one-out cross-validation), and 19% employed bootstrap to avoid overfitting. Concerning the models\u0026apos; limitations, 13% of the studies recommend that the models require additional variables to optimize their performance. Additional external validation of the models was only performed in seven studies\u0026nbsp;[60, 44, 40, 58, 61, 48, 38]. Particularly, Fairchild \u0026amp; O\u0026apos;Shea (2010) used datasets from University of Virginia NICU and Wake Forest University NICU to train, test, and validate the use of neonatal heart rate characteristics (HRC) to detect late-onset (LOS) neonatal sepsis. In another study, Fairchild et al. (2017) explored the use of vital signs to build models that predict neonatal sepsis using datasets from the University of Virginia, UVA, and Columbia University. Gur et al. (2015) trained, tested, and validated the RALIS algorithm\u0026apos;s ability to detect LOS before clinical suspicion with datasets from neonatal intensive care units (NICU) of three hospitals in Israel. Aiming to develop and validate a nomogram for assessing the individual prior probability of LOS based on maternal risk factors and neonatal clinical signs in preterm infants, Huang et al. (2020) created a validation cohort using data from three neonatal critical care centers in Guangdong province of China. Lastly, the study by Popowski et al. (2011) investigated the predictive value of maternal risk factors for early-onset (EOS) neonatal sepsis using a dataset from two French tertiary university referral centers.\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eQuality Assessment of Included Studies\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cbr\u003e\u003c/p\u003e\n\u003cp\u003e[Table 6 is in the supplementary files section.]\u003c/p\u003e\n\u003cp\u003e\u003cbr\u003e\u003c/p\u003e\n\u003cp\u003eTable 6 above shows the results of the quality assessment of the studies. The 31 studies\u0026apos; quality ranged from poor (meeting\u0026le; 40% of the criteria) to very good (meeting\u0026ge; 90% of the criteria). None of the studies fulfilled all 14 criteria as none of the studies met \u0026ge; 90%of the criteria. Few studies made the data used in their study available (n = 3; 10%). Only ten studies (32%) explained how features were generated before model training. Only two studies (6%) provided the code used for data cleaning and analysis. Only one study (3%) provided code to reproduce the exact sepsis labels [58]. Few studies reported the hyperparameters needed for study replication (n = 5; 16%). Finally, only seven studies (23%) validated their study result on an external data set. With the exception of two studies\n \u003c!--[if supportFields]\u003e\u003cspan\n style='mso-element:field-begin'\u003e\u003c/span\u003eCITATION Gri01 \\l 1033\u0026nbsp;\u0026nbsp;\\m Sta13\u003cspan style='mso-element:field-separator'\u003e\u003c/span\u003e\u003c![endif]--\u003e[64, 53]\n \u003c!--[if supportFields]\u003e\u003cspan style='mso-element:field-end'\u003e\u003c/span\u003e\u003c![endif]--\u003e, all other studies had sample sizes larger than 50, which is a requirement for the interpretation, power, and validity of machine learning methods.\u003c/p\u003e\n\u003cp\u003e\u003cbr\u003e\u003c/p\u003e\n\u003cp\u003e[Tables 7-10 are in the supplementary files section.]\u003c/p\u003e\n\u003cp\u003e\u003cbr\u003e\u003c/p\u003e\n\u003cp id=\"isPasted\" style='margin-top:0in;margin-right:0in;margin-bottom:8.0pt;margin-left:0in;line-height:107%;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:16px;line-height:107%;font-family:\"Times New Roman\",serif;'\u003eTable 11: Strength and weaknesses of the existing screening parameters\u003c/span\u003e\u003c/p\u003e\n\u003ctable style=\"width:6.75in;margin-left:-.25pt;border-collapse:collapse;border:none;\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 61.9pt;border: 1pt solid windowtext;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cstrong\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eScreening Parameters\u003c/span\u003e\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 199.55pt;border-color: windowtext windowtext windowtext currentcolor;border-style: solid solid solid none;border-width: 1pt 1pt 1pt medium;border-image: none 100% / 1 / 0 stretch;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cstrong\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eStrength\u003c/span\u003e\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 224.55pt;border-color: windowtext windowtext windowtext currentcolor;border-style: solid solid solid none;border-width: 1pt 1pt 1pt medium;border-image: none 100% / 1 / 0 stretch;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cstrong\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eWeakness\u003c/span\u003e\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 61.9pt;border-color: currentcolor windowtext windowtext;border-style: none solid solid;border-width: medium 1pt 1pt;border-image: none 100% / 1 / 0 stretch;padding: 0in 5.4pt;height: 22.95pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eDuration of ROM\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 199.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 22.95pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eHas strong and nearly linear association with neonatal sepsis.\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 224.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 22.95pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eAssociation is stronger with EOS than LOS.\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 61.9pt;border-color: currentcolor windowtext windowtext;border-style: none solid solid;border-width: medium 1pt 1pt;border-image: none 100% / 1 / 0 stretch;padding: 0in 5.4pt;height: 36.85pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eMaternal age\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 199.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 36.85pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eNeonatal sepsis is common among infants of older mothers and maternal age \u0026lt; 20 can be associated with EOS risk factors.\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 224.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 36.85pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eNot validated or considered as a determining risk factor for neonatal sepsis.\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 61.9pt;border-color: currentcolor windowtext windowtext;border-style: none solid solid;border-width: medium 1pt 1pt;border-image: none 100% / 1 / 0 stretch;padding: 0in 5.4pt;height: 22.95pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eParity\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 199.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 22.95pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eHas strong association with neonatal sepsis.\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 224.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 22.95pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eAssociation with neonatal sepsis is controversial.\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 61.9pt;border-color: currentcolor windowtext windowtext;border-style: none solid solid;border-width: medium 1pt 1pt;border-image: none 100% / 1 / 0 stretch;padding: 0in 5.4pt;height: 22.95pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eAntibiotic treatment\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 199.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 22.95pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eReduces the risk of infection to a mother and neonate.\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 224.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 22.95pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eIncreases other health risks to newborn infants.\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 61.9pt;border-color: currentcolor windowtext windowtext;border-style: none solid solid;border-width: medium 1pt 1pt;border-image: none 100% / 1 / 0 stretch;padding: 0in 5.4pt;height: 25.6pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eMaternal CRP\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 199.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 25.6pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eIt is associated with neonatal sepsis and a significant risk factor for neonatal sepsis.\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 224.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 25.6pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;color:black;background:white;'\u003eCRP values are also affected by other factors.\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 61.9pt;border-color: currentcolor windowtext windowtext;border-style: none solid solid;border-width: medium 1pt 1pt;border-image: none 100% / 1 / 0 stretch;padding: 0in 5.4pt;height: 48.1pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eGBS status\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 199.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 48.1pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eStrongly associated with neonatal sepsis.\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 224.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 48.1pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eEven though GBS remains the most frequent pathogen for EOS, there has been a shift in this as Escherichia coli (E. coli) becomes the most important pathogen causing EOS in preterm and very low birth weight infants.\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 61.9pt;border-color: currentcolor windowtext windowtext;border-style: none solid solid;border-width: medium 1pt 1pt;border-image: none 100% / 1 / 0 stretch;padding: 0in 5.4pt;height: 27.4pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eIntrapartum fever\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 199.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 27.4pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eIt\u0026rsquo;s generally considered a major risk factor for EOS.