Construction of prognosis prediction model and visualization system of acute paraquat poisoning based on improved machine learning model

Construction of prognosis prediction model and visualization system of acute paraquat poisoning based on improved machine learning model | 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 Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Article Construction of prognosis prediction model and visualization system of acute paraquat poisoning based on improved machine learning model Long Li, Xinxuan Han, Zhigang Zhang, Tingyong Han, Peng Wu, Yisha Xu, and 7 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3829515/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Objective: This study aims to develop a prognosis prediction model and visualization system for acute paraquat poisoning based on an improved machine learning model. Methods: A total of 101 patients with acute paraquat poisoning admitted to 6 hospitals from March 2020 to March 2022 were selected for this study. The patients were divided into two groups, the survival group (n=37) and the death group (n=64), based on treatment results. The biochemical indexes of the patients were analyzed, and a prognosis prediction model for acute paraquat poisoning was constructed using HHO-XGBoost, an improved machine learning algorithm. Multivariate logistic analysis was used to verify the value of the self-screening features in the model. Results: Seven features were selected in the HHO-XGBoost model, including oral dose, serum creatinine, alanine aminotransferase (ALT), white blood cell (WBC) count, neutrophil count, urea nitrogen level, and thrombin time. Univariate analysis showed statistically significant differences between the survival group and death group for these features (P<0.05). Multivariate logistic analysis identified four features that were significantly associated with prognosis-serum creatinine level, oral dose, ALT level, and WBC count - indicating their critical significance in predicting outcomes. Conclusion: The HHO-XGBoost model based on machine learning is highly valuable in constructing a prognosis prediction model and visualization system for acute paraquat poisoning, which can provide important help for clinical prognosis prediction of patients with paraquat poisoning. Biological sciences/Biological techniques Biological sciences/Biophysics Biological sciences/Biotechnology Biological sciences/Evolution Machine learning model Acute paraquat poisoning Prediction model Visualization system construction Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Figure 6 Introduction As the lung is the main target organ, paraquat poisoning leads to pulmonary interstitial disease and interstitial pulmonary fibrosis, resulting in patient death. There is no effective treatment for paraquat poisoning, making it a challenging problem in the field of toxicology [ 1 – 3 ]. The majority of paraquat poisoning cases result from oral ingestion, while some cases are caused by skin exposure and inhalation. Once absorbed into the human body, paraquat is rapidly distributed to various organs within approximately 6 hours. Notably, the lungs exhibit the highest concentration of paraquat, ranging from 10 to 90 times higher than other tissues and organs [ 4 – 7 ]. Due to the continuous occurrence of paraquat poisoning, researchers in various countries have conducted numerous clinical and basic studies. Studies on the mechanism of paraquat poisoning and damage have revealed that oxidative stress, such as the generation of reactive oxygen species (ROS) and other immune stimulatory effects released in large quantities, is associated with paraquat poisoning and damage, leading to tissue damage and intracellular calcium overload [ 8 – 10 ]. Many researchers have studied the early lesions of paraquat poisoning and have determined that early diagnosis and treatment are key factors in saving patients with paraquat poisoning [ 11 – 13 ]. The field of medicine has witnessed the emergence of machine learning, an artificial intelligence algorithm that has gained prominence in recent years. This algorithm exhibits continuous organization, adaptation, and learning capabilities during training, making it one of the most extensively employed neural network algorithms. In the field of medicine, machine learning techniques can be effectively employed for multivariate regression modeling, discerning intricate non-linear classifications, and various other applications[ 14 – 16 ]. Machine learning has been employed for the early detection of tumor diseases, regression prediction in disease treatment, and exploration of novel compounds in research and drug development [ 17 – 18 ]. The objective of this study is to investigate the development of a prognosis prediction model and visualization system for acute paraquat poisoning based on an enhanced machine learning approach, aiming to facilitate clinical diagnosis and prognostic assessment of acute paraquat poisoning. 1 Data and Methods 1.1 General Information This study was a retrospective study. A total of 101 patients with acute paraquat poisoning were selected from 6 hospitals between March 2020 and March 2022, and they were categorized into the survival group (n = 37) and death group (n = 64) based on treatment outcomes. There were no significant differences in gender, age, body mass index, receive pre-hospital care, time from poisoning to treatment between the two groups (P > 0.05). The duration of treatment in the death group was significantly shorter than that in the survival group (P < 0.05); The death time of the death group was 2–24 hours, with an average of (11.33 ± 6.41)h,as presented in Table 1 . Prior to implementation, the study was approved by the Ethics committee of the 6 hospitals[Ethics committee of the 945th Hospital of the Joint Logistics Support Force of the Chinese People's Liberation Army(Ethical Application Ref: 202200015);Ethics committee of Mingshan District People's Hospital of Ya 'an(Ethics Review 2022 No. 18);Medical Ethics Committee of Ya'an Polytechnic College Affiliated Hospital(Ethics Review 2022 No. 023);Ethics committee of Yucheng District People's Hospital of Ya 'an(No. 202204032);Ethical review opinions of Ya 'an People's Hospital(No. 2022-0014);Ethics committee of Ya 'an Traditional Chinese Medicine Hospital(2022 No. 021)]. This study was a retrospective analysis, and informed consent of patients could be waived(Ethics committee of the 945th Hospital of the Joint Logistics Support Force of the Chinese People's Liberation Army granted the waiver of patient informed consent), and this study was in accordance with the requirements and regulations of the World Medical Declaration of Helsinki. Table 1 Comparison of general data between the two groups Index Surviva groups( n = 37) Death groups( n = 64) t/χ 2 p Age (year) 31.30 ± 9.06 32.17 ± 12.03 -0.384 0.702 Gender 0.188 0.665 Male 19(51.35) 30(46.88) Female 18(48.65) 34(53.12) Body mass index(kg/m 2 ) 19.74 ± 2.12 20.60 ± 3.55 -1.330 0.187 Receive pre-hospital care 9(24.32) 28(43.75) 0.221 0.638 Time from poisoning to start of treatment(min) 42.49 ± 26.07 50.31 ± 23.62 -1.544 0.126 Duration of treatment(h) 22.16 ± 19.50 11.33 ± 6.41 4.090 < 0.001 1.2 Inclusion and exclusion criteria Inclusion criteria: ① All patients fulfilled the diagnostic criteria for [ 19 ]; ② No patients with congenital immune dysfunction were included. Exclusion criteria: ① Patients with excretory organ disorders; ② Combined with other poisoning patients; ③ The poisoning time has exceeded 24 hours. 1.3 Methods All patients underwent gastric lavage using a sodium bicarbonate solution (Sinopod Rongsheng Pharmaceutical Co., LTD., Sinopod Approval number H20013007, specifications: 250 mL), followed by oral administration of 120–200 mL of 15% white clay and 50 mL of mannitol + 6 g rhubarb powder /50 g manganese to induce diarrhea. Additionally, hemoplavage and hemodialysis were performed. Immunosuppressants including cyclophosphamide (Zhejiang Hisun Pharmaceutical Co., LTD., Sinophora H20084627, specification: 50 mg) and Eugene (Tianjin Tianyu Pharmaceutical Co., LTD., Sinophora H20020224, specification: 4 mg) were administered via injection. The data on ALT, blood creatinine, WBC, neutrophil count, blood urea nitrogen, and prothrombin time were collected within 24 hours of admission for patients with paraquat poisoning. The detection methods for each index are as follows: ALT levels were determined using an automatic clinical biochemical analyzer after extracting 2–3 mL of venous blood from the body surface and centrifuging it to obtain serum supernatant. Serum creatinine and blood urea nitrogen concentrations were measured using a Pran blood gas analyzer after extracting 1–2 mL of venous blood from the body surface and adding it to routine EDTA anticoagulant test tubes or heparinized test tubes. Prothrombin time was determined using a blood coagulator method. WBC and neutrophils were detected using a TEK8520 automatic five-classification blood cell analyzer. Synchronous optimization: Leveraging the robust global optimization capability of swarm intelligence algorithms, this study synchronizes the steps of feature screening and hyperparameter optimization in machine learning models. The Harris Hawks Optimization (HHO) algorithm is chosen for its strong global search ability and minimal parameter adjustments required. Building upon the basic algorithm, Tent Chaotic initialization is introduced to evenly distribute the initial population of Harris hawks across the search space. Additionally, a lens imaging reverse learning strategy is incorporated to enhance the algorithm's capacity for escaping local optima. As shown in Fig. 1. The selection of the XGBoost algorithm was based on optimizing the XGBoost model using HHO, and a hybrid HHO-XGBoost model was constructed. This model was compared with traditional XGBoost models, utilizing a total of 101 samples. Among these samples, 80% (n = 81) were randomly assigned to the training set, while the remaining 20% (20 cases) formed the test set. To prevent overfitting, a 5-fold cross-validation was performed on the training set. 1.4 Statistical Analysis Statistical analysis was performed using SPSS 26.0 software. Measurement data that followed a normal distribution were denoted as (Mean ± Standard Deviation) and analyzed using the T-test. Count data were expressed as percentages (%) and analyzed using either the χ2 test or Fisher's exact probability test. A significance level of P < 0.05 was considered statistically significant. 2 Results 2.1 Improved HHO algorithm performance test The performance of the improved HHO algorithm was evaluated using a set of 23 standard test functions. Comparative analysis was conducted with other swarm intelligence optimization algorithms, including genetic algorithm (GA), particle swarm optimization (PSO), multiverse optimization algorithm (MVO), and Sparrow optimization algorithm (SSA). The results demonstrate significant performance advantages of the improved HHO algorithm. As shown in Fig. 2. 