Analysis of Frailty in Peritoneal Dialysis Patients Based on Logistic Regression Model and XGBoost Model

Analysis of Frailty in Peritoneal Dialysis Patients Based on Logistic Regression Model and XGBoost Model | medRxiv /* */ /* */ <!-- <!-- /*! * yepnope1.5.4 * (c) WTFPL, GPLv2 */ (function(a,b,c){function d(a){return"[object Function]"==o.call(a)}function e(a){return"string"==typeof a}function f(){}function g(a){return!a||"loaded"==a||"complete"==a||"uninitialized"==a}function h(){var a=p.shift();q=1,a?a.t?m(function(){("c"==a.t?B.injectCss:B.injectJs)(a.s,0,a.a,a.x,a.e,1)},0):(a(),h()):q=0}function i(a,c,d,e,f,i,j){function k(b){if(!o&&g(l.readyState)&&(u.r=o=1,!q&&h(),l.onload=l.onreadystatechange=null,b)){"img"!=a&&m(function(){t.removeChild(l)},50);for(var d in y[c])y[c].hasOwnProperty(d)&&y[c][d].onload()}}var j=j||B.errorTimeout,l=b.createElement(a),o=0,r=0,u={t:d,s:c,e:f,a:i,x:j};1===y[c]&&(r=1,y[c]=[]),"object"==a?l.data=c:(l.src=c,l.type=a),l.width=l.height="0",l.onerror=l.onload=l.onreadystatechange=function(){k.call(this,r)},p.splice(e,0,u),"img"!=a&&(r||2===y[c]?(t.insertBefore(l,s?null:n),m(k,j)):y[c].push(l))}function j(a,b,c,d,f){return q=0,b=b||"j",e(a)?i("c"==b?v:u,a,b,this.i++,c,d,f):(p.splice(this.i++,0,a),1==p.length&&h()),this}function k(){var a=B;return a.loader={load:j,i:0},a}var l=b.documentElement,m=a.setTimeout,n=b.getElementsByTagName("script")[0],o={}.toString,p=[],q=0,r="MozAppearance"in l.style,s=r&&!!b.createRange().compareNode,t=s?l:n.parentNode,l=a.opera&&"[object Opera]"==o.call(a.opera),l=!!b.attachEvent&&!l,u=r?"object":l?"script":"img",v=l?"script":u,w=Array.isArray||function(a){return"[object Array]"==o.call(a)},x=[],y={},z={timeout:function(a,b){return b.length&&(a.timeout=b[0]),a}},A,B;B=function(a){function b(a){var a=a.split("!"),b=x.length,c=a.pop(),d=a.length,c={url:c,origUrl:c,prefixes:a},e,f,g;for(f=0;f<d;f++)g=a[f].split("="),(e=z[g.shift()])&&(c=e(c,g));for(f=0;f<b;f++)c=x[f](c);return c}function g(a,e,f,g,h){var i=b(a),j=i.autoCallback;i.url.split(".").pop().split("?").shift(),i.bypass||(e&&(e=d(e)?e:e[a]||e[g]||e[a.split("/").pop().split("?")[0]]),i.instead?i.instead(a,e,f,g,h):(y[i.url]?i.noexec=!0:y[i.url]=1,f.load(i.url,i.forceCSS||!i.forceJS&&"css"==i.url.split(".").pop().split("?").shift()?"c":c,i.noexec,i.attrs,i.timeout),(d(e)||d(j))&&f.load(function(){k(),e&&e(i.origUrl,h,g),j&&j(i.origUrl,h,g),y[i.url]=2})))}function h(a,b){function c(a,c){if(a){if(e(a))c||(j=function(){var a=[].slice.call(arguments);k.apply(this,a),l()}),g(a,j,b,0,h);else if(Object(a)===a)for(n in m=function(){var b=0,c;for(c in a)a.hasOwnProperty(c)&&b++;return b}(),a)a.hasOwnProperty(n)&&(!c&&!--m&&(d(j)?j=function(){var a=[].slice.call(arguments);k.apply(this,a),l()}:j[n]=function(a){return function(){var b=[].slice.call(arguments);a&&a.apply(this,b),l()}}(k[n])),g(a[n],j,b,n,h))}else!c&&l()}var h=!!a.test,i=a.load||a.both,j=a.callback||f,k=j,l=a.complete||f,m,n;c(h?a.yep:a.nope,!!i),i&&c(i)}var i,j,l=this.yepnope.loader;if(e(a))g(a,0,l,0);else if(w(a))for(i=0;i (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];var j=d.createElement(s);var dl=l!='dataLayer'?'&l='+l:'';j.src='//www.googletagmanager.com/gtm.js?id='+i+dl;j.type='text/javascript';j.async=true;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-P4HH5NV'); Skip to main content Home About Submit ALERTS / RSS Search for this keyword Advanced Search Analysis of Frailty in Peritoneal Dialysis Patients Based on Logistic Regression Model and XGBoost Model Qi Liu , View ORCID Profile Guanchao Tong , Qiong Ye doi: https://doi.org/10.1101/2024.07.29.24311190 Qi Liu a Wenzhou Central Hospital , 252 Baili East Rd, Lucheng, Wenzhou, Zhejiang Province 325000, China Find this author on Google Scholar Find this author on PubMed Search for this author on this site Guanchao Tong b Wenzhou-Kean University , 88 Daxue Rd, Ouhai, Wenzhou, Zhejiang Province 325060, China c Kean University , 1000 Morris Avenue, Union, New Jersey 07083, USA Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Guanchao Tong Qiong Ye b Wenzhou-Kean University , 88 Daxue Rd, Ouhai, Wenzhou, Zhejiang Province 325060, China Find this author on Google Scholar Find this author on PubMed Search for this author on this site For correspondence: yeqiong{at}wku.edu.cn Abstract Full Text