\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 224.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 27.4pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eThe risk of neonatal sepsis in newborns delivered by mothers with intrapartum fever is low.\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 61.9pt;border-color: currentcolor windowtext windowtext;border-style: none solid solid;border-width: medium 1pt 1pt;border-image: none 100% / 1 / 0 stretch;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eHeart rate variability\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 199.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eIt is a significant risk factor for neonatal sepsis, and neonates have reduced heart rate variability (HRV) before clinical signs of sepsis.\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 224.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eIts main drawback for early diagnosis of neonatal sepsis is the high false-positive rate.\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 61.9pt;border-color: currentcolor windowtext windowtext;border-style: none solid solid;border-width: medium 1pt 1pt;border-image: none 100% / 1 / 0 stretch;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eBirth weight\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 199.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eIt is one of the determining factors for neonatal sepsis as newborns with less than 2.5 kg are 1.42 times more likely to develop neonatal sepsis than newborns born with 2.5 kg and above.\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 224.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eInfants with low birth weights are at increased risk for other forms of infection and infection-related mortality.\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 61.9pt;border-color: currentcolor windowtext windowtext;border-style: none solid solid;border-width: medium 1pt 1pt;border-image: none 100% / 1 / 0 stretch;padding: 0in 5.4pt;height: 11.65pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eRespiratory rate\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 199.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 11.65pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eIts variability can be an indicator of sepsis.\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 224.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 11.65pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eThe variability in respiratory rate is also associated with other respiratory problems.\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 61.9pt;border-color: currentcolor windowtext windowtext;border-style: none solid solid;border-width: medium 1pt 1pt;border-image: none 100% / 1 / 0 stretch;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eHeart rate\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 199.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eIt is one of the most important clinical indicators to evaluate sepsis.\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 224.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eAn elevated score is not specific for sepsis and may occur in other conditions associated with nonspecific inflammation.\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 61.9pt;border-color: currentcolor windowtext windowtext;border-style: none solid solid;border-width: medium 1pt 1pt;border-image: none 100% / 1 / 0 stretch;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eSpO2\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 199.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003ePerforms well for preclinical detection of sepsis.\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 224.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eHigh altitudes and other factors may affect what is considered normal for a given neonate.\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 61.9pt;border-color: currentcolor windowtext windowtext;border-style: none solid solid;border-width: medium 1pt 1pt;border-image: none 100% / 1 / 0 stretch;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003ePoor feeding\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 199.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eIt appears to be crucial in a diagnosis of sepsis.\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 224.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eIt is a nonspecific symptom seen in newborn\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 61.9pt;border-color: currentcolor windowtext windowtext;border-style: none solid solid;border-width: medium 1pt 1pt;border-image: none 100% / 1 / 0 stretch;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eTemperature\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 199.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eIts variability can be an indicator of sepsis.\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 224.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eNewborns cannot regulate their body temperature well, causing instability.\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 61.9pt;border-color: currentcolor windowtext windowtext;border-style: none solid solid;border-width: medium 1pt 1pt;border-image: none 100% / 1 / 0 stretch;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eApnea\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 199.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eIt can be a clinical sign of neonatal sepsis\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 224.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eIt is common in infant breathing and can be caused by other factors.\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 61.9pt;border-color: currentcolor windowtext windowtext;border-style: none solid solid;border-width: medium 1pt 1pt;border-image: none 100% / 1 / 0 stretch;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eLethargy\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 199.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eIt can be a sign of infection\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 224.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eIt can be a sign of other conditions.\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 61.9pt;border-color: currentcolor windowtext windowtext;border-style: none solid solid;border-width: medium 1pt 1pt;border-image: none 100% / 1 / 0 stretch;padding: 0in 5.4pt;height: 22.95pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eDuration of umbilical venous catheters\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 199.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 22.95pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eA long duration of use is associated with bloodstream infection in newborn\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 224.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 22.95pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eIt is not significant in the diagnosis of sepsis.\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 61.9pt;border-color: currentcolor windowtext windowtext;border-style: none solid solid;border-width: medium 1pt 1pt;border-image: none 100% / 1 / 0 stretch;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eUse of antibiotics on newborns\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 199.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eAre administered to target most types of bacteria that cause an infection\u003c/span\u003e\u003c/p\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 224.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eBecause infants have a higher risk of complications, pediatricians often prescribe antibiotics even if they aren\u0026apos;t positive that it\u0026apos;s a bacterial infection.\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 61.9pt;border-color: currentcolor windowtext windowtext;border-style: none solid solid;border-width: medium 1pt 1pt;border-image: none 100% / 1 / 0 stretch;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eBlood pressure\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 199.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eIt can be associated with newborn infection.\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 224.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eIt can be affected by other conditions.\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 61.9pt;border-color: currentcolor windowtext windowtext;border-style: none solid solid;border-width: medium 1pt 1pt;border-image: none 100% / 1 / 0 stretch;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eGestational age\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 199.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003ePreterm babies are more likely to develop neonatal sepsis than term babies.\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 224.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eIt is a risk factor for other conditions.\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 61.9pt;border-color: currentcolor windowtext windowtext;border-style: none solid solid;border-width: medium 1pt 1pt;border-image: none 100% / 1 / 0 stretch;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eGender\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 199.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eIt influences both the incidence and the outcomes of sepsis.\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 224.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eIt is not a strong indicator of sepsis.\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 61.9pt;border-color: currentcolor windowtext windowtext;border-style: none solid solid;border-width: medium 1pt 1pt;border-image: none 100% / 1 / 0 stretch;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003ePlatelets\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 199.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eIt\u0026apos;s beneficial to predict mortality or to diagnose the sepsis\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 224.