2.2 Construction of synchronous optimization prediction model The ROC-AUC and PR-AUC of the HHO-XGBoost model were 0.9433 and 0.9720 on the training set and 0.9167 and 0.9583 on the test set, respectively, which were significantly higher than those of the other three models. Ultimately, seven characteristics were selected for the HHO-XGBoost model: oral dose, serum creatinine level, ALT level, WBC count, neutrophil count, urea nitrogen level and thrombin time. The training and validation results of the model are presented in Table 2 and Table 3 respectively; Fig. 3 and Fig. 4 depict these results. Table 2 Training set Model PRE SEN SPE ACC F1 ROC-AUC PR-AUC LR 0.8400 0.8077 0.7241 0.7778 0.8235 0.8541 0.9127 SVM 0.8035 0.8654 0.6207 0.7778 0.8333 0.9055 0.9492 XGBoost 0.8246 0.9039 0.6552 0.8148 0.8624 0.9237 0.9590 HHO-XGBoost 0.9575 0.8654 0.9310 0.8889 0.9091 0.9433 0.9720 Table 3 Test set Model PRE SEN SPE ACC F1 ROC-AUC PR-AUC LR 0.6667 0.8333 0.3750 0.6500 0.7407 0.6042 0.7896 SVM 0.6667 0.6667 0.5000 0.6000 0.6667 0.6563 0.8363 XGBoost 0.8000 0.6667 0.7500 0.7000 0.7273 0.7500 0.8257 HHO-XGBoost 1.0000 0.6667 1.0000 0.8000 0.8000 0.9167 0.9583 2.3 Verification of the effect of screening characteristics on acute paraquat death 2.3.1 Single factor analysis The Ho-xgboost screening of 7 features revealed statistically significant differences between the survival and death groups (P < 0.05), indicating the critical significance of the variables selected by HHO-XGBoost, as presented in Table 4 . Table 4 Univariate analysis of survival group and death group Index Surviva groups( n = 37) Death groups( n = 64) t p Oral dose(ML) 25.08 ± 13.41 73.31 ± 17.30 -14.603 < 0.001 Serum creatinine(µmol/L) 79.97 ± 32.16 192.36 ± 94.71 -8.668 < 0.001 Urea nitrogen(mmol/L) 4.27 ± 1.90 8.20 ± 3.39 -7.483 < 0.001 ALT(U/L) 15.35 ± 5.43 26.27 ± 11.85 -6.312 < 0.001 WBC(10 9 /L) 11.55 ± 4.40 21.83 ± 10.62 -6.802 < 0.001 Neutrophil count(10 9 /L) 8.92 ± 2.61 18.94 ± 7.00 -10.275 < 0.001 Thrombin time(s) 16.73 ± 2.57 19.25 ± 2.29 -5.098 < 0.001 2.3.2 Multifactor analysis The multifactor analysis was conducted using stepwise logistic regression, resulting in the inclusion of four significant features in the equation: serum creatinine, oral dose, ALT, and WBC. These variables were identified as critical by HHO-XGBoost screening, as presented in Table 5 . Table 5 Multivariate analysis of survival group and death group Index β SE Z Wald χ 2 P OR 95% CI Serum creatinine 0.061 0.023 2.601 6.766 0.009 1.063 1.015 ~ 1.113 Oral dose 0.849 0.356 2.385 5.689 0.017 2.338 1.164 ~ 4.699 ALT 0.446 0.157 2.835 8.034 0.005 1.563 1.148 ~ 2.128 WBC 0.380 0.189 2.004 4.017 0.045 1.462 1.008 ~ 2.119 Intercept -25.545 8.565 -2.982 8.895 0.003 0.000 0.000 ~ 0.000 2.4 Visualization system construction As shown in Figs. 5 and 6, the visualization system can directly output the risk of patient death after inputting patient-related indicators. 3 Discussion The widespread use of Paraquat worldwide can be attributed to its effective application, affordability, and minimal environmental impact. However, in recent years, the occurrence of paraquat poisoning incidents has significantly impacted individuals' daily lives[ 20 – 22 ]. The findings of various studies have demonstrated that patients with paraquat poisoning experience severe damage to their major vital organs, particularly the lungs which can develop pulmonary fibrosis, ultimately resulting in asphyxiation and potential fatality even when conscious. Due to the lack of effective antidotes, the mortality rate associated with paraquat poisoning reaches an alarming 80%, significantly compromising societal safety [ 23 ]. Despite the diligent efforts of numerous researchers in search of efficacious treatments and early diagnostic methods for paraquat poisoning, the current clinical mortality rate remains considerably high. Therefore, the timely evaluation of clinical outcomes and risk assessment for critically ill patients with paraquat poisoning is of utmost importance in facilitating accurate clinical diagnosis and treatment, as well as establishing a strong connection between public medical services and social welfare [ 24 ]. The gold standard for diagnosing clinical acute paraquat poisoning is the identification of paraquat components or metabolites in blood or urine samples[ 25 ]. Several studies have demonstrated that paraquat can be detected in urine within 6 hours of ingestion, and a paraquat concentration exceeding 30 mg/L in the blood is indicative of an unfavorable prognosis[ 26 ]. The qualitative and quantitative analysis of paraquat in blood or urine was not conducted in this study, highlighting the need for future research. With the advancement of machine learning and its integration into medical care, recent studies have demonstrated that predictive machine learning models can provide valuable insights for guiding future clinical trials of antidotes and other treatment modalities [ 27 ]. The XGBoost algorithm currently stands as the preeminent open-source tool in clinical applications, renowned for its exceptional computational prowess. XGBoost, a widely adopted open-source tool in clinical applications, exhibits exceptional speed and performance. It efficiently handles millions or even hundreds of millions of data points simultaneously, mitigating the challenges associated with error-prone manual processing, missing data points, and inaccurate analysis outcomes. Moreover, machine learning enables automated processing and analysis of extensive datasets to swiftly uncover patterns and insights, thereby providing precise and valuable support for professional endeavors as well as daily life. Compared to alternative models, the XGBoost model exhibits commonly utilized indicators in clinical practice, while maintaining a low cost and easy accessibility of data for any hospital. The XGBoost model not only enables programmatic analysis of data but also facilitates summarization of analyzed data and obtained results, thereby enhancing analysis efficiency and prediction accuracy [ 28 – 31 ]. The HHO-XGBoost model was employed to screen 7 features in this study, including oral dose, serum creatinine, ALT, white blood cell count, neutrophil count, urea nitrogen, and thrombin time. Additionally, logistic regression multivariate analysis revealed that serum creatinine, oral dosage, ALT, and WBC were all included as screening variables. The prognosis of oral paraquat is closely correlated with the administered oral dosage, thereby accounting for the underlying reasons. The literature suggests that the lethal dose of oral paraquat ranges from 1 to 3 g. When the dosage is below 20 mg/kg, appropriate treatment can usually prevent life-threatening consequences, leading to complete recovery in most patients. For individuals receiving a single oral dose between 20 and 40 mg/kg, mortality occurs within a period of two to three weeks. Those exposed to a single oral dose equal to or exceeding 40 mg/kg succumb within one to four days[ 32 ]. The kidneys exhibit the highest concentration of paraquat during the early stages of poisoning. Paraquat is not reabsorbed in renal tubules but rather excreted from the kidney in its original form with weak binding to plasma proteins. Consequently, serum creatinine serves as a reliable indicator of renal function and exhibits a close association with prognosis among patients suffering from acute paraquat poisoning[ 33 ]. The administration of Paraquat may induce activation of the sympathetic-adrenal medulla axis, leading to a redistribution of renal blood flow from the cortex to predominantly supply the medulla, thereby resulting in an elevation in serum creatinine levels [ 34 ]. By inducing proximal renal tubule destruction, paraquat disrupts the mitochondrial transmission chain and instigates the generation of reactive oxygen species. The subsequent production of a substantial amount of reactive oxygen species indirectly triggers sulfhydryl compound formation within the body, thereby accelerating lipid cell damage and peroxidation while elevating ALT levels. Studies have revealed a close association between paraquat poisoning and alterations in inflammatory cytokines. The elevation in toxin concentration is correlated with an increase in inflammatory cytokines, and as time progresses, the levels of inflammatory cells consistently rise, demonstrating dynamic changes throughout the entire experiment [ 34 ]. The primary molecular mechanism underlying paraquat toxicity involves disruption of the body's REDOX system and induction of intracellular oxidative stress. Paraquat-induced alterations in cytokines, particularly inflammatory factors, play a pivotal role in the development of acute lung injury and subsequent pulmonary fibrosis resulting from paraquat poisoning. Therefore, the level of white blood cells is closely associated with the prognosis of patients suffering from paraquat poisoning [ 35 ]. 4 Conclusion In the context of acute paraquat poisoning, the HHO-XGBoost model based on machine learning holds significant implications for developing prognosis prediction models and visualization systems, which can provide important help for clinical prognosis prediction of patients with paraquat poisoning. The relevant detection indicators of patients within 24 hours can be inputted into the visualization system, enabling risk assessment for mortality and providing valuable assistance to clinicians in guiding subsequent treatment. The present study, however, has certain limitations with regards to the representativeness of the sample due to its retrospective design. The limited sample size of this study, however, poses challenges in accurately representing the entire target group. Additionally, the prognosis of patients with paraquat poisoning may be influenced by other factors not accounted for in the observational indicators utilized in this study, potentially impacting the interpretation and inference of the findings. To address these limitations, future investigations can adopt the following measures to enhance the experimental design. Firstly, we recommend adopting a more comprehensive approach in the selection of samples, and considering an increase in sample size to enhance the representativeness and generalizability of the findings. Furthermore, future research endeavors should encompass a broader range of indicators and variables in order to attain a comprehensive understanding of the research topic. The utilization of this extension can yield more precise outcomes and facilitate in-depth deductions. Finally, prospective studies are implemented to enhance control over variables, improve the management of observed outcome dynamics, and strengthen causal inference. Declarations Ethics approval: The study was approved by the Ethics committee of the 6 hospitals[Ethics committee of the 945th Hospital of the Joint Logistics Support Force of the Chinese People's Liberation Army(Ethical Application Ref: 202200015);Ethics committee of Mingshan District People's Hospital of Ya 'an(Ethics Review 2022 No. 18);Medical Ethics Committee of Ya'an Polytechnic College Affiliated Hospital(Ethics Review 2022 No. 023);Ethics committee of Yucheng District People's Hospital of Ya 'an(No. 202204032);Ethical review opinions of Ya 'an People's Hospital(No. 2022-0014);Ethics committee of Ya 'an Traditional Chinese Medicine Hospital(2022 No. 021)]. Consent for publication: This study was a retrospective analysis, and informed consent of patients could be waived. The study was approved by the ethics committee of the 6 hospitals. Availability of data and materials: All data generated or analysed during this study are included in this published article [and its supplementary information files]. Competing interests: The authors declare that they have no competing interests. Funding: There was no funding support for this research. Authors' contributions: MZ:Formulation of overarching research goals and aims;Oversight and leadership responsibility for the research activity planning and execution, including mentorship external to the core team. XH:Management and coordination responsibility for the research activity planning and execution. ZZ、TH、PW、YX、LZ、ZL、ZX、HL、XY、PH:Conducting a research and investigation process, specifically data collection. LL:Writing the initial draft (including substantive translation);Programming; software development; designing computer programs; implementation of the computer code and supporting algorithms; testing of existing code components; Application of statistical, mathematical, computational to analyze data. All authors read and approved the final manuscript. Acknowledgements: Not applicable. References Chen F, Ye Y, Jin B, Yi B, Wei Q, Liao L. Homicidal Paraquat Poisoning. J Forensic Sci. 2019;64(3):941–945. doi: 10.1111/1556-4029.13945 . Kakkar A, Jandial A, Suri V. Atrocious tetrad in paraquat poisoning. QJM. 2022;115(5):310–311. doi: 10.1093/qjmed/hcac077 . Ruwanpura R, Nandasiri C. Homicidal Paraquat Poisoning Following Ligature Strangulation. Acad Forensic Pathol. 2019;9(3–4):212–216. doi: 10.1177/1925362119891704 . Sukumar CA, Shanbhag V, Shastry AB. Paraquat: The Poison Potion. Indian J Crit Care Med. 2019;23(Suppl 4):S263-S266. doi: 10.5005/jp-journals-10071-23306 . Trakulsrichai S, Paisanrodjanarat B, Sriapha C, Tongpoo A, Udomsubpayakul U, Wananukul W. Clinical outcome of paraquat poisoning during pregnancy. Clin Toxicol (Phila). 