Info/History Metrics Data/Code Preview PDF ABSTRACT Purpose The aim of this study was to establish a model that would enable healthcare providers to use routine follow-up measures of peritoneal dialysis to predict frailty in those patients. Design A cross-sectional design with Logistic regression and XGBoost machine learning algorithms analysis. Methods One hundred and twenty-three cases of peritoneal dialysis patients who underwent regular follow-up at our center were included in this study. We use the FRAIL scale to confirm the frailty of the patients. Clinical and Laboratory data were obtained from the peritoneal dialysis registration system. Factors associated with patient Frailty were identified through regularized logistic regression and validated using an XGBoost model. The final selected variables were in-cluded in the unregularized Logistic Regression to construct the model Findings A total of 123 patients were reviewed in this study, with an average age of 61.58 years, and the median dialysis Duration was 38.5(18.07,60.53) months. 39 patients (31.71%) were female, 54 PD patients (43.9%) were classified as frail. Age, Ferritin, and TCH are the top three im-portant features labeled by the XGBoost. The results are consistent with the regularized logistic regression. Conclusions In this study, age, total cholesterol, and ferritin are the most important features associated with the frailty in peritoneal dialysis patients. This model can be used to predict frailty status and help health monitoring of peritoneal dialysis patients. Clinical Evidence Logistic regression and XGBoost machine learning algorithms can be used to construct a predictive model of frailty in peritoneal dialysis patients. The model could provide doctors with an objective tool to find frailty in peritoneal dialysis patients. As the data is obtained from routine examinations, the prediction model will not bring additional burden to the work of doctors or nurses. INTRODUCTION Peritoneal dialysis can bring many benefits to patients with end-stage renal disease and prolongs their lives. However, it also has disadvantages, such as infections, metabolic and mechanical complications, risk of inadequate dialysis or limited possibilities to increase adequacy, malnutrition, long-term viability, psychological problems related to indwelling abdominal dialysis catheters, and fatigue from continuous use, particularly among elderly people[ 1 ]. Frailty is a commonly used term to denote a multidimensional syndrome of loss of reserves (energy, physical ability, cognition, health), which gives rise to vulnerability[ 2 ]. Frailty is highly prevalent in older patients with dialysis-dependent kidney failure[ 3 ]. The causes of frailty in PD patients are a little more complex. The buildup of toxins in uremia can cause loss of appetite and fatigue. Among those undergoing dialysis, particularly peritoneal dialysis (PD), challenges such as abdominal distention and bloating can exacerbate the loss of appetite. This diminished appetite, combined with dietary restrictions and reduced physical activity, leads to protein-energy wasting, muscle breakdown, and the onset of sarcopenia[ 6 ], [ 7 ]. Elevated levels of uremic toxins in circulation and disruptions in acid-base balance contribute to chronic inflammation and hinder the effectiveness of anabolic hormones, ultimately resulting in catabolism and impaired energy utilization[ 6 ]. Moreover, dialysis removes uremic toxins and restores homeostasis, thus theoretically improving weakness[ 7 ]. The interaction between malnutrition, inflammation, and frailty often coexist and have a combined effect on patient outcomes[ 8 ]. In patients with chronic kidney disease, both before or after dialysis initiation, frailty has been linked with increased risks of falls, hospitalization, cognitive dysfunction, and mortality[ 7 ], [ 9 ]. Early identification may enable timely intervention to prevent adverse health outcomes in this group of patients. A significant amount of research has employed statistical learning and machine learning algorithms to address medical problems and identify relationships between various factors through patient observation and indicators of different diseases[ 10 ]. Machine learning can process large data sets and then efficiently