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eIt is not very sensitive for the diagnosis of neonatal sepsis and is not very helpful in monitoring the response to therapy.\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 61.9pt;border-color: currentcolor windowtext windowtext;border-style: none solid solid;border-width: medium 1pt 1pt;border-image: none 100% / 1 / 0 stretch;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eWBC\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 199.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eIt is highly predictive of infection.\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 224.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eMultiple variables can affect the various components of WBC.\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 61.9pt;border-color: currentcolor windowtext windowtext;border-style: none solid solid;border-width: medium 1pt 1pt;border-image: none 100% / 1 / 0 stretch;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eCRP\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 199.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eIt increases significantly in cases with infection.\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 224.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eIt may not be elevated in the early stages of infection due to the time taken for its synthesis in the liver and, eventually, appear in the blood.\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 61.9pt;border-color: currentcolor windowtext windowtext;border-style: none solid solid;border-width: medium 1pt 1pt;border-image: none 100% / 1 / 0 stretch;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eLeucocyte count\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 199.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eIt can aid in clinical decision-making in cases where a low-to-moderate clinical suspicion for sepsis is present.\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 224.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eIt has low sensitivity in diagnosing neonatal sepsis.\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 61.9pt;border-color: currentcolor windowtext windowtext;border-style: none solid solid;border-width: medium 1pt 1pt;border-image: none 100% / 1 / 0 stretch;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;I/T ratio\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 199.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eIt is highly predictive of infection.\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 224.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eIt is not particularly useful as an independent test in identifying the majority of septic infants.\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 61.9pt;border-color: currentcolor windowtext windowtext;border-style: none solid solid;border-width: medium 1pt 1pt;border-image: none 100% / 1 / 0 stretch;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003epH\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 199.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eIt can be significantly lower in newborns with sepsis\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 224.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eIt can be caused by other conditions.\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 61.9pt;border-color: currentcolor windowtext windowtext;border-style: none solid solid;border-width: medium 1pt 1pt;border-image: none 100% / 1 / 0 stretch;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eGlucose\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 199.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eIts level can be significantly affected by neonatal sepsis.\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 224.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eLow blood sugar can happen for many reasons\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 61.9pt;border-color: currentcolor windowtext windowtext;border-style: none solid solid;border-width: medium 1pt 1pt;border-image: none 100% / 1 / 0 stretch;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eHCO3\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 199.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eIt can be significantly lower in newborns with sepsis\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 224.55pt;border-color: currentcolor windowtext windowtext currentcolor;border-style: none solid solid none;border-width: medium 1pt 1pt medium;padding: 0in 5.4pt;height: 11.45pt;vertical-align: top;\"\u003e\n \u003cp style='margin-top:0in;margin-right:0in;margin-bottom:0in;margin-left:0in;line-height:normal;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-size:13px;font-family:\"Times New Roman\",serif;'\u003eIt can be caused by other conditions.\u003c/span\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp style='margin-top:0in;margin-right:0in;margin-bottom:8.0pt;margin-left:0in;line-height:107%;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n\u003cp style='margin-top:0in;margin-right:0in;margin-bottom:8.0pt;margin-left:0in;line-height:107%;font-size:15px;font-family:\"Calibri\",sans-serif;'\u003e\u003cspan style='font-family:\"Times New Roman\",serif;'\u003e\u0026nbsp;\u003c/span\u003e\u003c/p\u003e\n\u003cp\u003e[Table 12 is in the supplementary files section.]\u003c/p\u003e"},{"header":"Discussion","content":"\u003cp\u003eThe review summarized studies on neonatal sepsis with ML algorithms to facilitate early prediction. Looking at ML methods, which includes cohort selections, predictor variables, outcomes, the building of models, and validation methods. A wide range of ML algorithms was chosen for analysis in the studies to leverage neonates\u0026apos; digital health data to predict sepsis. Based on the findings from the reviewed studies, this section outlines three major challenges that studies on neonatal sepsis prediction leveraging machine learning are currently facing: (i) asynchronicity, (ii) comparability, and (iii) reproducibility.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAsynchronicity\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eStudies focused on predicting neonatal sepsis with ML have shown to have the advantage of increasing the prediction power and have promising results\u0026nbsp;[43, 50]. But so far, the reports on which of the open challenges are the most pressing challenges that need to be addressed are diverging, which poses difficulty in achieving the goal of early neonatal sepsis detection. On one hand, the blood culture test, which is the standard gold test, has been stated as the most reliable test for confirming neonatal sepsis\u0026nbsp;[62]. While on the other hand, recent findings have cast doubt on the validity and meaningfulness of the blood culture test. As it has been stated to be unreliable due to the longer time (48-72 hours), it takes to obtain the result and the insufficient amount of blood obtained from neonates, which produces false-negative results\u0026nbsp;[54, 50]. Also, it was stated that neonatal clinical signs (e.g., the use of heart rate variability) alone are sufficient in detecting neonatal sepsis\u0026nbsp;[40, 61]. However, recent studies are posing doubts to this as they state that a combination of predictor variables yield better results in the detection of neonatal sepsis\u0026nbsp;[48, 57, 43, 50]. The developed ML models need to be explored in clinical trials to ascertain their clinical settings usage as most of the models are developed retrospectively, facing multiple obstacles.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eComparability\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eIn terms of comparability of the reviewed studies, several challenges were identified that are yet to be overcome; (i) neonatal sepsis definition, (ii) implementation of a given neonatal sepsis definition, and (iii) performance measures of the models. Each of these challenges is discussed below.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eDefining and Implementing Neonatal Sepsis\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe choice of neonatal sepsis definition is an obstacle that affects the comparison of studies in terms of septic neonates\u0026apos; prevalence. A various set of neonatal sepsis definitions (and modifications) were used in the reviewed studies. Having a large set of septic neonates is anticipated to be useful in training ML models (most especially the deep neural networks). However, having a high number of septic neonates could make it difficult to differentiate the septic neonates from the non-septic neonates. Neonatal sepsis is inherently hard to define as, over the years, there has not been a consensus definition for it. The previous study shows that the use of different sepsis definitions on the same dataset gives a largely dissimilar cohort\u0026nbsp;[68]. This study found that blood culture is less inclusive, leading to a small cohort showing severe symptoms, which has been reported in several studies\u0026nbsp;[54, 43, 50]. It was also seen that even the use of the same definition on the same dataset gives dissimilar cohorts. This can be confirmed from studies carried out at the University of Virginia and studies that used the MIMIC-III dataset (see Table 9 above). The underlying problem cannot be easily discovered, as the code for assigning the labels are not available in 30 studies out of 31 (97%) studies. The diversity of neonatal sepsis prevalence is another factor that is increasing the problem of comparability. Some studies balance their datasets to improve the training of the ML models, but this training setup can partly affect the study\u0026nbsp;[56]. While other studies keep the observed case counts to see how their approach will work in clinical settings. From this study findings, it has been identified that the neonatal sepsis definition used and the data pre-processing steps affect the prediction of sepsis and also the prevalence\u0026nbsp;[68]. The maximum prevalence reported is 87.0%\u0026nbsp;[64].