2019;57(8):712–717. doi: 10.1080/15563650.2018.1549328 . Zhang S, Song S, Luo X, Liu J, Liu M, Li W, Cao T, Li N, Zeng C, Zhang B, Cai H. Prognostic value of liver and kidney function parameters and their correlation with the ratio of urine-to-plasma paraquat in patients with paraquat poisoning. Basic Clin Pharmacol Toxicol. 2021;128(6):822–830. doi: 10.1111/bcpt.13555 . Eizadi-Mood N, Jaberi D, Barouti Z, Rahimi A, Mansourian M, Dorooshi G, Sabzghabaee AM, Alfred S. The efficacy of hemodialysis on paraquat poisoning mortality: A systematic review and meta-analysis. J Res Med Sci. 2022;27:74. doi: 10.4103/jrms.jrms_235_21 . Moar JJ, Hill L. Histopathological Findings in a Fatal Case of Paraquat Poisoning. Am J Forensic Med Pathol. 2022;43(1):69–72. doi: 10.1097/PAF.0000000000000698 . Kumar S, Gupta S, Bansal YS, Bal A, Rastogi P, Muthu V, Arora V. Pulmonary histopathology in fatal paraquat poisoning. Autops Case Rep. 2021;11:e2021342. doi: 10.4322/acr.2021.342 . Qiu L, Deng Y. Paraquat Poisoning in Children: A 5-Year Review. Pediatr Emerg Care. 2021;37(12):e846-e849. doi: 10.1097/PEC.0000000000001868 . Liu Z, Huang F, Zhao S, Ma L, Shi Q, Zhou Y. Homicidal paraquat poisoning: Poisoned while drinking. J Forensic Sci. 2022;67(3):1312–1319. doi: 10.1111/1556-4029.14968. . Chen CK, Yeh YT, Mégarbane B, Chen YC, Chen KF, Chang CH, Lin CC. A novel flowchart to predict mortality and analyse effectiveness of routinely used pharmacological regimens in paraquat poisoning. Basic Clin Pharmacol Toxicol. 2021;129(6):496–503. doi: 10.1111/bcpt.13652 . Dambal A, Naik S, Hemamalini G, Siddaganga S, Kashinkunti MD. Reasons for under-reporting of paraquat poisoning in India. Natl Med J India. 2021 May-Jun;34(3):138–142. doi: 10.25259/NMJI_383_19. . Choi RY, Coyner AS, Kalpathy-Cramer J, Chiang MF, Campbell JP. Introduction to Machine Learning, Neural Networks, and Deep Learning. Transl Vis Sci Technol. 2020;9(2):14. doi: 10.1167/tvst.9.2.14. . Silva GFS, Fagundes TP, Teixeira BC, Chiavegatto Filho ADP. Machine Learning for Hypertension Prediction: a Systematic Review. Curr Hypertens Rep. 2022;24(11):523–533. doi: 10.1007/s11906-022-01212-6 .. Sultan AS, Elgharib MA, Tavares T, Jessri M, Basile JR. The use of artificial intelligence, machine learning and deep learning in oncologic histopathology. J Oral Pathol Med. 2020;49(9):849–856. doi: 10.1111/jop.13042 . Peiffer-Smadja N, Rawson TM, Ahmad R, Buchard A, Georgiou P, Lescure FX, Birgand G, Holmes AH. Machine learning for clinical decision support in infectious diseases: a narrative review of current applications. Clin Microbiol Infect. 2020;26(5):584–595. doi: 10.1016/j.cmi.2019.09.009 . Lo Vercio L, Amador K, Bannister JJ, Crites S, Gutierrez A, MacDonald ME, Moore J, Mouches P, Rajashekar D, Schimert S, Subbanna N, Tuladhar A, Wang N, Wilms M, Winder A, Forkert ND. Supervised machine learning tools: a tutorial for clinicians. J Neural Eng. 2020;17(6). doi: 10.1088/1741-2552/abbff2 . Dinis-Oliveira RJ, Duarte JA, Sánchez-Navarro A, Remião F, Bastos ML, Carvalho F. Paraquat poisonings: mechanisms of lung toxicity, clinical features, and treatment. Crit Rev Toxicol. 2008;38(1):13–71. doi: 10.1080/10408440701669959 . Kumar MS, Shekhawat RS, Kanchan T, Midha NK. Diagnostic Dilemma in Fatal Paraquat Poisoning: An Autopsy Case Report. Acad Forensic Pathol. 2023;13(2):80–85. doi: 10.1177/19253621231184612 . Zhang X, Xu X, Li S, Li L, Zhang J, Wang R. A Synthetic Receptor as a Specific Antidote for Paraquat Poisoning. Theranostics. 2019;9(3):633–645. doi: 10.7150/thno.31485 . Chen H, Yang R, Tang Y, Fu X. Effects of curcumin on artery blood gas index of rats with pulmonary fibrosis caused by paraquat poisoning and the expression of Smad 4, Smurf 2, interleukin-4 and interferon-γ. Exp Ther Med. 2019;17(5):3664–3670. doi: 10.3892/etm.2019.7341 . James N, Bakshi R, Rudresh SS, Kaushik K, Ghumaan KS, Pannu AK. Pneumoperitoneum from pneumomediastinum in paraquat poisoning. Trop Doct. 2021;51(2):241–242. doi: 10.1177/0049475520960872 . Ravichandran R, Amalnath D, Shaha KK, Srinivas BH. Paraquat Poisoning: A Retrospective Study of 55 Patients From a Tertiary Care Center in Southern India. Indian J Crit Care Med. 2020;24(3):155–159. doi: 10.5005/jp-journals-10071-23369 . Jha M, Gaur N. Paraquat poisoning with spontaneous pneumothorax in the era of online shopping. J Family Med Prim Care. 2022;11(1):357–359. doi: 10.4103/jfmpc.jfmpc_957_21 . Sharma DS, Prajapati AM, Shah DM. Review of a Case of Paraquat Poisoning in a Tertiary Care Rural-based ICU. Indian J Crit Care Med. 2019;23(6):284–286. doi: 10.5005/jp-journals-10071-23182 . Kim SS, Hwang KS, Kan H, Yang JY, Son Y, Shin DS, Lee BH, Chae CH, Bae MA. Neurotoxicological Profiling of Paraquat in Zebrafish Model. Neurochem Res. 2022;47(8):2294–2306. doi: 10.1007/s11064-022-03615-y . Chen H, Hu L, Li H, Hong G, Zhang T, Ma J, Lu Z. An Effective Machine Learning Approach for Prognosis of Paraquat Poisoning Patients Using Blood Routine Indexes. Basic Clin Pharmacol Toxicol. 2017;120(1):86–96. doi: 10.1111/bcpt.12638 . Hu L, Li H, Cai Z, Lin F, Hong G, Chen H, Lu Z. A new machine-learning method to prognosticate paraquat poisoned patients by combining coagulation, liver, and kidney indices. PLoS One. 2017;12(10):e0186427. doi: 10.1371/journal.pone.0186427 . Wen C, Lin F, Huang B, Zhang Z, Wang X, Ma J, Lin G, Chen H, Hu L. Metabolomics Analysis in Acute Paraquat Poisoning Patients Based on UPLC-Q-TOF-MS and Machine Learning Approach. Chem Res Toxicol. 2019;32(4):629–637. doi: 10.1021/acs.chemrestox.8b00328 . Hu L, Hong G, Ma J, Wang X, Chen H. An efficient machine learning approach for diagnosis of paraquat-poisoned patients. Comput Biol Med. 2015;59:116–124. doi: 10.1016/j.compbiomed.2015.02.003. . Chen CK, Chen YC, Mégarbane B, Yeh YT, Chaou CH, Chang CH, Lin CC. The acute paraquat poisoning mortality (APPM) score to predict the risk of death in paraquat-poisoned patients. Clin Toxicol (Phila). 2022;60(4):446–450. doi: 10.1080/15563650.2021.1979234 . Panda PK, Manna S, Bhasi A, Singh SS, Maneesh VS. Paraquat poisoning in Andaman and Nicobar Islands - Government must intervene. J Family Med Prim Care. 2021;10(4):1780–1784. doi: 10.4103/jfmpc.jfmpc_2020_20. . Ahmad J, D'Angelo K, Rivas M, Mahal M, Nookala V, Kulakauskiene D, Makaryus AN. Dilated Cardiomyopathy Associated with Paraquat Herbicide Poisoning. Clin Pract. 2021;11(3):679–686. doi: 10.3390/clinpract11030083. . Lv B, Han DF, Chen J, Zhao HB, Liu XL. Can kissing cause paraquat poisoning: A case report and review of literature. World J Clin Cases. 2021;9(20):5588–5593. doi: 10.12998/wjcc.v9.i20.5588 . Additional Declarations No competing interests reported. Supplementary Files newdatad1.xlsx Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version 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 Advisory Board 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-3829515","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":265509083,"identity":"7632e530-cb7a-415d-9db6-1f2ed02877f8","order_by":0,"name":"Long Li","email":"","orcid":"","institution":"The 945th Hospital of the Joint Logistics Support Force of the Chinese People's Liberation Army","correspondingAuthor":false,"prefix":"","firstName":"Long","middleName":"","lastName":"Li","suffix":""},{"id":265509084,"identity":"dfd682a6-8a5e-4027-8af2-6cd6a0aa2d66","order_by":1,"name":"Xinxuan Han","email":"","orcid":"","institution":"The 945th Hospital of the Joint Logistics Support Force of the Chinese People's Liberation Army","correspondingAuthor":false,"prefix":"","firstName":"Xinxuan","middleName":"","lastName":"Han","suffix":""},{"id":265509085,"identity":"0fb4bbaa-fbb9-4ac2-afb4-036d6fad03b6","order_by":2,"name":"Zhigang Zhang","email":"","orcid":"","institution":"Mingshan District People's Hospital of Ya 'an","correspondingAuthor":false,"prefix":"","firstName":"Zhigang","middleName":"","lastName":"Zhang","suffix":""},{"id":265509086,"identity":"c3d3265a-c3a8-4c5b-ba50-09735eddb093","order_by":3,"name":"Tingyong Han","email":"","orcid":"","institution":"Ya'an Polytechnic College Aûliated Hospital","correspondingAuthor":false,"prefix":"","firstName":"Tingyong","middleName":"","lastName":"Han","suffix":""},{"id":265509087,"identity":"ab0defa0-cfc7-47df-bcd6-a32b5fb68b38","order_by":4,"name":"Peng Wu","email":"","orcid":"","institution":"Yucheng District People's Hospital of Ya'an","correspondingAuthor":false,"prefix":"","firstName":"Peng","middleName":"","lastName":"Wu","suffix":""},{"id":265509088,"identity":"6768292a-e06d-442d-b1eb-d22b87bbe9b1","order_by":5,"name":"Yisha Xu","email":"","orcid":"","institution":"Ya'an People's Hospital","correspondingAuthor":false,"prefix":"","firstName":"Yisha","middleName":"","lastName":"Xu","suffix":""},{"id":265509089,"identity":"ea867e2a-4827-4303-b822-e9cb2a18c4b9","order_by":6,"name":"Liangjie Zhang","email":"","orcid":"","institution":"Ya'an Traditional Chinese Medicine Hospital","correspondingAuthor":false,"prefix":"","firstName":"Liangjie","middleName":"","lastName":"Zhang","suffix":""},{"id":265509090,"identity":"ab947d91-cd8d-4593-bc5a-05588e2ff883","order_by":7,"name":"Zhenyi Liu","email":"","orcid":"","institution":"The 945th Hospital of the Joint Logistics Support Force of the Chinese People's Liberation Army","correspondingAuthor":false,"prefix":"","firstName":"Zhenyi","middleName":"","lastName":"Liu","suffix":""},{"id":265509091,"identity":"b51ff795-9531-4827-8cbf-ed9bb24c40e7","order_by":8,"name":"Zhenzhong Xi","email":"","orcid":"","institution":"The 945th Hospital of the Joint Logistics Support Force of the Chinese People's Liberation Army","correspondingAuthor":false,"prefix":"","firstName":"Zhenzhong","middleName":"","lastName":"Xi","suffix":""},{"id":265509092,"identity":"d2eb5a25-83c2-46ba-9a83-77b346f6ff1b","order_by":9,"name":"Haoran Li","email":"","orcid":"","institution":"The 945th Hospital of the Joint Logistics Support Force of the Chinese People's Liberation Army","correspondingAuthor":false,"prefix":"","firstName":"Haoran","middleName":"","lastName":"Li","suffix":""},{"id":265509093,"identity":"13a71c34-05f2-4043-8ead-d7c298b7e691","order_by":10,"name":"Xiangjiang Yu","email":"","orcid":"","institution":"The 945th Hospital of the Joint Logistics Support Force of the Chinese People's Liberation Army","correspondingAuthor":false,"prefix":"","firstName":"Xiangjiang","middleName":"","lastName":"Yu","suffix":""},{"id":265509094,"identity":"e19e007a-1e84-4665-8eb7-1ee57eb28914","order_by":11,"name":"Pan He","email":"","orcid":"","institution":"The 945th Hospital of the Joint Logistics Support Force of the Chinese People's Liberation Army","correspondingAuthor":false,"prefix":"","firstName":"Pan","middleName":"","lastName":"He","suffix":""},{"id":265509095,"identity":"7ed6c43c-4752-4717-8b5a-ac1e7fc695fd","order_by":12,"name":"Ming Zhang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABDklEQVRIiWNgGAWjYDACCRjJzHz8x4cKGzk29vYDRGphZ0uQnHEmzZiP50wCMVqAgJ/HQJq35VDiPAkHA7w65Gc3P3v4NcciT96Zx8BwZsOB9DYJhgSGHxXbcGphnHPM3Fh2m0Sx4WG2goSPO+7ktkk3HmDsOXMbpxZmiQQzacltEokbm5k3HJx55llum8yBBGbGNtxa2CTSv0G1MBg287YdTmeTSDDAq4VHIsdM8iNQy3xmFmNmoJYEglokJHLKpBmBWjYws6UxAgPZsA0YyAfx+UV+Rvo2yZ/b6hLn9x8+xgCMSnn59vaDD35U4NYCDgIeIGFwAEnkAHaFCMD4A2RdAyFlo2AUjIJRMGIBAKlFWfzakXdiAAAAAElFTkSuQmCC","orcid":"","institution":"The 945th Hospital of the Joint Logistics Support Force of the Chinese People's Liberation Army","correspondingAuthor":true,"prefix":"","firstName":"Ming","middleName":"","lastName":"Zhang","suffix":""}],"badges":[],"createdAt":"2024-01-02 12:44:26","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-3829515/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-3829515/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":49324601,"identity":"8c2c862c-1d44-4e23-99e0-35738320e75d","added_by":"auto","created_at":"2024-01-08 17:19:37","extension":"jpg","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":55901,"visible":true,"origin":"","legend":"\u003cp\u003eSchematic diagr am of synchr onous optimization\u003c/p\u003e","description":"","filename":"1.jpg","url":"https://assets-eu.researchsquare.com/files/rs-3829515/v1/6a55296635bce63cae87fb8a.jpg"},{"id":49327055,"identity":"a9afb372-fa50-4c06-9bdb-b14feefb47aa","added_by":"auto","created_at":"2024-01-08 17:35:38","extension":"jpg","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":733006,"visible":true,"origin":"","legend":"\u003cp\u003eSearch space and convergence curve of the base function\u003c/p\u003e","description":"","filename":"2.jpg","url":"https://assets-eu.researchsquare.com/files/rs-3829515/v1/47afc85d095e1089450088b4.jpg"},{"id":49324602,"identity":"8363dad0-bc81-4ba3-91e7-00538f5f95d1","added_by":"auto","created_at":"2024-01-08 17:19:37","extension":"jpg","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":68661,"visible":true,"origin":"","legend":"\u003cp\u003eillustrates the comparative performance of the model on the training set.