process this data into clinical knowledge that enables physicians to prepare and deliver treatments, ultimately improving outcomes[ 11 ]. Based on clinical data, machine learning models can diagnose aphasia, and urinary tract infections, and predict breast cancer, among others, providing clinicians with a “second opinion”. This study aims to analyze the relationship between frailty and various indicators (especially nutritional related) through the observation of patients with regular peritoneal dialysis follow-up in our center by using logistic regression and extreme Gradient Boost (XGBoost) algorithms and try to find out the important factors of frailty in patients with peritoneal dialysis, to intervene in the early stage and improve the quality of life of patients. MATERIALS AND METHODS Participants A total of 123 patients with peritoneal dialysis followed up for more than 1 year were included in the study. The inclusion criteria were patients on maintenance PD and age >18 years old, with basic listening, speaking, reading, and understanding skills. The exclusion criteria were patients with critical illness, unable to cooperate with the required actions, unable to understand the content of the scale, patients with acute infection, tumor patients, etc. This study was approved by the Wenzhou Central Hospital Human Research Ethics Committee, and prior written consent was obtained from the Participants. Data collection The study started with registration on September 02, 2023. Trained and qualified nurses explained the study’s purpose to patients and obtained their informed consent. They administered the scale questions by reading them and recording the patient’s responses. Researchers then reviewed the completed scales to ensure data accuracy and consistency. Clinical and Laboratory data were obtained from the peritoneal dialysis registration system. Assessment of Frailty The FRAIL scale includes 5 components: Fatigue, Resistance, Ambulation (slow walking speed), Illness, and Loss of Weight (5% or more in the previous year). Frail scale scores range from 0–5 (i.e., 1 point for each component; 0=best to 5=worst) and represent frail (3–5), pre-frail (1–2), and robust (0) health status[ 12 ]. The FRAIL scale has been recommended by the latest international guidelines as the best screening tool for Frailty[ 13 ]. In a study of HD (hemodialysis) patients, the FRAIL scale proved to be an easy-to-apply tool, identifying a high prevalence of frailty and being a predictor of hospital admission[ 14 ]. In this study, we combine frail and pre-frail, classify 1-5 as frail, and 0 as non-frail status. Logistic Regression model Logistic regression is a widely used classification algorithm that uses a linear model to predict the probability of a binary outcome[ 24 ]. The model of the binary logistic regression is a linear regression of the log odds which can be expressed as[ 15 ]: It is a simple and effective way to model binary data, but it can sometimes suffer from overfitting. The loss function of the Overfitted models will fail to replicate in future samples, thus creating considerable uncertainty about the scientific merit of the finding[ 16 ]. Regularization is a technique used to avoid overfitting in machine learning models. The lasso, ridge, and elastic net are popular regularized regression models for supervised learning[ 17 ]. Elastic Net regularization combines L1 (Lasso) and L2 (Ridge) regularization by adding a penalty term to the objective function that is a combination of the absolute value and square of the coefficients. The loss function of the elastic net model can be expressed as[ 18 ]: In the loss function, the value of the α controls the mix of the lasso and ridge regression. When α = 0, it becomes the pure ridge regression, and when α = 1, it is the pure lasso regression. XGBoost Model XGBoost was mainly designed for speed and performance using gradient-boosted decision trees. It represents a way for machine boosting, or in other words, applying boosting to machines[ 19 ]. It is based on the sparsity-aware algorithm and weighted quantile sketch, which can converge the weak learners step-wisely into the ensemble to form a strong learner. Overfitting also can be reduced largely in the XGBoost model through parallel calculation and