\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003ePerformance Measures of the Models\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe choice of performance measures is the last obstacle to be discussed that is obstructing comparability. This obstacle is largely affected by the prevalence of neonatal sepsis in the study. Accuracy is a simple performance metric directly influenced by class prevalence; comparing two studies with different prevalence values is problematic. Some studies report the area under the receiver operating characteristic curve (AUROC, also known as AUC) to improve the performance metrics report. However, AUROC also depends on class prevalence and can be less informative on highly imbalanced classes\u0026nbsp;[69]. The area under the precision-recall curve (AUPRC, also known as average precision) is preferable in such a situation. Both AUPRC and AUROC are affected by prevalence. However, AUPRC allows comparison with a random baseline that just \u0026quot;guesses\u0026quot; the neonate label, and it\u0026apos;s useful when considering the positive class. While AUROC can be high even for classifiers that could not classify the minority class of septic neonates. The effect of the choice of performance metrics is greatly seen with highly imbalanced classes. Recent research recommends reporting the AUPRC of models, particularly in clinical studies\u0026nbsp;[70], which is a good recommendation.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eComparing Studies of Low Comparability\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eBased on this review study\u0026apos;s findings, comparing the reviewed studies quantitatively is currently a challenging task to accomplish, which was also seen in a study by (Moor, et al., 2020). The studies were assessed qualitatively to identify underlying biases that could lead to unduly optimistic results. This was done as the best-performing methods could not be ascertained by just evaluating the performance measures\u0026apos; numeric values. A meta-analysis will be preferable to sum up, an overall trend in the performance of the models.\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eReproducibility\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eReproducibility, which is the ability to obtain consistent results using the same data and code as the original experiment, is the means for scientific accountability. There have been failures of this accountability in several disciplines, including ML\u0026nbsp;[35]. The use of sensitive data makes it difficult to make available the dataset used in studies, which is one of the challenges digital medicine poses to reproducibility. \u0026nbsp;Another challenge is the failure to provide detailed preprocessing methods used in ML papers. Based on the quality assessment carried out, important areas were outlined that need to be improved. As it was seen, only two studies\u0026nbsp;[50, 66]\u0026nbsp;made available their analysis code. Only one study\u0026nbsp;[58]\u0026nbsp;made available their code for generating a \u0026ldquo;label.\u0026rdquo; Both cases amount to less than 10% of the eligible studies. In addition, only three studies\u0026nbsp;[57, 50, 66]\u0026nbsp;made available the dataset used for their study. Only eight studies were found to share the hyperparameters used in their studies. However, a positive finding of this analysis is that a considerable number of studies (n = 10) shared the preprocessing methods used in their studies, which is useful information in the reproducibility of computational experiments.\u003c/p\u003e\n\u003cp\u003eThis review focused on publications that studied the prediction of neonatal sepsis implementing ML algorithms. The majority of the reviewed studies investigating neonatal sepsis prediction defined neonatal sepsis as having positive blood culture or observational condition (i.e., the use of neonatal clinical signs). None of the 31 included studies reflects an African cohort, which shows a significant dataset bias in the publications and insufficient research in Africa (see Supplemental table 1 for an overview of demographical information). The review found a lot of room for improvement, which will benefit the comparability of different models, most importantly, when ML models are going to be evaluated prospectively.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eLimitations\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis review was carried out with some shortcomings. The reviewed studies had certain inherent limitations, as previously mentioned. The diagnostic performance evaluation report of the models was suboptimal. The studies were assessed qualitatively due to the variation in the performance measures used. A meta-analysis will be preferable to evaluate the performance of the models. Some studies may have been omitted from the review as English language restrictions were applied.\u0026nbsp;\u003c/p\u003e"},{"header":"Conclusion","content":"\u003cp\u003eCombination of these variables have been predicted to strengthen the prediction of neonatal sepsis which was shown in some of the studies above. This study seeks to inform researchers on what predictor variables are required to develop algorithms/models with better diagnostic performance which will improve the detection of neonatal sepsis. The parameters and machine learning models used in the reviewed studies were largely different, so diagnostic performance was different. It should be considered that neonatal sepsis is consistent with other symptoms as well as underlying conditions. What is important here is the weight assigned to a variable. Suggestions for risk stratification based on maternal risk factors (such as; intrapartum fever, chorioamnionitis, duration of ROM, GBS colonization and intrapartum antibiotics), neonatal clinical signs (such as; gestational age, birth weight, heart rate, postnatal distress and feeding difficulty), and laboratory tests (such as; absolute neutrophil count, C reactive protein, I/T ratio, micro-ESR, platelet count and total leukocyte count) could be considered for future studies.\u003c/p\u003e"},{"header":"List Of Abbreviations","content":"\u003ctable border=\"0\" cellpadding=\"0\" cellspacing=\"0\" width=\"680\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" width=\"40.588235294117645%\"\u003e\n \u003cp\u003eANC\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"59.411764705882355%\"\u003e\n \u003cp\u003eAbsolute Neutrophil Count \u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" width=\"40.588235294117645%\"\u003e\n \u003cp\u003eAR-HMM\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"59.411764705882355%\"\u003e\n \u003cp\u003eAutoregressive hidden Markov model\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" width=\"40.588235294117645%\"\u003e\n \u003cp\u003eAUROC\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"59.411764705882355%\"\u003e\n \u003cp\u003eArea Under the Receiver Operating Characteristics\u0026nbsp;\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" width=\"40.588235294117645%\"\u003e\n \u003cp\u003eCNNs\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"59.411764705882355%\"\u003e\n \u003cp\u003eConvolutional neural networks\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" width=\"40.588235294117645%\"\u003e\n \u003cp\u003eCRP\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"59.411764705882355%\"\u003e\n \u003cp\u003eC-reactive protein\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" width=\"40.588235294117645%\"\u003e\n \u003cp\u003eCSF \u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"59.411764705882355%\"\u003e\n \u003cp\u003eCerebrospinal Fluid \u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" width=\"40.588235294117645%\"\u003e\n \u003cp\u003eECG\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"59.411764705882355%\"\u003e\n \u003cp\u003eElectrocardiogram\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" width=\"40.588235294117645%\"\u003e\n \u003cp\u003eEMR\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"59.411764705882355%\"\u003e\n \u003cp\u003eElectronic Medical Record\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" width=\"40.588235294117645%\"\u003e\n \u003cp\u003eEOS\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"59.411764705882355%\"\u003e\n \u003cp\u003eEarly onset sepsis\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" width=\"40.588235294117645%\"\u003e\n \u003cp\u003eGA\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"59.411764705882355%\"\u003e\n \u003cp\u003eGestational age\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" width=\"40.588235294117645%\"\u003e\n \u003cp\u003eGBS\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"59.411764705882355%\"\u003e\n \u003cp\u003eGroup B Streptococcus \u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" width=\"40.588235294117645%\"\u003e\n \u003cp\u003eHELLP syndrome\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"59.411764705882355%\"\u003e\n \u003cp\u003eHemolysis elevated liver enzymes low platelet count\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" width=\"40.588235294117645%\"\u003e\n \u003cp\u003eHRC\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"59.411764705882355%\"\u003e\n \u003cp\u003eHeart rate characteristics\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" width=\"40.588235294117645%\"\u003e\n \u003cp\u003eHR\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"59.411764705882355%\"\u003e\n \u003cp\u003eHeart rate\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" width=\"40.588235294117645%\"\u003e\n \u003cp\u003eHRV\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"59.411764705882355%\"\u003e\n \u003cp\u003eHeart Rate Variability \u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" width=\"40.588235294117645%\"\u003e\n \u003cp\u003eI/T ratio\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"59.411764705882355%\"\u003e\n \u003cp\u003eImmature to Total Neutrophil Ratio\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" width=\"40.588235294117645%\"\u003e\n \u003cp\u003eLNS\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"59.411764705882355%\"\u003e\n \u003cp\u003eLate-neonatal sepsis\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" width=\"40.588235294117645%\"\u003e\n \u003cp\u003eLOCF\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"59.411764705882355%\"\u003e\n \u003cp\u003eLast observation carried forward\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" width=\"40.588235294117645%\"\u003e\n \u003cp\u003eLOS\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"59.411764705882355%\"\u003e\n \u003cp\u003eLate-onset sepsis\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" width=\"40.588235294117645%\"\u003e\n \u003cp\u003eM-ESR\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"59.411764705882355%\"\u003e\n \u003cp\u003eMicro Erythrocyte Sedimentation Rate\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" width=\"40.588235294117645%\"\u003e\n \u003cp\u003eMIMIC\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"59.411764705882355%\"\u003e\n \u003cp\u003eMedical Information Mart for Intensive care III\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" width=\"40.588235294117645%\"\u003e\n \u003cp\u003eML\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"59.411764705882355%\"\u003e\n \u003cp\u003eMachine Learning\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" width=\"40.588235294117645%\"\u003e\n \u003cp\u003eNICUs\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"59.411764705882355%\"\u003e\n \u003cp\u003eNeonatal Intensive Care Units\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" width=\"40.588235294117645%\"\u003e\n \u003cp\u003eNPV\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"59.411764705882355%\"\u003e\n \u003cp\u003eNegative Predictive Value\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" width=\"40.588235294117645%\"\u003e\n \u003cp\u003ePPROM\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"59.411764705882355%\"\u003e\n \u003cp\u003ePreterm Premature Rupture of the Membranes \u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" width=\"40.588235294117645%\"\u003e\n \u003cp\u003ePPROMEXIL\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"59.411764705882355%\"\u003e\n \u003cp\u003ePreterm pre-labor rupture of the membrane expectant management or induction of labor study\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" width=\"40.588235294117645%\"\u003e\n \u003cp\u003ePro\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"59.411764705882355%\"\u003e\n \u003cp\u003eProspective\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" width=\"40.588235294117645%\"\u003e\n \u003cp\u003ePR\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"59.411764705882355%\"\u003e\n \u003cp\u003ePulse rate\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" width=\"40.588235294117645%\"\u003e\n \u003cp\u003ePPV\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"59.411764705882355%\"\u003e\n \u003cp\u003ePositive Predictive Value\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" width=\"40.588235294117645%\"\u003e\n \u003cp\u003eRetro\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"59.411764705882355%\"\u003e\n \u003cp\u003eRetrospective\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" width=\"40.588235294117645%\"\u003e\n \u003cp\u003eROC curve\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"59.411764705882355%\"\u003e\n \u003cp\u003eReceiver-operating characteristic curve\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" width=\"40.588235294117645%\"\u003e\n \u003cp\u003eROM\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"59.411764705882355%\"\u003e\n \u003cp\u003eRupture of Membranes\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" width=\"40.588235294117645%\"\u003e\n \u003cp\u003eRR\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"59.411764705882355%\"\u003e\n \u003cp\u003eRespiratory rate\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" width=\"40.588235294117645%\"\u003e\n \u003cp\u003eSDG\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"59.411764705882355%\"\u003e\n \u003cp\u003eSustainable Development Goals\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" width=\"40.588235294117645%\"\u003e\n \u003cp\u003eSIRS\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"59.411764705882355%\"\u003e\n \u003cp\u003eSystemic Inflammatory Response Syndrome\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" width=\"40.588235294117645%\"\u003e\n \u003cp\u003eSO\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"59.411764705882355%\"\u003e\n \u003cp\u003eOxygen saturation\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" width=\"40.588235294117645%\"\u003e\n \u003cp\u003eSpO2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"59.411764705882355%\"\u003e\n \u003cp\u003eBlood oxygen level\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" width=\"40.588235294117645%\"\u003e\n \u003cp\u003eSSA\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"59.411764705882355%\"\u003e\n \u003cp\u003eSub-Saharan Africa\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" width=\"40.588235294117645%\"\u003e\n \u003cp\u003eTC\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"59.411764705882355%\"\u003e\n \u003cp\u003eCore temperature\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" width=\"40.588235294117645%\"\u003e\n \u003cp\u003eTLC\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"59.411764705882355%\"\u003e\n \u003cp\u003eTotal Leukocyte Count\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" width=\"40.588235294117645%\"\u003e\n \u003cp\u003eTP\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"59.411764705882355%\"\u003e\n \u003cp\u003ePeripheral temperature\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" width=\"40.588235294117645%\"\u003e\n \u003cp\u003eWBC\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"59.411764705882355%\"\u003e\n \u003cp\u003eWhite blood cell\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e"},{"header":"Declarations","content":"\u003cp\u003eThe work presented in this Manuscript is the result of our original research work. Where we have used the works of other persons, due acknowledgements are clearly stated. This work has not been submitted for publication in any journal before.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eEthical approval and consent to participate\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNot applicable; as the study reviewed only published data.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConsent for publication\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNot applicable\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAvailability of data and materials\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNot applicable.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eCompeting Interests\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe authors declare that they have no competing interests.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eFunding\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNo external funding was obtained for this study.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAuthor\u0026rsquo;s contributions\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eEDP, WW and AM carried out the preliminary literature search following the PRISMA guidelines, tabulated and analyzed the collected data and developed the first draft of the manuscript. KS contributed the neonatology expertise and edited the manuscript accordingly. All the authors reviewed and approved the final manuscript.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAcknowledgement\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNot applicable.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAuthors information\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eEDP\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eDepartment: Information Technology\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eCourse: Masters in Health Information Technology\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eAuthors\u0026apos; qualifications: BS.c, MS.c\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eInstitution: Mbarara University of Science and Technology (MUST)\u0026nbsp;\u003c/p\u003e\n\u003cp\u003ePosition: Post-Graduate Student\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eWW\u003c/p\u003e\n\u003cp\u003eAuthors\u0026apos; qualifications: BS.c, MS.c, PhD\u003c/p\u003e\n\u003cp\u003eDepartment: Biomedical Sciences and Engineering \u0026nbsp;\u003c/p\u003e\n\u003cp\u003eInstitution: Mbarara University of Science and Technology (MUST)\u0026nbsp;\u003c/p\u003e\n\u003cp\u003ePosition: Head of Department (HOD)\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eAM\u003c/p\u003e\n\u003cp\u003eAuthors\u0026apos; qualifications: BS.c, MS.c, PhD\u003c/p\u003e\n\u003cp\u003eDepartment: Information Technology \u0026nbsp;\u003c/p\u003e\n\u003cp\u003eInstitution: Mbarara University of Science and Technology (MUST)\u0026nbsp;\u003c/p\u003e\n\u003cp\u003ePosition: Deputy Dean of the Faculty\u003c/p\u003e\n\u003cp\u003eLocation: Mbarara, Uganda\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eKS\u003c/p\u003e\n\u003cp\u003eAuthors\u0026apos; qualifications: MBChB, MMed \u0026nbsp;\u003c/p\u003e\n\u003cp\u003eDepartment: Pediatrics and Child Health MRRH\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eHospital: Mbarara Regional Referral Hospital (MRRH)\u0026nbsp;\u003c/p\u003e\n\u003cp\u003ePosition: Head of Department (HOD), Neonatology division\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eSupplementary Material\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe supplementary file contains the filled\u0026nbsp;PRISMA statement checklist for the study.\u003c/p\u003e\n\u003cp\u003eTable 1: The table contain an overview of trial designs, demographical information and machine learning details of the studies.