\u003c/p\u003e","description":"","filename":"3.jpg","url":"https://assets-eu.researchsquare.com/files/rs-3829515/v1/90c9e4ffae674875c93686dd.jpg"},{"id":49324603,"identity":"3c35bbc5-7312-449b-8b2f-51a968630b28","added_by":"auto","created_at":"2024-01-08 17:19:38","extension":"jpg","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":78423,"visible":true,"origin":"","legend":"\u003cp\u003eillustrates the comparative performance of the model on the test set.\u003c/p\u003e","description":"","filename":"4.jpg","url":"https://assets-eu.researchsquare.com/files/rs-3829515/v1/c4042bec1b6e29e7c67e8744.jpg"},{"id":49325621,"identity":"bac1aeda-0056-4b66-975c-006725bcbf88","added_by":"auto","created_at":"2024-01-08 17:27:38","extension":"jpg","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":50929,"visible":true,"origin":"","legend":"\u003cp\u003eIllustrates the low-risk outcome of death\u003c/p\u003e","description":"","filename":"5.jpg","url":"https://assets-eu.researchsquare.com/files/rs-3829515/v1/a1a48704af0325265a1bfb07.jpg"},{"id":49324606,"identity":"92cdf353-f4de-4bf7-a270-56f074f983f5","added_by":"auto","created_at":"2024-01-08 17:19:38","extension":"jpg","order_by":6,"title":"Figure 6","display":"","copyAsset":false,"role":"figure","size":59836,"visible":true,"origin":"","legend":"\u003cp\u003eillustrates the high-risk outcome of death\u003c/p\u003e","description":"","filename":"6.jpg","url":"https://assets-eu.researchsquare.com/files/rs-3829515/v1/54c6cc3d8637eb2f1b0d17b6.jpg"},{"id":51541376,"identity":"27259000-cc64-4a25-a347-e245f4530029","added_by":"auto","created_at":"2024-02-23 11:30:53","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":779164,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3829515/v1/adea85c1-6199-46c8-ad08-409f23cd177b.pdf"},{"id":49325619,"identity":"00eb6648-5272-4f2b-b443-af8611a1745d","added_by":"auto","created_at":"2024-01-08 17:27:38","extension":"xlsx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":29277,"visible":true,"origin":"","legend":"","description":"","filename":"newdatad1.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-3829515/v1/02013d32ce870cdf70864128.xlsx"}],"financialInterests":"No competing interests reported.","formattedTitle":"Construction of prognosis prediction model and visualization system of acute paraquat poisoning based on improved machine learning model","fulltext":[{"header":"Introduction","content":"\u003cp\u003eAs the lung is the main target organ, paraquat poisoning leads to pulmonary interstitial disease and interstitial pulmonary fibrosis, resulting in patient death. There is no effective treatment for paraquat poisoning, making it a challenging problem in the field of toxicology [\u003cspan additionalcitationids=\"CR2\" citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e]. The majority of paraquat poisoning cases result from oral ingestion, while some cases are caused by skin exposure and inhalation. Once absorbed into the human body, paraquat is rapidly distributed to various organs within approximately 6 hours. Notably, the lungs exhibit the highest concentration of paraquat, ranging from 10 to 90 times higher than other tissues and organs [\u003cspan additionalcitationids=\"CR5 CR6\" citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e]. Due to the continuous occurrence of paraquat poisoning, researchers in various countries have conducted numerous clinical and basic studies. Studies on the mechanism of paraquat poisoning and damage have revealed that oxidative stress, such as the generation of reactive oxygen species (ROS) and other immune stimulatory effects released in large quantities, is associated with paraquat poisoning and damage, leading to tissue damage and intracellular calcium overload [\u003cspan additionalcitationids=\"CR9\" citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e]. Many researchers have studied the early lesions of paraquat poisoning and have determined that early diagnosis and treatment are key factors in saving patients with paraquat poisoning [\u003cspan additionalcitationids=\"CR12\" citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e]. The field of medicine has witnessed the emergence of machine learning, an artificial intelligence algorithm that has gained prominence in recent years. This algorithm exhibits continuous organization, adaptation, and learning capabilities during training, making it one of the most extensively employed neural network algorithms. In the field of medicine, machine learning techniques can be effectively employed for multivariate regression modeling, discerning intricate non-linear classifications, and various other applications[\u003cspan additionalcitationids=\"CR15\" citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e]. Machine learning has been employed for the early detection of tumor diseases, regression prediction in disease treatment, and exploration of novel compounds in research and drug development [\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e]. The objective of this study is to investigate the development of a prognosis prediction model and visualization system for acute paraquat poisoning based on an enhanced machine learning approach, aiming to facilitate clinical diagnosis and prognostic assessment of acute paraquat poisoning.\u003c/p\u003e"},{"header":"1 Data and Methods","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e\n \u003ch2\u003e1.1 General Information\u003c/h2\u003e\n \u003cp\u003eThis study was a retrospective study. A total of 101 patients with acute paraquat poisoning were selected from 6 hospitals between March 2020 and March 2022, and they were categorized into the survival group (n\u0026thinsp;=\u0026thinsp;37) and death group (n\u0026thinsp;=\u0026thinsp;64) based on treatment outcomes. There were no significant differences in gender, age, body mass index, receive pre-hospital care, time from poisoning to treatment between the two groups (P\u0026thinsp;\u0026gt;\u0026thinsp;0.05). The duration of treatment in the death group was significantly shorter than that in the survival group (P\u0026thinsp;\u0026lt;\u0026thinsp;0.05); The death time of the death group was 2\u0026ndash;24 hours, with an average of (11.33\u0026thinsp;\u0026plusmn;\u0026thinsp;6.41)h,as presented in Table \u003cspan class=\"InternalRef\"\u003e1\u003c/span\u003e. Prior to implementation, the study was approved by the Ethics committee of the 6 hospitals[Ethics committee of the 945th Hospital of the Joint Logistics Support Force of the Chinese People\u0026apos;s Liberation Army(Ethical Application Ref: 202200015);Ethics committee of Mingshan District People\u0026apos;s Hospital of Ya \u0026apos;an(Ethics Review 2022 No. 18);Medical Ethics Committee of Ya\u0026apos;an Polytechnic College Affiliated Hospital(Ethics Review 2022 No. 023);Ethics committee of Yucheng District People\u0026apos;s Hospital of Ya \u0026apos;an(No. 202204032);Ethical review opinions of Ya \u0026apos;an People\u0026apos;s Hospital(No. 2022-0014);Ethics committee of Ya \u0026apos;an Traditional Chinese Medicine Hospital(2022 No. 021)]. This study was a retrospective analysis, and informed consent of patients could be waived(Ethics committee of the 945th Hospital of the Joint Logistics Support Force of the Chinese People\u0026apos;s Liberation Army granted the waiver of patient informed consent), and this study was in accordance with the requirements and regulations of the World Medical Declaration of Helsinki.\u003c/p\u003e\n\u003ctable id=\"Tab1\" border=\"1\"\u003e\n \u003ccaption language=\"En\"\u003e\n \u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e\n \u003cdiv class=\"CaptionContent\"\u003e\n \u003cp\u003eComparison of general data between the two groups\u003c/p\u003e\n \u003c/div\u003e\n \u003c/caption\u003e\n \u003ccolgroup cols=\"5\"\u003e\u003c/colgroup\u003e\n \u003cthead\u003e\n \u003ctr\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eIndex\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eSurviva groups(\u003cem\u003en\u003c/em\u003e\u0026thinsp;=\u0026thinsp;37)\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eDeath groups(\u003cem\u003en\u003c/em\u003e\u0026thinsp;=\u0026thinsp;64)\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003e\u003cem\u003et/\u0026chi;\u003c/em\u003e\u003csup\u003e\u003cem\u003e2\u003c/em\u003e\u003c/sup\u003e\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003e\u003cem\u003ep\u003c/em\u003e\u003c/p\u003e\n \u003c/th\u003e\n \u003c/tr\u003e\n \u003c/thead\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eAge (year)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e31.30\u0026thinsp;\u0026plusmn;\u0026thinsp;9.06\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e32.17\u0026thinsp;\u0026plusmn;\u0026thinsp;12.03\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e-0.384\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e0.702\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eGender\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e0.188\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e0.665\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMale\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e19(51.35)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e30(46.88)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eFemale\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e18(48.65)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e34(53.12)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eBody mass index(kg/m\u003csup\u003e2\u003c/sup\u003e)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e19.74\u0026thinsp;\u0026plusmn;\u0026thinsp;2.12\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e20.60\u0026thinsp;\u0026plusmn;\u0026thinsp;3.55\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e-1.330\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e0.187\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eReceive pre-hospital care\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e9(24.32)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e28(43.75)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e0.221\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e0.638\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eTime from poisoning to start of treatment(min)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e42.49\u0026thinsp;\u0026plusmn;\u0026thinsp;26.07\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e50.31\u0026thinsp;\u0026plusmn;\u0026thinsp;23.62\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e-1.544\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e0.126\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eDuration of treatment(h)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e22.16\u0026thinsp;\u0026plusmn;\u0026thinsp;19.50\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e11.33\u0026thinsp;\u0026plusmn;\u0026thinsp;6.41\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e4.090\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n \u003c/table\u003e\n \u003c/div\u003e\u003cbr\u003e\n\u003c/div\u003e\n\u003cdiv id=\"Sec4\" class=\"Section2\"\u003e\n \u003ch2\u003e1.2 Inclusion and exclusion criteria\u003c/h2\u003e\n \u003cp\u003eInclusion criteria: ① All patients fulfilled the diagnostic criteria for \u0026lt;\u0026thinsp;Paraquat poisonings, encompassing mechanisms of pulmonary toxicity, clinical manifestations, and therapeutic interventions\u0026gt;[\u003cspan class=\"CitationRef\"\u003e19\u003c/span\u003e]; ② No patients with congenital immune dysfunction were included.