regularization lifting technology[ 20 ]. Data Analysis IBM SPSS Statistics 25 and R-Studio software (version 4.3.2) were used for data analysis. The Continuous data were expressed in different ways according to the results of normal tests, mean ± standard deviation, or median (interquartile range). The count data were expressed as the percentage of cases. Regularized Logistic Regression analysis was used to filter the effective variables for the frailty. The variables with non-zero regression coefficients would be included in the final model. The importance of the prediction model variables was ranked by XGBoost, by which the results of Regularized Logistic Regression analysis would be verified. The final selected variables were included in the unregularized Logistic Regression to construct the model ( Figure 1 ). Download figure Open in new tab Figure 1. Flow Chart of the procedure: Regularized logistic regression analysis and the XGBoost model were used to screen variables. The three features significantly related to the frail were filtered by regularized logistic regression and are the top three important variables in the XGBoost importance. The results from regularized logistic regression and XGBoost are consistent. The unregularized logistic regression was used to construct the prediction model for the frail. RESULTS Participants and Baseline Frailty Status A total of 123 patients were reviewed in this study, with an average age of (61.58± 12.8) years, and the median dialysis Duration was 38.5(18.07,60.53) months. 39 patients (31.71%) were female, 54 patients with original kidney disease (43.9%) were hypertensive nephropathy, and 54 PD patients (43.9%) were classified as frail( Table 1 ). View this table: View inline View popup Download powerpoint Table 1. Patient demographics. There are a total of one hundred and twenty-three patients in the dataset, of which forty-five Peritoneal Dialysis (PD) patients were frail. Regularized Logistic Regression Results and Verified by XGBoost Using the Regularized Logistic Regression algorithm with optimal parameters (Alpha=0.5, lambda=0.15), three significant factors associated with frailty occurrence in PD patients, each with non-zero coefficients, were selected from clinical data. As shown in the Table 2 , the three most important factors are Age, Total Cholesterol, and Ferritin. View this table: View inline View popup Download powerpoint Table 2. The Importance and the Coefficients for the Regularized Model. We find three variables are significantly related to the frailty occurrence in PD patients: Age, Total Cholesterol, and Ferritin. Using the XGBoost algorithm with optimal parameters (max_depth = 4, verbose = 0, nrounds = 20). The factors are ranked by importance from XGBoost as shown in Table 3 and Figure 2 . Table 3 shows the three measures: Gain, Cover, and Frequency in the variable importance matrix [ 19 ]. The Gain implies the relative contribution of the corresponding feature to the model. The Cover shows the relative number of observations related to the corresponding feature. Moreover, The Frequency represents the percentage of times a particular feature occurs in the model. The Gain is the most relevant attribute for interpreting the relative importance of each feature[ 19 ]. Figure 2 shows the visualization of the Gain of the different features. View this table: View inline View popup Table 3. The Importance Matrix of the Variables from XGBoost There are three measures: Gain, Cover and Frequency in the variable importance matrix The Gain is the most relevant attribute for interpreting the relative importance of each feature. Download figure Open in new tab Figure 2. XGBoost Variable Importance Plot: The Variable importance (Gain) of the XGBoost. Age, Ferritin, and TCH are the top three important features labeled by the XGBoost. The results are consistent with the regularized logistic regression. The top three features in the Gain column, Age, Total Cholesterol, and Ferritin, are consistent with the results of the regularized logistic regression model. Unregularized Logistic Regression After applying the regularized logistic regression and being verified by XGBoost, we determined that age, total cholesterol, and ferritin are the three significant factors associated with the occurrence