\u003c/p\u003e"},{"header":"References","content":"\u003ctable border=\"0\" cellpadding=\"0\" cellspacing=\"3\" width=\"100%\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[1]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eWHO, \u0026quot;Newborn death and illness,\u0026quot; Partnership for Maternal, Newborn \u0026amp; Child Health, Geneva, Switzerland, 2011.\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[2]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eUNICEF, \u0026quot;Levels and Trends in Child Mortality Report 2017.,\u0026quot; United Nations Children\u0026rsquo;s Fund, New York, 2017.\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[3]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eS. W. B. Ranjeva and S. Schiff, \u0026quot;Economic burden of neonatal sepsis in sub-Saharan Africa.,\u0026quot; \u003cem\u003eBMJ global health,\u0026nbsp;\u003c/em\u003evol. 3, no. 1, p. e000347, 2018.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[4]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eL. Liu, S. Oza, D. Hogan, J. Perin, I. Rudan, J. Lawn, S. Cousens, C. Mathers and R. Black, \u0026quot;Global, regional, and national causes of child mortality in 2000\u0026ndash;13, with projections to inform post-2015 priorities: an updated systematic analysis.,\u0026quot; \u003cem\u003eLancet,\u0026nbsp;\u003c/em\u003evol. 385, pp. 430-440, 2015.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[5]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eA. Sarkar, G. Dhar, M. Sarkar, T. Ghosh and S. Ghosh, \u0026quot;Early diagnosis of neonatal sepsis in primary health care unit.,\u0026quot; \u003cem\u003eBangladesh J. Med. Sci.,\u0026nbsp;\u003c/em\u003evol. 14, no. 2, pp. 5-8, 2015.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[6]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eM. V. M. Stephannie and J. M. M. Patrick, \u0026quot;Neonatal Sepsis.,\u0026quot; \u003cem\u003eClin. Pediatr. Emerg. Med.,\u0026nbsp;\u003c/em\u003evol. 17, pp. 129-133, 2016.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[7]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eZ.-V. Alonso and J. O. Theresa, \u0026quot;Challenges in the diagnosis and management of neonatal sepsis,\u0026quot; \u003cem\u003eJournal of Tropical Pediatrics,\u0026nbsp;\u003c/em\u003evol. 61, p. 1\u0026ndash;13, 2015.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[8]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eA. Shane, P. S\u0026aacute;nchez and B. Stoll, \u0026quot;Neonatal sepsis.,\u0026quot; \u003cem\u003eLancet,\u0026nbsp;\u003c/em\u003e2017.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[9]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eJ. S. M. Barbara, I. H. M. Nellie, A.-C. M. Ira, A. F. M. Avroy, R. H. M. Susan, V. M. Betty and D. H. M. Rosemary, \u0026quot;Neurodevelopmental and Growth Impairment Among Extremely Low-Birth-Weight Infants With Neonatal Infection,\u0026quot; \u003cem\u003eJAMA.,\u0026nbsp;\u003c/em\u003evol. 292, no. 19, pp. 2357-2365, 2004.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[10]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eE. S. M. Bonnie and R. M. Betty, \u0026quot;Neurodevelopmental Outcome of the Premature Infant,\u0026quot; \u003cem\u003ePediatric Clinics of North America,\u0026nbsp;\u003c/em\u003evol. 56, no. 3, p. 631\u0026ndash;646., 2009.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[11]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eJ. S. M. Barbara, I. H. M. Nellie, F. B. M. Edward, S. M. Seetha, R. L. M. Abbot, C. W. M. M. Michele and B. R. Nancy S. Newman, \u0026quot;Neonatal Outcomes of Extremely Preterm Infants From the NICHD Neonatal Research Network,\u0026quot; \u003cem\u003ePediatrics,\u0026nbsp;\u003c/em\u003evol. 126, no. 3, p. 443\u0026ndash;456, 2010.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[12]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eC. Jonathan, V. Jean-Louis, K. J. A. Neill, R. M. Flavia, C. A. Derek, C. Thierry, J. Katia, G. Stefano, D. Julie, O. Steven, T. Kevin, v. d. P. Tom and P. Eric, \u0026quot;Sepsis: a roadmap for future research,\u0026quot; \u003cem\u003eThe Lancet Infectious Diseases Commission,\u0026nbsp;\u003c/em\u003evol. 15, no. 5, p. 581\u0026ndash;614., 2015.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[13]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eG. M. M. Elsie, S. M. P. Lisa, F. R. P. Lynn and M. M. M. Paul, \u0026quot;A Nurse-Driven Screening Tool for the Early Identification of Sepsis in an Intermediate Care Unit Setting,\u0026quot; \u003cem\u003eJ Hosp Med ,\u0026nbsp;\u003c/em\u003evol. 10, no. 2, p. 97\u0026ndash;103, 2015.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[14]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eJ. P. P. M. Carly, P. Mark A. Reynolds, M. Meenal Sinha, P. Matthew Gitlin and M. Elliott Crouser, \u0026quot;Epidemiology and Costs of Sepsis in the United States\u0026mdash;An Analysis Based on Timing of Diagnosis and Severity Level,\u0026quot; \u003cem\u003eCritical Care Medicine,\u0026nbsp;\u003c/em\u003evol. 46, no. 12, 2018.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[15]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eH. Jihane, B. Natalie, S. Jola and J. Douglas, \u0026quot;The \u0026ldquo;Centrality of Sepsis\u0026rdquo;: A Review on Incidence, Mortality, and Cost of Care,\u0026quot; \u003cem\u003eHealthcare,\u0026nbsp;\u003c/em\u003evol. 6, no. 3, 2018.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[16]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eL. W. James, \u0026quot;Defining Neonatal Sepsis,\u0026quot; \u003cem\u003eCurr Opin Pediatr. ,\u0026nbsp;\u003c/em\u003evol. 28, no. 2, p. 135\u0026ndash;140, 2016.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[17]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eR. Konrad, B. Michael, C. R. Niels and S. H. Christiane, \u0026quot;New Approaches to Sepsis: Molecular Diagnostics and Biomarkers,\u0026quot; \u003cem\u003eClinical Microbiology Reviews ,\u0026nbsp;\u003c/em\u003evol. 25, no. 4, p. 609 \u0026ndash; 634, 2012.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[18]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eB. M. P. M. Fran, R. A. M. M. Elizabeth, K. A. M. R. Mary, H. B. Katie, S. P. Aileen, L. M. Jane, M. P. Julie C. Fitzgerald, L. W. M. M. Scott and J. Z. M. M. Joseph, \u0026quot;Improving Recognition of Pediatric Severe Sepsis in the Emergency Department: Contributions of a Vital Sign Based Electronic Alert and Bedside Clinician Identification,\u0026quot; \u003cem\u003eAnn Emerg Med. ,\u0026nbsp;\u003c/em\u003evol. 70, no. 6, p. 759\u0026ndash;768., 2017.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[19]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eL. J. M. M. Stephen, M. A. M. M. Carol, K. M. Lisa, G. N. Elizabeth, B.-G. D. R. F.-C. C. N.-B. Charyl, D. R. C. Maureen, M. M. F. F. Faisal, A. S. P. Beverly and M. M. Nelda P. Wray, \u0026quot;Reductions in Sepsis Mortality and Costs After Design and Implementation of a Nurse-Based Early Recognition and Response Program,\u0026quot; \u003cem\u003eJt Comm J Qual Patient Saf,\u0026nbsp;\u003c/em\u003evol. 41, no. 11, p. 483\u0026ndash;491, 2015.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[20]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eO. Lori, \u0026quot;Early Recognition and Management of Maternal Sepsis,\u0026quot; \u003cem\u003eNursing for Women\u0026rsquo;s Health ,\u0026nbsp;\u003c/em\u003e2016.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[21]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eA. S. Michael, J. B.-M. Samantha and D. P. Gavin, \u0026quot;Identification of adults with sepsis in the prehospital environment: a systematic review,\u0026quot; \u003cem\u003eBMJ Open ,\u0026nbsp;\u003c/em\u003e2016.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[22]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eB. F. Deshayne, H. Steven, A. W. Coralie, A. W. Lindsay, S. Q. M. Malia, C. Pranesh, L.-M. Thierry, K. P. Beth and W. Kumanan, \u0026quot;Using newborn screening analytes to identify cases of neonatal sepsis,\u0026quot; \u003cem\u003eSCIENTIFIC REPORTS ,\u0026nbsp;\u003c/em\u003e2017.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[23]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eB. Mercedes, P. S. Joao, A. Edgardo, F. Bukola, K. Marian, K. Seni, L. Pisake, N. Ashraf, N. Ruta, B. Vanessa and G. A. Metin, \u0026quot;The global maternal sepsis study and awareness campaign (GLOSS): study protocol,\u0026quot; \u003cem\u003eReproductive Health,\u0026nbsp;\u003c/em\u003e2018.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[24]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eA. S. Birju and F. P. James, \u0026quot;Neonatal sepsis An old problem with new insights,\u0026quot; \u003cem\u003eVirulence,\u0026nbsp;\u003c/em\u003evol. 5, no. 1, p. 170\u0026ndash;178, 2014.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[25]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eD. M. Clarissa, S. M. Karen and K. J. M. Sunil, \u0026quot;Biomarkers of Neonatal Sepsis.,\u0026quot; \u003cem\u003eNeoreviews,\u0026nbsp;\u003c/em\u003evol. 16, no. 5, p. e297\u0026ndash;e308, 2015.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[26]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eF. Aline, B. Julia, M. Shrey, S. Mike and N. V. D. A. Johannes, \u0026quot;Antibiotic Use for Sepsis in Neonates and Children: 2016 Evidence Update,\u0026quot; \u003cem\u003eWHO,\u0026nbsp;\u003c/em\u003e2016.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[27]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eK. Claus, F. K. Ren\u0026eacute;, B. Giuseppe, F. M. Rolf and S. Martin, \u0026quot;Culture-Negative Early-Onset Neonatal Sepsis \u0026mdash; At the Crossroad Sepsis Care and Antimicrobial Stewardship,\u0026quot; \u003cem\u003eFront. Pediatr.,\u0026nbsp;\u003c/em\u003e2018.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[28]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eJ. T. Priti, O. Anjumanara and M. Rachel, \u0026quot;Audit of Antibiotic Prescribing Practices for Neonatal Sepsis and Measurement of Outcome in New Born Unit at Kenyatta National Hospital,\u0026quot; \u003cem\u003eInternational Journal of Pediatrics,\u0026nbsp;\u003c/em\u003e2019.