\u003c/p\u003e\n \u003cp\u003eExclusion criteria: ① Patients with excretory organ disorders; ② Combined with other poisoning patients; ③ The poisoning time has exceeded 24 hours.\u003c/p\u003e\n\u003c/div\u003e\n\u003cdiv id=\"Sec5\" class=\"Section2\"\u003e\n \u003ch2\u003e1.3 Methods\u003c/h2\u003e\n \u003cp\u003eAll patients underwent gastric lavage using a sodium bicarbonate solution (Sinopod Rongsheng Pharmaceutical Co., LTD., Sinopod Approval number H20013007, specifications: 250 mL), followed by oral administration of 120\u0026ndash;200 mL of 15% white clay and 50 mL of mannitol\u0026thinsp;+\u0026thinsp;6 g rhubarb powder /50 g manganese to induce diarrhea. Additionally, hemoplavage and hemodialysis were performed. Immunosuppressants including cyclophosphamide (Zhejiang Hisun Pharmaceutical Co., LTD., Sinophora H20084627, specification: 50 mg) and Eugene (Tianjin Tianyu Pharmaceutical Co., LTD., Sinophora H20020224, specification: 4 mg) were administered via injection.\u003c/p\u003e\n \u003cp\u003eThe data on ALT, blood creatinine, WBC, neutrophil count, blood urea nitrogen, and prothrombin time were collected within 24 hours of admission for patients with paraquat poisoning. The detection methods for each index are as follows: ALT levels were determined using an automatic clinical biochemical analyzer after extracting 2\u0026ndash;3 mL of venous blood from the body surface and centrifuging it to obtain serum supernatant. Serum creatinine and blood urea nitrogen concentrations were measured using a Pran blood gas analyzer after extracting 1\u0026ndash;2 mL of venous blood from the body surface and adding it to routine EDTA anticoagulant test tubes or heparinized test tubes. Prothrombin time was determined using a blood coagulator method. WBC and neutrophils were detected using a TEK8520 automatic five-classification blood cell analyzer.\u003c/p\u003e\n \u003cp\u003eSynchronous optimization: Leveraging the robust global optimization capability of swarm intelligence algorithms, this study synchronizes the steps of feature screening and hyperparameter optimization in machine learning models. The Harris Hawks Optimization (HHO) algorithm is chosen for its strong global search ability and minimal parameter adjustments required. Building upon the basic algorithm, Tent Chaotic initialization is introduced to evenly distribute the initial population of Harris hawks across the search space. Additionally, a lens imaging reverse learning strategy is incorporated to enhance the algorithm\u0026apos;s capacity for escaping local optima. As shown in Fig. 1. The selection of the XGBoost algorithm was based on optimizing the XGBoost model using HHO, and a hybrid HHO-XGBoost model was constructed. This model was compared with traditional XGBoost models, utilizing a total of 101 samples. Among these samples, 80% (n\u0026thinsp;=\u0026thinsp;81) were randomly assigned to the training set, while the remaining 20% (20 cases) formed the test set. To prevent overfitting, a 5-fold cross-validation was performed on the training set.\u003c/p\u003e\n\u003c/div\u003e\n\u003cdiv id=\"Sec6\" class=\"Section2\"\u003e\n \u003ch2\u003e1.4 Statistical Analysis\u003c/h2\u003e\n \u003cp\u003eStatistical analysis was performed using SPSS 26.0 software. Measurement data that followed a normal distribution were denoted as (Mean\u0026thinsp;\u0026plusmn;\u0026thinsp;Standard Deviation) and analyzed using the T-test. Count data were expressed as percentages (%) and analyzed using either the \u0026chi;2 test or Fisher\u0026apos;s exact probability test. A significance level of P\u0026thinsp;\u0026lt;\u0026thinsp;0.05 was considered statistically significant.\u003c/p\u003e\n\u003c/div\u003e"},{"header":"2 Results","content":"\u003cdiv id=\"Sec8\" class=\"Section2\"\u003e\n \u003ch2\u003e2.1 Improved HHO algorithm performance test\u003c/h2\u003e\n \u003cp\u003eThe performance of the improved HHO algorithm was evaluated using a set of 23 standard test functions. Comparative analysis was conducted with other swarm intelligence optimization algorithms, including genetic algorithm (GA), particle swarm optimization (PSO), multiverse optimization algorithm (MVO), and Sparrow optimization algorithm (SSA). The results demonstrate significant performance advantages of the improved HHO algorithm. As shown in Fig. 2.\u003c/p\u003e\n\u003c/div\u003e\n\u003cdiv id=\"Sec9\" class=\"Section2\"\u003e\n \u003ch2\u003e2.2 Construction of synchronous optimization prediction model\u003c/h2\u003e\n \u003cp\u003eThe ROC-AUC and PR-AUC of the HHO-XGBoost model were 0.9433 and 0.9720 on the training set and 0.9167 and 0.9583 on the test set, respectively, which were significantly higher than those of the other three models. Ultimately, seven characteristics were selected for the HHO-XGBoost model: oral dose, serum creatinine level, ALT level, WBC count, neutrophil count, urea nitrogen level and thrombin time. The training and validation results of the model are presented in Table \u003cspan class=\"InternalRef\"\u003e2\u003c/span\u003e and Table \u003cspan class=\"InternalRef\"\u003e3\u003c/span\u003e respectively; Fig. 3 and Fig. 4 depict these results.\u003c/p\u003e\u0026nbsp;\u003ctable id=\"Tab2\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\n \u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e\n \u003cdiv class=\"CaptionContent\"\u003e\n \u003cp\u003eTraining set\u003c/p\u003e\n \u003c/div\u003e\n \u003c/caption\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\"\u003e\n \u003cp\u003eModel\u003c/p\u003e\n \u003c/th\u003e\u003cth align=\"left\"\u003e\n \u003cp\u003ePRE\u003c/p\u003e\n \u003c/th\u003e\u003cth align=\"left\"\u003e\n \u003cp\u003eSEN\u003c/p\u003e\n \u003c/th\u003e\u003cth align=\"left\"\u003e\n \u003cp\u003eSPE\u003c/p\u003e\n \u003c/th\u003e\u003cth align=\"left\"\u003e\n \u003cp\u003eACC\u003c/p\u003e\n \u003c/th\u003e\u003cth align=\"left\"\u003e\n \u003cp\u003eF1\u003c/p\u003e\n \u003c/th\u003e\u003cth align=\"left\"\u003e\n \u003cp\u003eROC-AUC\u003c/p\u003e\n \u003c/th\u003e\u003cth align=\"left\"\u003e\n \u003cp\u003ePR-AUC\u003c/p\u003e\n \u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\"\u003e\n \u003cp\u003eLR\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.8400\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.8077\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.7241\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.7778\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.8235\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.8541\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.9127\u003c/p\u003e\n \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\"\u003e\n \u003cp\u003eSVM\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.8035\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.8654\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.6207\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.7778\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.8333\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.9055\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.9492\u003c/p\u003e\n \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\"\u003e\n \u003cp\u003eXGBoost\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.8246\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.9039\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.6552\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.8148\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.8624\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.9237\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.9590\u003c/p\u003e\n \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\"\u003e\n \u003cp\u003eHHO-XGBoost\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.9575\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.8654\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.9310\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.8889\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.9091\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.9433\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.9720\u003c/p\u003e\n \u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/table\u003e\n \u003cdiv class=\"gridtable\"\u003e\n \u003cdiv align=\"char\" class=\"colspec\"\u003e\u003cbr\u003e\u003c/div\u003e\u0026nbsp;\u003ctable id=\"Tab3\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\n \u003cdiv class=\"CaptionNumber\"\u003eTable 3\u003c/div\u003e\n \u003cdiv class=\"CaptionContent\"\u003e\n \u003cp\u003eTest set\u003c/p\u003e\n \u003c/div\u003e\n \u003c/caption\u003e\u003ccolgroup cols=\"8\"\u003e\u003c/colgroup\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\"\u003e\n \u003cp\u003eModel\u003c/p\u003e\n \u003c/th\u003e\u003cth align=\"left\"\u003e\n \u003cp\u003ePRE\u003c/p\u003e\n \u003c/th\u003e\u003cth align=\"left\"\u003e\n \u003cp\u003eSEN\u003c/p\u003e\n \u003c/th\u003e\u003cth align=\"left\"\u003e\n \u003cp\u003eSPE\u003c/p\u003e\n \u003c/th\u003e\u003cth align=\"left\"\u003e\n \u003cp\u003eACC\u003c/p\u003e\n \u003c/th\u003e\u003cth align=\"left\"\u003e\n \u003cp\u003eF1\u003c/p\u003e\n \u003c/th\u003e\u003cth align=\"left\"\u003e\n \u003cp\u003eROC-AUC\u003c/p\u003e\n \u003c/th\u003e\u003cth align=\"left\"\u003e\n \u003cp\u003ePR-AUC\u003c/p\u003e\n \u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\"\u003e\n \u003cp\u003eLR\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.6667\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.8333\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.3750\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.6500\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.7407\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.6042\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.7896\u003c/p\u003e\n \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\"\u003e\n \u003cp\u003eSVM\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.6667\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.6667\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.5000\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.6000\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.6667\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.6563\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.8363\u003c/p\u003e\n \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\"\u003e\n \u003cp\u003eXGBoost\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.8000\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.6667\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.7500\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.7000\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.7273\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.7500\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.8257\u003c/p\u003e\n \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\"\u003e\n \u003cp\u003eHHO-XGBoost\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e1.0000\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.6667\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e1.0000\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.8000\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.8000\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.9167\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.9583\u003c/p\u003e\n \u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/table\u003e\n \u003c/div\u003e\n \u003cp\u003e\u003cbr\u003e\u003c/p\u003e\n\u003c/div\u003e\n\u003cdiv id=\"Sec10\" class=\"Section2\"\u003e\n \u003ch2\u003e2.3 Verification of the effect of screening characteristics on acute paraquat death\u003c/h2\u003e\n \u003cdiv id=\"Sec11\" class=\"Section3\"\u003e\n \u003ch2\u003e2.3.1 Single factor analysis\u003c/h2\u003e\n \u003cp\u003eThe Ho-xgboost screening of 7 features revealed statistically significant differences between the survival and death groups (P \u0026lt; 0.05), indicating the critical significance of the variables selected by HHO-XGBoost, as presented in Table\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e4\u003c/span\u003e.\u003c/p\u003e\n \u003cdiv class=\"gridtable\"\u003e\u0026nbsp;\u003ctable id=\"Tab4\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\n \u003cdiv class=\"CaptionNumber\"\u003eTable 4\u003c/div\u003e\n \u003cdiv class=\"CaptionContent\"\u003e\n \u003cp\u003eUnivariate analysis of survival group and death group\u003c/p\u003e\n \u003c/div\u003e\n \u003c/caption\u003e\u003ccolgroup cols=\"5\"\u003e\u003c/colgroup\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\"\u003e\n \u003cp\u003eIndex\u003c/p\u003e\n \u003c/th\u003e\u003cth align=\"left\"\u003e\n \u003cp\u003eSurviva groups(\u003cem\u003en\u003c/em\u003e = 37)\u003c/p\u003e\n \u003c/th\u003e\u003cth align=\"left\"\u003e\n \u003cp\u003eDeath groups(\u003cem\u003en\u003c/em\u003e = 64)\u003c/p\u003e\n \u003c/th\u003e\u003cth align=\"left\"\u003e\n \u003cp\u003e\u003cem\u003et\u003c/em\u003e\u003c/p\u003e\n \u003c/th\u003e\u003cth align=\"left\"\u003e\n \u003cp\u003e\u003cem\u003ep\u003c/em\u003e\u003c/p\u003e\n \u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\"\u003e\n \u003cp\u003eOral dose(ML)\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e25.08 ± 13.41\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e73.31 ± 17.30\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e-14.603\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e\u0026lt; 0.001\u003c/p\u003e\n \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\"\u003e\n \u003cp\u003eSerum creatinine(µmol/L)\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e79.97 ± 32.16\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e192.36 ± 94.71\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e-8.668\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e\u0026lt; 0.001\u003c/p\u003e\n \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\"\u003e\n \u003cp\u003eUrea nitrogen(mmol/L)\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e4.27 ± 1.90\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e8.20 ± 3.39\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e-7.483\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e\u0026lt; 0.001\u003c/p\u003e\n \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\"\u003e\n \u003cp\u003eALT(U/L)\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e15.35 ± 5.43\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e26.27 ± 11.85\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e-6.312\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e\u0026lt; 0.001\u003c/p\u003e\n \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\"\u003e\n \u003cp\u003eWBC(10\u003csup\u003e9\u003c/sup\u003e/L)\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e11.55 ± 4.40\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e21.83 ± 10.62\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e-6.802\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e\u0026lt; 0.001\u003c/p\u003e\n \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\"\u003e\n \u003cp\u003eNeutrophil count(10\u003csup\u003e9\u003c/sup\u003e/L)\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e8.92 ± 2.61\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e18.94 ± 7.00\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e-10.275\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e\u0026lt; 0.001\u003c/p\u003e\n \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\"\u003e\n \u003cp\u003eThrombin time(s)\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e16.73 ± 2.57\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e19.25 ± 2.29\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e-5.098\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e\u0026lt; 0.001\u003c/p\u003e\n \u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/table\u003e\n \u003c/div\u003e\n \u003cp\u003e\u003cbr\u003e\u003c/p\u003e\n \u003c/div\u003e\n\u003c/div\u003e\n\u003cdiv id=\"Sec12\" class=\"Section2\"\u003e\n \u003ch2\u003e2.3.2 Multifactor analysis\u003c/h2\u003e\n \u003cp\u003eThe multifactor analysis was conducted using stepwise logistic regression, resulting in the inclusion of four significant features in the equation: serum creatinine, oral dose, ALT, and WBC. These variables were identified as critical by HHO-XGBoost screening, as presented in Table \u003cspan class=\"InternalRef\"\u003e5\u003c/span\u003e.\u003c/p\u003e\n \u003cdiv class=\"gridtable\"\u003e\u0026nbsp;\u003ctable id=\"Tab5\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\n \u003cdiv class=\"CaptionNumber\"\u003eTable 5\u003c/div\u003e\n \u003cdiv class=\"CaptionContent\"\u003e\n \u003cp\u003eMultivariate analysis of survival group and death group\u003c/p\u003e\n \u003c/div\u003e\n \u003c/caption\u003e\u003ccolgroup cols=\"8\"\u003e\u003c/colgroup\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\"\u003e\n \u003cp\u003eIndex\u003c/p\u003e\n \u003c/th\u003e\u003cth align=\"left\"\u003e\n \u003cp\u003e\u003cem\u003eβ\u003c/em\u003e\u003c/p\u003e\n \u003c/th\u003e\u003cth align=\"left\"\u003e\n \u003cp\u003e\u003cem\u003eSE\u003c/em\u003e\u003c/p\u003e\n \u003c/th\u003e\u003cth align=\"left\"\u003e\n \u003cp\u003e\u003cem\u003eZ\u003c/em\u003e\u003c/p\u003e\n \u003c/th\u003e\u003cth align=\"left\"\u003e\n \u003cp\u003e\u003cem\u003eWald χ\u003c/em\u003e\u003csup\u003e\u003cem\u003e2\u003c/em\u003e\u003c/sup\u003e\u003c/p\u003e\n \u003c/th\u003e\u003cth align=\"left\"\u003e\n \u003cp\u003e\u003cem\u003eP\u003c/em\u003e\u003c/p\u003e\n \u003c/th\u003e\u003cth align=\"left\"\u003e\n \u003cp\u003e\u003cem\u003eOR\u003c/em\u003e\u003c/p\u003e\n \u003c/th\u003e\u003cth align=\"left\"\u003e\n \u003cp\u003e\u003cem\u003e95% CI\u003c/em\u003e\u003c/p\u003e\n \u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\"\u003e\n \u003cp\u003eSerum creatinine\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.061\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.023\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e2.601\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e6.766\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.009\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e1.063\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e1.015 ~ 1.113\u003c/p\u003e\n \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\"\u003e\n \u003cp\u003eOral dose\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.849\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.356\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e2.385\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e5.689\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.017\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e2.338\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e1.164 ~ 4.699\u003c/p\u003e\n \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\"\u003e\n \u003cp\u003eALT\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.446\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.157\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e2.835\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e8.034\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.005\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e1.563\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e1.148 ~ 2.128\u003c/p\u003e\n \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\"\u003e\n \u003cp\u003eWBC\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.380\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.189\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e2.004\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e4.017\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.045\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e1.462\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e1.008 ~ 2.119\u003c/p\u003e\n \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\"\u003e\n \u003cp\u003eIntercept\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e-25.545\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e8.565\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e-2.982\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e8.895\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.003\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.000\u003c/p\u003e\n \u003c/td\u003e\u003ctd align=\"char\"\u003e\n \u003cp\u003e0.000 ~ 0.000\u003c/p\u003e\n \u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/table\u003e\n \u003c/div\u003e\n \u003cp\u003e\u003cbr\u003e\u003c/p\u003e\n\u003c/div\u003e\n\u003cdiv id=\"Sec13\" class=\"Section2\"\u003e\n \u003ch2\u003e2.4 Visualization system construction\u003c/h2\u003e\n \u003cp\u003eAs shown in Figs. 5 and 6, the visualization system can directly output the risk of patient death after inputting patient-related indicators.\u003c/p\u003e\n\u003c/div\u003e"},{"header":"3 Discussion","content":"\u003cp\u003eThe widespread use of Paraquat worldwide can be attributed to its effective application, affordability, and minimal environmental impact. However, in recent years, the occurrence of paraquat poisoning incidents has significantly impacted individuals' daily lives[\u003cspan class=\"CitationRef\"\u003e20\u003c/span\u003e–\u003cspan class=\"CitationRef\"\u003e22\u003c/span\u003e]. The findings of various studies have demonstrated that patients with paraquat poisoning experience severe damage to their major vital organs, particularly the lungs which can develop pulmonary fibrosis, ultimately resulting in asphyxiation and potential fatality even when conscious. Due to the lack of effective antidotes, the mortality rate associated with paraquat poisoning reaches an alarming 80%, significantly compromising societal safety [\u003cspan class=\"CitationRef\"\u003e23\u003c/span\u003e]. Despite the diligent efforts of numerous researchers in search of efficacious treatments and early diagnostic methods for paraquat poisoning, the current clinical mortality rate remains considerably high. Therefore, the timely evaluation of clinical outcomes and risk assessment for critically ill patients with paraquat poisoning is of utmost importance in facilitating accurate clinical diagnosis and treatment, as well as establishing a strong connection between public medical services and social welfare [\u003cspan class=\"CitationRef\"\u003e24\u003c/span\u003e]. The gold standard for diagnosing clinical acute paraquat poisoning is the identification of paraquat components or metabolites in blood or urine samples[\u003cspan class=\"CitationRef\"\u003e25\u003c/span\u003e]. Several studies have demonstrated that paraquat can be detected in urine within 6 hours of ingestion, and a paraquat concentration exceeding 30 mg/L in the blood is indicative of an unfavorable prognosis[\u003cspan class=\"CitationRef\"\u003e26\u003c/span\u003e]. The qualitative and quantitative analysis of paraquat in blood or urine was not conducted in this study, highlighting the need for future research.\u003c/p\u003e\u003cp\u003eWith the advancement of machine learning and its integration into medical care, recent studies have demonstrated that predictive machine learning models can provide valuable insights for guiding future clinical trials of antidotes and other treatment modalities [\u003cspan class=\"CitationRef\"\u003e27\u003c/span\u003e]. The XGBoost algorithm currently stands as the preeminent open-source tool in clinical applications, renowned for its exceptional computational prowess. XGBoost, a widely adopted open-source tool in clinical applications, exhibits exceptional speed and performance. It efficiently handles millions or even hundreds of millions of data points simultaneously, mitigating the challenges associated with error-prone manual processing, missing data points, and inaccurate analysis outcomes. Moreover, machine learning enables automated processing and analysis of extensive datasets to swiftly uncover patterns and insights, thereby providing precise and valuable support for professional endeavors as well as daily life. Compared to alternative models, the XGBoost model exhibits commonly utilized indicators in clinical practice, while maintaining a low cost and easy accessibility of data for any hospital. The XGBoost model not only enables programmatic analysis of data but also facilitates summarization of analyzed data and obtained results, thereby enhancing analysis efficiency and prediction accuracy [\u003cspan class=\"CitationRef\"\u003e28\u003c/span\u003e–\u003cspan class=\"CitationRef\"\u003e31\u003c/span\u003e].