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[29]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eR. Kartik, M. Sahana, D. Prathiba and J. Malavika, \u0026quot;Evaluation of screening of neonatal sepsis,\u0026quot; \u003cem\u003eInternational Journal of Contemporary Pediatrics,\u0026nbsp;\u003c/em\u003evol. 5, no. 2, pp. 580-583, 2018.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[30]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eJ. M. Aaron, C. H. Mary, F. Daniel, O. Svetlana, S. Lakshmi, P. B. Christopher, B. Fran, S. Melissa and W. G. Robert, \u0026quot;Machine learning models for early sepsis recognition in the neonatal intensive care unit using readily available electronic health record data,\u0026quot; \u003cem\u003ePLoS ONE ,\u0026nbsp;\u003c/em\u003evol. 14, no. 2, 2019.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[31]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eE. H. Katharine, N. H. David, J. P. Peter and S. Suchi, \u0026quot;A targeted real-time early warning score (TREWScore) for septic shock,\u0026quot; \u003cem\u003eScience Translational Medicine,\u0026nbsp;\u003c/em\u003evol. 7 , no. 299, 2015.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[32]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eR. Taylor, J. Pare and A. Venkatesh, \u0026quot;Prediction of In-hospital Mortality in Emergency Department Patients With Sepsis: A Local Big Data\u0026ndash;Driven, Machine Learning Approach,\u0026quot; \u003cem\u003eAcad Emerg Med. ,\u0026nbsp;\u003c/em\u003evol. 23, no. 3, p. 269\u0026ndash;278., 2016.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[33]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eT. Desautels, J. Calvert and J. Hoffman, \u0026quot;Prediction of Sepsis in the Intensive Care Unit With Minimal Electronic Health Record Data: A Machine Learning Approach,\u0026quot; \u003cem\u003eJMIR Med Inform. ,\u0026nbsp;\u003c/em\u003evol. 4, no. 3, 2016.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[34]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eJ. K. Hye and Y. K. Ha, \u0026quot;Learning representations for the early detection of sepsis with deep neural networks,\u0026quot; \u003cem\u003eComputers in Biology and Medicine,\u0026nbsp;\u003c/em\u003e2017.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[35]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eM. Moor, B. Rieck, M. Horn, C. Jutzeler and K. Borgwardt, \u0026quot;Early Prediction of Sepsis in the ICU using Machine Learning: A Systematic Review,\u0026quot; \u003cem\u003emedRxiv,\u0026nbsp;\u003c/em\u003evol. 8, no. 7, pp. 952-960, 2020.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[36]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eA. A. D. T. J. M. C. G. P. I. J. C. M. Liberati and P. Devereaux, \u0026quot;The PRISMA statement for reporting systematic and meta-analyses of studies that evaluate interventions: explanation and elaboration.,\u0026quot; \u003cem\u003ePLoS Medicine,\u0026nbsp;\u003c/em\u003evol. 6, no. 7, pp. 1-28, 2009.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[37]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eL. Mahieu, A. De Muynck, J. De Dooy, S. Laroche and K. Van Acker, \u0026quot;Prediction of nosocomial sepsis in neonates by means of a computer-weighted bedside scoring system (NOSEP score),\u0026quot; \u003cem\u003eCritical care medicine,\u0026nbsp;\u003c/em\u003evol. 28, no. 6, pp. 2026-2033, 2000.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[38]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eY. Huang, X. Yu, W. Li, Y. Li, J. Yang, Z. Hu, Y. Wang, P. Chen, W. Li and Y. Chen, \u0026quot;Development and validation of a nomogram for predicting late-onset sepsis in preterm infants on the basis of thyroid function and other risk factors: Mixed retrospective and prospective cohort study,\u0026quot; \u003cem\u003eJournal of Advanced Research,\u0026nbsp;\u003c/em\u003evol. 24, pp. 43-51, 2020.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[39]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eD. Lake, J. Richman, M. Griffin and J. Moorman, \u0026quot;Sample entropy analysis of neonatal heart rate variability,\u0026quot; \u003cem\u003eAmerican Journal of Physiology-Regulatory, Integrative and Comparative Physiology,\u0026nbsp;\u003c/em\u003evol. 283, no. 3, pp. R789-R797, 2002.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[40]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eK. Fairchild and T. O\u0026apos;Shea, \u0026quot;Heart rate characteristics: physiomarkers for detection of late-onset neonatal sepsis,\u0026quot; \u003cem\u003eClinics in perinatology,\u0026nbsp;\u003c/em\u003evol. 37, no. 3, pp. 581-598, 2010.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[41]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eY. Xiao, M. Griffin, D. Lake and J. Moorman, \u0026quot;Nearest-neighbor and logistic regression analyses of clinical and heart rate characteristics in the early diagnosis of neonatal sepsis,\u0026quot; \u003cem\u003eMedical Decision Making,\u0026nbsp;\u003c/em\u003evol. 30, no. 2, pp. 258-266, 2010.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[42]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eY. Hu, V. Lee and K. Tan, \u0026quot;Prediction of clinicians\u0026apos; treatment in preterm infants with suspected late-onset sepsis\u0026mdash;An ML approach. In 2018 13th IEEE conference on industrial electronics and applications (ICIEA),\u0026quot; \u003cem\u003eIEEE,\u0026nbsp;\u003c/em\u003epp. 1177-1182, 2018.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[43]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eR. G\u0026oacute;mez, N. Garc\u0026iacute;a, G. Collantes, F. Ponce and P. Redon, \u0026quot;Development of a non-invasive procedure to early detect neonatal sepsis using HRV monitoring and machine learning algorithms. In 2019 IEEE 32nd International Symposium on Computer-Based Medical Systems (CBMS),\u0026quot; \u003cem\u003eIEEE,\u0026nbsp;\u003c/em\u003epp. 132-137, 2019.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[44]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eM. Griffin, D. Lake and J. Moorman, \u0026quot;Heart rate characteristics and laboratory tests in neonatal sepsis,\u0026quot; \u003cem\u003ePediatrics,\u0026nbsp;\u003c/em\u003evol. 115, no. 4, pp. 937-941, 2005.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[45]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eM. Griffin, D. Lake, T. O\u0026apos;Shea and J. Moorman, \u0026quot;Heart rate characteristics and clinical signs in neonatal sepsis,\u0026quot; \u003cem\u003ePediatric research,\u0026nbsp;\u003c/em\u003evol. 61, no. 2, pp. 222-227, 2007.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[46]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eA. Herbst and K. K\u0026auml;ll\u0026eacute;n, \u0026quot;Time between membrane rupture and delivery and septicemia in term neonates,\u0026quot; \u003cem\u003eObstetrics \u0026amp; gynecology,\u0026nbsp;\u003c/em\u003evol. 110, no. 3, pp. 612-618, 2007.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[47]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eD. H. D. Van, S. Van Kuijk, B. Opmeer, C. Willekes, J. Van Beek, A. Mulder, A. Van Loon, M. Groenewout, G. Mantel, K. Bloemenkamp and M. Porath, \u0026quot;Can neonatal sepsis be predicted in late preterm premature rupture of membranes? Development of a prediction model,\u0026quot; \u003cem\u003eEuropean Journal of Obstetrics \u0026amp; Gynecology and Reproductive Biology,\u0026nbsp;\u003c/em\u003evol. 176, pp. 90-95, 2014.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[48]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eK. Fairchild, D. Lake, J. Kattwinkel, J. Moorman, D. Bateman, P. Grieve, J. Isler and R. Sahni, \u0026quot;Vital signs and their cross-correlation in sepsis and NEC: a study of 1,065 very-low-birth-weight infants in two NICUs,\u0026quot; \u003cem\u003ePediatric research,\u0026nbsp;\u003c/em\u003evol. 81, no. 2, pp. 315-321, 2017.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[49]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eJ. Thakur, S. Pahuja and R. Pahuja, \u0026quot;Neonatal sepsis prediction model for resource-poor developing countries. In 2018 2nd International Conference on Electronics, Materials Engineering \u0026amp; Nano-Technology (IEMENTech),\u0026quot; \u003cem\u003eIEEE.,\u0026nbsp;\u003c/em\u003epp. 1-5, 2018.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[50]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eA. Masino, M. Harris, D. Forsyth, S. Ostapenko, L. Srinivasan, C. Bonafide, F. Balamuth, M. Schmatz and R. Grundmeier, \u0026quot;Machine learning models for early sepsis recognition in the neonatal intensive care unit using readily available electronic health record data,\u0026quot; \u003cem\u003ePloS one,\u0026nbsp;\u003c/em\u003evol. 14, no. 2, p. e0212665, 2019.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[51]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eJ. Thakur, S. Pahuja and R. Pahuja, \u0026quot;Non-invasive prediction model for developing countries to predict SEPSIS in neonates,\u0026quot; \u003cem\u003eBiomedical Engineering: Applications, Basis and Communications,\u0026nbsp;\u003c/em\u003evol. 31, no. 1, p. 1950001, 2019.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[52]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eL. Mithal, R. Yogev, H. Palac, D. Kaminsky, I. Gur and K. Mestan, \u0026quot;Vital signs analysis algorithm detects inflammatory response in premature infants with late onset sepsis and necrotizing enterocolitis.,\u0026quot; \u003cem\u003eEarly human development,\u0026nbsp;\u003c/em\u003evol. 117, pp. 83-89, 2018.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[53]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eI. Stanculescu, C. Williams and Y. Freer, \u0026quot;Autoregressive hidden Markov models for the early detection of neonatal sepsis,\u0026quot; \u003cem\u003eIEEE journal of biomedical and health informatics,\u0026nbsp;\u003c/em\u003evol. 18, no. 5, pp. 1560-1570, 2013.