\u003c/p\u003e\u003cp\u003eThe HHO-XGBoost model was employed to screen 7 features in this study, including oral dose, serum creatinine, ALT, white blood cell count, neutrophil count, urea nitrogen, and thrombin time. Additionally, logistic regression multivariate analysis revealed that serum creatinine, oral dosage, ALT, and WBC were all included as screening variables. The prognosis of oral paraquat is closely correlated with the administered oral dosage, thereby accounting for the underlying reasons. The literature suggests that the lethal dose of oral paraquat ranges from 1 to 3 g. When the dosage is below 20 mg/kg, appropriate treatment can usually prevent life-threatening consequences, leading to complete recovery in most patients. For individuals receiving a single oral dose between 20 and 40 mg/kg, mortality occurs within a period of two to three weeks. Those exposed to a single oral dose equal to or exceeding 40 mg/kg succumb within one to four days[\u003cspan class=\"CitationRef\"\u003e32\u003c/span\u003e]. The kidneys exhibit the highest concentration of paraquat during the early stages of poisoning. Paraquat is not reabsorbed in renal tubules but rather excreted from the kidney in its original form with weak binding to plasma proteins. Consequently, serum creatinine serves as a reliable indicator of renal function and exhibits a close association with prognosis among patients suffering from acute paraquat poisoning[\u003cspan class=\"CitationRef\"\u003e33\u003c/span\u003e]. The administration of Paraquat may induce activation of the sympathetic-adrenal medulla axis, leading to a redistribution of renal blood flow from the cortex to predominantly supply the medulla, thereby resulting in an elevation in serum creatinine levels [\u003cspan class=\"CitationRef\"\u003e34\u003c/span\u003e]. By inducing proximal renal tubule destruction, paraquat disrupts the mitochondrial transmission chain and instigates the generation of reactive oxygen species. The subsequent production of a substantial amount of reactive oxygen species indirectly triggers sulfhydryl compound formation within the body, thereby accelerating lipid cell damage and peroxidation while elevating ALT levels. Studies have revealed a close association between paraquat poisoning and alterations in inflammatory cytokines. The elevation in toxin concentration is correlated with an increase in inflammatory cytokines, and as time progresses, the levels of inflammatory cells consistently rise, demonstrating dynamic changes throughout the entire experiment [\u003cspan class=\"CitationRef\"\u003e34\u003c/span\u003e]. The primary molecular mechanism underlying paraquat toxicity involves disruption of the body's REDOX system and induction of intracellular oxidative stress. Paraquat-induced alterations in cytokines, particularly inflammatory factors, play a pivotal role in the development of acute lung injury and subsequent pulmonary fibrosis resulting from paraquat poisoning. Therefore, the level of white blood cells is closely associated with the prognosis of patients suffering from paraquat poisoning [\u003cspan class=\"CitationRef\"\u003e35\u003c/span\u003e].\u003c/p\u003e"},{"header":"4 Conclusion","content":"\u003cp\u003eIn the context of acute paraquat poisoning, the HHO-XGBoost model based on machine learning holds significant implications for developing prognosis prediction models and visualization systems, which can provide important help for clinical prognosis prediction of patients with paraquat poisoning. The relevant detection indicators of patients within 24 hours can be inputted into the visualization system, enabling risk assessment for mortality and providing valuable assistance to clinicians in guiding subsequent treatment. The present study, however, has certain limitations with regards to the representativeness of the sample due to its retrospective design. The limited sample size of this study, however, poses challenges in accurately representing the entire target group. Additionally, the prognosis of patients with paraquat poisoning may be influenced by other factors not accounted for in the observational indicators utilized in this study, potentially impacting the interpretation and inference of the findings. To address these limitations, future investigations can adopt the following measures to enhance the experimental design. Firstly, we recommend adopting a more comprehensive approach in the selection of samples, and considering an increase in sample size to enhance the representativeness and generalizability of the findings. Furthermore, future research endeavors should encompass a broader range of indicators and variables in order to attain a comprehensive understanding of the research topic. The utilization of this extension can yield more precise outcomes and facilitate in-depth deductions. Finally, prospective studies are implemented to enhance control over variables, improve the management of observed outcome dynamics, and strengthen causal inference.\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003e\u0026nbsp;Ethics approval:\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe study was approved by the Ethics committee of the 6 hospitals[Ethics committee of the 945th Hospital of the Joint Logistics Support Force of the Chinese People\u0026apos;s Liberation Army(Ethical Application Ref: 202200015);Ethics committee of Mingshan District People\u0026apos;s Hospital of Ya \u0026apos;an(Ethics Review 2022 No. 18);Medical Ethics Committee of Ya\u0026apos;an Polytechnic College Affiliated Hospital(Ethics Review 2022 No. 023);Ethics committee of Yucheng District People\u0026apos;s Hospital of Ya \u0026apos;an(No. 202204032);Ethical review opinions of Ya \u0026apos;an People\u0026apos;s Hospital(No. 2022-0014);Ethics committee of Ya \u0026apos;an Traditional Chinese Medicine Hospital(2022 No. 021)].\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConsent for publication:\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis study was a retrospective analysis, and informed consent of patients could be waived. The study was approved by the ethics committee\u0026nbsp;of the 6 hospitals.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAvailability of data and materials:\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eAll data generated or analysed during this study are included in this published article [and its supplementary information files].\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\u003eThere was no funding support for this research.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAuthors\u0026apos; contributions:\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eMZ:Formulation of overarching research goals and aims;Oversight and leadership responsibility for the research activity planning and execution, including mentorship external to the core team.\u003c/p\u003e\n\u003cp\u003eXH:Management and coordination responsibility for the research activity planning and execution.\u003c/p\u003e\n\u003cp\u003eZZ、TH、PW、YX、LZ、ZL、ZX、HL、XY、PH:Conducting a research and investigation process, specifically data collection.\u003c/p\u003e\n\u003cp\u003eLL:Writing the initial draft (including substantive translation);Programming; software development; designing computer programs; implementation of the computer code and supporting algorithms; testing of existing code components; Application of statistical, mathematical, computational to analyze data.\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;All authors read and approved the final manuscript.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAcknowledgements:\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNot applicable.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eChen F, Ye Y, Jin B, Yi B, Wei Q, Liao L. Homicidal Paraquat Poisoning. J Forensic Sci. 2019;64(3):941\u0026ndash;945. doi: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1111/1556-4029.13945\u003c/span\u003e\u003cspan address=\"10.1111/1556-4029.13945\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKakkar A, Jandial A, Suri V. Atrocious tetrad in paraquat poisoning. QJM. 2022;115(5):310\u0026ndash;311. doi: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1093/qjmed/hcac077\u003c/span\u003e\u003cspan address=\"10.1093/qjmed/hcac077\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRuwanpura R, Nandasiri C. Homicidal Paraquat Poisoning Following Ligature Strangulation. Acad Forensic Pathol. 2019;9(3\u0026ndash;4):212\u0026ndash;216. doi: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1177/1925362119891704\u003c/span\u003e\u003cspan address=\"10.1177/1925362119891704\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSukumar CA, Shanbhag V, Shastry AB. Paraquat: The Poison Potion. Indian J Crit Care Med. 2019;23(Suppl 4):S263-S266. doi: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.5005/jp-journals-10071-23306\u003c/span\u003e\u003cspan address=\"10.5005/jp-journals-10071-23306\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eTrakulsrichai S, Paisanrodjanarat B, Sriapha C, Tongpoo A, Udomsubpayakul U, Wananukul W. Clinical outcome of paraquat poisoning during pregnancy. Clin Toxicol (Phila). 2019;57(8):712\u0026ndash;717. doi: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1080/15563650.2018.1549328\u003c/span\u003e\u003cspan address=\"10.1080/15563650.2018.1549328\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhang S, Song S, Luo X, Liu J, Liu M, Li W, Cao T, Li N, Zeng C, Zhang B, Cai H. Prognostic value of liver and kidney function parameters and their correlation with the ratio of urine-to-plasma paraquat in patients with paraquat poisoning. Basic Clin Pharmacol Toxicol. 2021;128(6):822\u0026ndash;830. doi: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1111/bcpt.13555\u003c/span\u003e\u003cspan address=\"10.1111/bcpt.13555\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eEizadi-Mood N, Jaberi D, Barouti Z, Rahimi A, Mansourian M, Dorooshi G, Sabzghabaee AM, Alfred S. The efficacy of hemodialysis on paraquat poisoning mortality: A systematic review and meta-analysis. J Res Med Sci. 2022;27:74. doi: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.4103/jrms.jrms_235_21\u003c/span\u003e\u003cspan address=\"10.4103/jrms.jrms_235_21\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMoar JJ, Hill L. Histopathological Findings in a Fatal Case of Paraquat Poisoning. Am J Forensic Med Pathol. 2022;43(1):69\u0026ndash;72. doi: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1097/PAF.0000000000000698\u003c/span\u003e\u003cspan address=\"10.1097/PAF.0000000000000698\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKumar S, Gupta S, Bansal YS, Bal A, Rastogi P, Muthu V, Arora V. Pulmonary histopathology in fatal paraquat poisoning. Autops Case Rep. 2021;11:e2021342. doi: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.4322/acr.2021.342\u003c/span\u003e\u003cspan address=\"10.4322/acr.2021.342\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eQiu L, Deng Y. Paraquat Poisoning in Children: A 5-Year Review. Pediatr Emerg Care. 2021;37(12):e846-e849. doi: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1097/PEC.0000000000001868\u003c/span\u003e\u003cspan address=\"10.1097/PEC.0000000000001868\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLiu Z, Huang F, Zhao S, Ma L, Shi Q, Zhou Y. Homicidal paraquat poisoning: Poisoned while drinking. J Forensic Sci. 2022;67(3):1312\u0026ndash;1319. doi: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1111/1556-4029.14968.\u003c/span\u003e\u003cspan address=\"10.1111/1556-4029.14968.\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChen CK, Yeh YT, M\u0026eacute;garbane B, Chen YC, Chen KF, Chang CH, Lin CC. A novel flowchart to predict mortality and analyse effectiveness of routinely used pharmacological regimens in paraquat poisoning. Basic Clin Pharmacol Toxicol. 2021;129(6):496\u0026ndash;503. doi: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1111/bcpt.13652\u003c/span\u003e\u003cspan address=\"10.1111/bcpt.13652\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDambal A, Naik S, Hemamalini G, Siddaganga S, Kashinkunti MD. Reasons for under-reporting of paraquat poisoning in India. Natl Med J India. 