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[54]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eS. Mani, A. Ozdas, C. Aliferis, H. Varol, Q. Chen, R. Carnevale, Y. Chen, J. Romano-Keeler, H. Nian and J. Weitkamp, \u0026quot;Medical decision support using machine learning for early detection of late-onset neonatal sepsis.,\u0026quot; \u003cem\u003eJournal of the American Medical Informatics Association,\u0026nbsp;\u003c/em\u003evol. 2, no. 21, pp. 326-336, 2014.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[55]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eI. G\u0026uuml;zey and \u0026Ouml;. U\u0026ccedil;ar, \u0026quot;Machine Learning Based Non-Invasive Vital Signs Analysis for Preterm Sepsis Risk Prediction,\u0026quot; \u003cem\u003eInternational Journal of Research in Engineering and Applied Sciences (IJREAS),\u0026nbsp;\u003c/em\u003evol. 8, no. 12, 2018.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[56]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eW. Song, S. Jung, H. Baek, C. Choi, Y. Jung and S. Yoo, \u0026quot;A Predictive Model Based on Machine Learning for the Early Detection of Late-Onset Neonatal Sepsis: Development and Observational Study.,\u0026quot; \u003cem\u003eJMIR Medical Informatics,\u0026nbsp;\u003c/em\u003evol. 8, no. 7, p. 15965, 2020.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[57]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eM. Beltempo, I. Viel-Th\u0026eacute;riault, R. Thibeault, A. Julien and B. Piedboeuf, \u0026quot;C-reactive protein for late-onset sepsis diagnosis in very low birth weight infants,\u0026quot; \u003cem\u003eBMC pediatrics,\u0026nbsp;\u003c/em\u003evol. 18, no. 1, p. 16, 2018.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[58]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eT. Popowski, F. Goffinet, F. Maillard, T. Schmitz, S. Leroy and G. Kayem, \u0026quot;Maternal markers for detecting early-onset neonatal infection and chorioamnionitis in cases of premature rupture of membranes at or after 34 weeks of gestation: a two-center prospective study,\u0026quot; \u003cem\u003eBMC pregnancy and childbirth,\u0026nbsp;\u003c/em\u003evol. 11, no. 1, p. 26, 2011.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[59]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eA. Palatnik, L. Liu, A. Lee and L. Yee, \u0026quot;Predictors of early-onset neonatal sepsis or death among newborns born at\u0026lt; 32 weeks of gestation,\u0026quot; \u003cem\u003eJournal of Perinatology,\u0026nbsp;\u003c/em\u003evol. 39, no. 7, pp. 949-955, 2019.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[60]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eM. Griffin, T. O\u0026apos;Shea, E. Bissonette, F. Harrell, D. Lake and J. Moorman, \u0026quot;Abnormal heart rate characteristics preceding neonatal sepsis and sepsis-like illness,\u0026quot; \u003cem\u003ePediatric research,\u0026nbsp;\u003c/em\u003evol. 53, no. 6, pp. 920-926, 2003.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[61]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eI. Gur, A. Riskin, G. Markel, D. Bader, Y. Nave, B. Barzilay, F. Eyal and A. Eisenkraft, \u0026quot;Pilot study of a new mathematical algorithm for early detection of late-onset sepsis in very low-birth-weight infants,\u0026quot; \u003cem\u003eAmerican journal of perinatology,\u0026nbsp;\u003c/em\u003evol. 32, no. 04, pp. 321-330, 2015.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[62]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eJ. Bekhof, J. Reitsma, J. Kok and I. Van Straaten, \u0026quot;Clinical signs to identify late-onset sepsis in preterm infants,\u0026quot; \u003cem\u003eEuropean journal of pediatrics,\u0026nbsp;\u003c/em\u003evol. 172, no. 4, pp. 501-508, 2013.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[63]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eS. Dutta, R. Reddy, S. Sheikh, J. Kalra, P. Ray and A. Narang, \u0026quot;Intrapartum antibiotics and risk factors for early onset sepsis,\u0026quot; \u003cem\u003eArchives of Disease in Childhood-Fetal and Neonatal Edition,\u0026nbsp;\u003c/em\u003evol. 95, no. 2, pp. 99-103, 2010.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[64]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eM. Griffin and J. Moorman, \u0026quot;Toward the early diagnosis of neonatal sepsis and sepsis-like illness using novel heart rate analysis,\u0026quot; \u003cem\u003ePediatrics,\u0026nbsp;\u003c/em\u003evol. 107, no. 1, pp. 97-104, 2001.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[65]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eY. Hu, V. Lee and K. Tan, \u0026quot;An application of convolutional neural networks for the early detection of late-onset neonatal sepsis. In 2019 International Joint Conference on Neural Networks (IJCNN),\u0026quot; \u003cem\u003eIEEE.,\u0026nbsp;\u003c/em\u003epp. 1-8, 2019.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[66]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eD. Husada, P. Chanthavanich, U. Chotigeat, P. Sunttarattiwong, C. Sirivichayakul, K. Pengsaa, W. Chokejindachai and J. Kaewkungwal, \u0026quot;Predictive model for bacterial late-onset neonatal sepsis in a tertiary care hospital in Thailand,\u0026quot; \u003cem\u003eBMC infectious diseases,\u0026nbsp;\u003c/em\u003evol. 20, no. 1, pp. 1-11, 2020.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[67]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eR. Rosenberg, A. Ahmed, S. Saha, M. Chowdhury, S. Ahmed, P. Law, R. Black, M. Santosham and G. Darmstadt, \u0026quot;Nosocomial sepsis risk score for preterm infants in low-resource settings,\u0026quot; \u003cem\u003eJournal of tropical pediatrics,\u0026nbsp;\u003c/em\u003evol. 56, no. 2, pp. 82-89, 2010.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[68]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eA. Johnson, J. Aboab, J. Raffa, T. Pollard, R. Deliberato, L. Celi and D. Stone, \u0026quot;A comparative analysis of sepsis identification methods in an electronic database,\u0026quot; \u003cem\u003eCritical care medicine,\u0026nbsp;\u003c/em\u003evol. 46, no. 4, p. 494, 2018.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[69]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eT. Saito and M. Rehmsmeier, \u0026quot;The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets,\u0026quot; \u003cem\u003ePloS one,\u0026nbsp;\u003c/em\u003evol. 10, no. 3, p. e0118432, 2015.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[70]\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eE. Pinker, \u0026quot;Reporting accuracy of rare event classifiers,\u0026quot; \u003cem\u003eNPJ digital medicine,\u0026nbsp;\u003c/em\u003evol. 1, no. 1, pp. 1-2, 2018.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e"},{"header":"Tables","content":"Tables 6-10 and 12 are in the supplementary files section."}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Mbarara University of Science and Technology","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":true,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Neonatal sepsis, screening parameters, algorithms, models","lastPublishedDoi":"10.21203/rs.3.rs-1354764/v2","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-1354764/v2","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAbout 2.9\u0026nbsp;million neonates die every year worldwide, and most of these deaths occur in low-resource settings. Neonatal sepsis occurs when there is a bacterial invasion in the bloodstream; the immune system begins a systemic inflammatory response syndrome (SIRS) damaging to the body and can quickly advance to severe sepsis, multi-organ failure, and finally, death. Sepsis in neonates can progress more rapidly than in adults; therefore, a timely diagnosis is critical. The standard gold test for diagnosing neonatal sepsis is blood culture, which takes at least 72 hours. Hence, identifying key predictor variables and models that work best can help reduce neonatal morbidity and mortality.\u003c/p\u003e \u003cp\u003eThe matching articles were identified by searching the PubMed, IEEE, and Cochrane bibliography databases. For the inclusion of articles, the abstract and titles were first screened based on some predetermined criteria and then, the full-text articles were screened. Thirty-one studies met the full inclusion criteria. The duration of ROM was found to be more significant than other maternal risk factors. Heart rate and heart rate variability were found to be more significant than other neonatal clinical signs. C reactive protein and I/T ratio were found to be more significant than other laboratory tests. The main limitation is the variation in the performance measures used in the studies, which made it difficult to perform a quantitative assessment.\u003c/p\u003e \u003cp\u003eA combination of predictor variables has been shown to strengthen neonatal sepsis prediction, as shown by some of the reviewed studies. Predictive algorithms that combine multiple variables are urgently needed to improve models for early detection, prognosis, and treatment of neonatal sepsis.\u003c/p\u003e","manuscriptTitle":"Evaluation of screening parameters and machine learning models for the prediction of neonatal sepsis: A systematic review","msid":"","msnumber":"","nonDraftVersions":[{"code":2,"date":"2023-01-03 01:38:34","doi":"10.21203/rs.3.rs-1354764/v2","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}},{"code":1,"date":"2022-02-18 14:44:31","doi":"10.21203/rs.3.rs-1354764/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"719e72af-0294-4274-b75c-262916f86f77","owner":[],"postedDate":"January 3rd, 2023","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":10521173,"name":"Bioinformatics"},{"id":10521174,"name":"Computational Biology"}],"tags":[],"updatedAt":"2022-02-18T14:44:31+00:00","versionOfRecord":[],"versionCreatedAt":"2023-01-03 01:38:34","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v2","identity":"rs-1354764","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-1354764","identity":"rs-1354764","version":["v2"]},"buildId":"omnImTCwR2MFx8CMYfrG7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}