2021 May-Jun;34(3):138\u0026ndash;142. doi: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.25259/NMJI_383_19.\u003c/span\u003e\u003cspan address=\"10.25259/NMJI_383_19.\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChoi RY, Coyner AS, Kalpathy-Cramer J, Chiang MF, Campbell JP. Introduction to Machine Learning, Neural Networks, and Deep Learning. Transl Vis Sci Technol. 2020;9(2):14. doi: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1167/tvst.9.2.14.\u003c/span\u003e\u003cspan address=\"10.1167/tvst.9.2.14.\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSilva GFS, Fagundes TP, Teixeira BC, Chiavegatto Filho ADP. Machine Learning for Hypertension Prediction: a Systematic Review. Curr Hypertens Rep. 2022;24(11):523\u0026ndash;533. doi: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1007/s11906-022-01212-6\u003c/span\u003e\u003cspan address=\"10.1007/s11906-022-01212-6\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e..\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSultan AS, Elgharib MA, Tavares T, Jessri M, Basile JR. The use of artificial intelligence, machine learning and deep learning in oncologic histopathology. J Oral Pathol Med. 2020;49(9):849\u0026ndash;856. doi: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1111/jop.13042\u003c/span\u003e\u003cspan address=\"10.1111/jop.13042\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePeiffer-Smadja N, Rawson TM, Ahmad R, Buchard A, Georgiou P, Lescure FX, Birgand G, Holmes AH. Machine learning for clinical decision support in infectious diseases: a narrative review of current applications. Clin Microbiol Infect. 2020;26(5):584\u0026ndash;595. doi: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/j.cmi.2019.09.009\u003c/span\u003e\u003cspan address=\"10.1016/j.cmi.2019.09.009\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLo Vercio L, Amador K, Bannister JJ, Crites S, Gutierrez A, MacDonald ME, Moore J, Mouches P, Rajashekar D, Schimert S, Subbanna N, Tuladhar A, Wang N, Wilms M, Winder A, Forkert ND. Supervised machine learning tools: a tutorial for clinicians. J Neural Eng. 2020;17(6). doi: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1088/1741-2552/abbff2\u003c/span\u003e\u003cspan address=\"10.1088/1741-2552/abbff2\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDinis-Oliveira RJ, Duarte JA, S\u0026aacute;nchez-Navarro A, Remi\u0026atilde;o F, Bastos ML, Carvalho F. Paraquat poisonings: mechanisms of lung toxicity, clinical features, and treatment. Crit Rev Toxicol. 2008;38(1):13\u0026ndash;71. doi: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1080/10408440701669959\u003c/span\u003e\u003cspan address=\"10.1080/10408440701669959\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKumar MS, Shekhawat RS, Kanchan T, Midha NK. Diagnostic Dilemma in Fatal Paraquat Poisoning: An Autopsy Case Report. Acad Forensic Pathol. 2023;13(2):80\u0026ndash;85. doi: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1177/19253621231184612\u003c/span\u003e\u003cspan address=\"10.1177/19253621231184612\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhang X, Xu X, Li S, Li L, Zhang J, Wang R. A Synthetic Receptor as a Specific Antidote for Paraquat Poisoning. Theranostics. 2019;9(3):633\u0026ndash;645. doi: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.7150/thno.31485\u003c/span\u003e\u003cspan address=\"10.7150/thno.31485\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChen H, Yang R, Tang Y, Fu X. Effects of curcumin on artery blood gas index of rats with pulmonary fibrosis caused by paraquat poisoning and the expression of Smad 4, Smurf 2, interleukin-4 and interferon-γ. Exp Ther Med. 2019;17(5):3664\u0026ndash;3670. doi: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3892/etm.2019.7341\u003c/span\u003e\u003cspan address=\"10.3892/etm.2019.7341\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eJames N, Bakshi R, Rudresh SS, Kaushik K, Ghumaan KS, Pannu AK. Pneumoperitoneum from pneumomediastinum in paraquat poisoning. Trop Doct. 2021;51(2):241\u0026ndash;242. doi: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1177/0049475520960872\u003c/span\u003e\u003cspan address=\"10.1177/0049475520960872\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRavichandran R, Amalnath D, Shaha KK, Srinivas BH. Paraquat Poisoning: A Retrospective Study of 55 Patients From a Tertiary Care Center in Southern India. Indian J Crit Care Med. 2020;24(3):155\u0026ndash;159. doi: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.5005/jp-journals-10071-23369\u003c/span\u003e\u003cspan address=\"10.5005/jp-journals-10071-23369\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eJha M, Gaur N. Paraquat poisoning with spontaneous pneumothorax in the era of online shopping. J Family Med Prim Care. 2022;11(1):357\u0026ndash;359. doi: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.4103/jfmpc.jfmpc_957_21\u003c/span\u003e\u003cspan address=\"10.4103/jfmpc.jfmpc_957_21\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSharma DS, Prajapati AM, Shah DM. Review of a Case of Paraquat Poisoning in a Tertiary Care Rural-based ICU. Indian J Crit Care Med. 2019;23(6):284\u0026ndash;286. doi: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.5005/jp-journals-10071-23182\u003c/span\u003e\u003cspan address=\"10.5005/jp-journals-10071-23182\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKim SS, Hwang KS, Kan H, Yang JY, Son Y, Shin DS, Lee BH, Chae CH, Bae MA. Neurotoxicological Profiling of Paraquat in Zebrafish Model. Neurochem Res. 2022;47(8):2294\u0026ndash;2306. doi: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1007/s11064-022-03615-y\u003c/span\u003e\u003cspan address=\"10.1007/s11064-022-03615-y\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChen H, Hu L, Li H, Hong G, Zhang T, Ma J, Lu Z. An Effective Machine Learning Approach for Prognosis of Paraquat Poisoning Patients Using Blood Routine Indexes. Basic Clin Pharmacol Toxicol. 2017;120(1):86\u0026ndash;96. doi: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1111/bcpt.12638\u003c/span\u003e\u003cspan address=\"10.1111/bcpt.12638\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHu L, Li H, Cai Z, Lin F, Hong G, Chen H, Lu Z. A new machine-learning method to prognosticate paraquat poisoned patients by combining coagulation, liver, and kidney indices. PLoS One. 2017;12(10):e0186427. doi: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1371/journal.pone.0186427\u003c/span\u003e\u003cspan address=\"10.1371/journal.pone.0186427\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWen C, Lin F, Huang B, Zhang Z, Wang X, Ma J, Lin G, Chen H, Hu L. Metabolomics Analysis in Acute Paraquat Poisoning Patients Based on UPLC-Q-TOF-MS and Machine Learning Approach. Chem Res Toxicol. 2019;32(4):629\u0026ndash;637. doi: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1021/acs.chemrestox.8b00328\u003c/span\u003e\u003cspan address=\"10.1021/acs.chemrestox.8b00328\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHu L, Hong G, Ma J, Wang X, Chen H. An efficient machine learning approach for diagnosis of paraquat-poisoned patients. Comput Biol Med. 2015;59:116\u0026ndash;124. doi: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/j.compbiomed.2015.02.003.\u003c/span\u003e\u003cspan address=\"10.1016/j.compbiomed.2015.02.003.\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChen CK, Chen YC, M\u0026eacute;garbane B, Yeh YT, Chaou CH, Chang CH, Lin CC. The acute paraquat poisoning mortality (APPM) score to predict the risk of death in paraquat-poisoned patients. Clin Toxicol (Phila). 2022;60(4):446\u0026ndash;450. doi: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1080/15563650.2021.1979234\u003c/span\u003e\u003cspan address=\"10.1080/15563650.2021.1979234\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePanda PK, Manna S, Bhasi A, Singh SS, Maneesh VS. Paraquat poisoning in Andaman and Nicobar Islands - Government must intervene. J Family Med Prim Care. 2021;10(4):1780\u0026ndash;1784. doi: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.4103/jfmpc.jfmpc_2020_20.\u003c/span\u003e\u003cspan address=\"10.4103/jfmpc.jfmpc_2020_20.\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAhmad J, D'Angelo K, Rivas M, Mahal M, Nookala V, Kulakauskiene D, Makaryus AN. Dilated Cardiomyopathy Associated with Paraquat Herbicide Poisoning. Clin Pract. 2021;11(3):679\u0026ndash;686. doi: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3390/clinpract11030083.\u003c/span\u003e\u003cspan address=\"10.3390/clinpract11030083.\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLv B, Han DF, Chen J, Zhao HB, Liu XL. Can kissing cause paraquat poisoning: A case report and review of literature. World J Clin Cases. 2021;9(20):5588\u0026ndash;5593. doi: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.12998/wjcc.v9.i20.5588\u003c/span\u003e\u003cspan address=\"10.12998/wjcc.v9.i20.5588\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"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":"Machine learning model, Acute paraquat poisoning, Prediction model, Visualization system construction","lastPublishedDoi":"10.21203/rs.3.rs-3829515/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3829515/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e\u003cstrong\u003eObjective:\u003c/strong\u003e This study aims to develop a prognosis prediction model and visualization system for acute paraquat poisoning based on an improved machine learning model.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eMethods:\u003c/strong\u003e A total of 101 patients with acute paraquat poisoning admitted to 6 hospitals from March 2020 to March 2022 were selected for this study. The patients were divided into two groups, the survival group (n=37) and the death group (n=64), based on treatment results. The biochemical indexes of the patients were analyzed, and a prognosis prediction model for acute paraquat poisoning was constructed using HHO-XGBoost, an improved machine learning algorithm. Multivariate logistic analysis was used to verify the value of the self-screening features in the model.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eResults:\u003c/strong\u003e Seven features were selected in the HHO-XGBoost model, including oral dose, serum creatinine, alanine aminotransferase (ALT), white blood cell (WBC) count, neutrophil count, urea nitrogen level, and thrombin time. Univariate analysis showed statistically significant differences between the survival group and death group for these features (P\u0026lt;0.05). Multivariate logistic analysis identified four features that were significantly associated with prognosis-serum creatinine level, oral dose, ALT level, and WBC count - indicating their critical significance in predicting outcomes.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConclusion:\u003c/strong\u003e The HHO-XGBoost model based on machine learning is highly valuable in constructing a prognosis prediction model and visualization system for acute paraquat poisoning, which can provide important help for clinical prognosis prediction of patients with paraquat poisoning.\u003c/p\u003e","manuscriptTitle":"Construction of prognosis prediction model and visualization system of acute paraquat poisoning based on improved machine learning model","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-01-08 17:19:33","doi":"10.21203/rs.3.rs-3829515/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":"8c0e11b5-2c88-48b5-adda-30c555f4e62c","owner":[],"postedDate":"January 8th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":27986239,"name":"Biological sciences/Biological techniques"},{"id":27986240,"name":"Biological sciences/Biophysics"},{"id":27986241,"name":"Biological sciences/Biotechnology"},{"id":27986242,"name":"Biological sciences/Evolution"}],"tags":[],"updatedAt":"2024-02-23T11:22:46+00:00","versionOfRecord":[],"versionCreatedAt":"2024-01-08 17:19:33","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-3829515","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3829515","identity":"rs-3829515","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}