of frailty in PD patients. Then, we use the unregularized Logistic Regression to obtain the relationship between the three variables and the occurrence of frailty. Based on the results of Unregularized Logistic Regression, a frailty prediction model for PD patients was established using three independent predictive factors: age, total cholesterol (TCH), and ferritin. The prediction model is as follows: , where logit(p) is equal to the log-odds of the p, which is . In the model above, the p is the probability of frailty. The model above shows that increasing one unit (year) of the age will result in a 0.0664 increase in logit(p), which means there is a 6.8% increase in the odd of probability of frailty. Increasing one unit (mmol/L) of the TCH will result in a 0.2157 decrease in logit(p), which means there is a 19.4% decrease in the odd of the probability of frailty. Increasing one unit (ug/L) of the Ferritin will result in a 0.003 decrease in logit(p), which means there is a 0.30% decrease in the odd of the probability of frailty. The area under the receiver operating characteristic curve (AUC) for the unregularized logistic regression model is 0.736 as shown in Figure 3 . The model shows a positive association between age and frailty, while total cholesterol and ferritin are nagetively associated with the development of frailty. Download figure Open in new tab Figure 3. The ROC of the Unregularized Logistic Regression Model: The AUC for the unregularized logistic regression model is 0.736 DISCUSSION We found that 43.9% of peritoneal dialysis patients from our data had different levels of frailty based on the FRAIL scale. The main related factors for frailty are age, total cholesterol, and ferritin. In this study, age was the most important factor for frailty in both logistic regression and importance analysis with XGBoost, which is consistent with previous studies[ 21 ], [ 22 ] ( Figure 2 ). While the biological causative mechanisms of frailty are different from those processes causing the aging process, age is still the most important factor affecting frailty.With aging, one or more physiological systems change especially the neuro-muscular, neuroendocrine, and immune systems[ 23 ]. These changes interact and accumulate, decreasing physiological function and reserve. Frailty is thought to result when damage to multiple physiological systems exceeds a threshold so much that repair mechanisms fail to maintain system homeostasis[ 22 ], [ 24 ]. Peritoneal dialysis patients often face a lot of health challenges, such as malnutrition, metabolic disorders, and cardiovascular disease[ 8 ]. Peritoneal dialysis may affect patients’ physiological function, immune system function, mental health, and quality of life[ 1 ], [ 25 ]. The patients often have chronic diseases such as diabetes and hypertension. Peritoneal dialysis patients would be sensitive to the age-related features, such that the effect of age on frailty may be exacerbated. Too much cholesterol could increase the risk of heart disease, stroke, and pancreatitis.However, the low cholesterol is also related to nutrition, infections, tumors, and liver disease[ 26 ], [ 27 ]. For patients on regular dialysis, the lower total cholesterol is usually due to malnutrition and inflammation[ 28 ]. A cross-sectional study in older adults found being at a high level of TCH was associated with a lower risk of frailty. A low TCH level might be the most associated with frailty risk[ 29 ]. People with lower TCH (≤5.2 mmol/l) were more likely to decline in functional status compared to others with higher TCH[ 27 ]. The complex effects of cholesterol may be related to age. A report showed high midlife TCH is a risk factor for subsequent dementia/Alzheimer’s disease, but decreasing TCH after midlife may reflect ongoing disease processes and may represent a risk marker for late-life cognitive impairment[ 30 ]. Additionally, other studies show that total TCH is inversely associated with mortality as a metabolic shift and reverse metabolism as well[ 31 ], [ 32 ]. Hypocholesterolemia was associated not only with an increased risk of mortality but also with an increased rate of complications (especially infections), clear biochemical evidence of malnutrition, and higher duration and cost of hospitalization[ 33 ]. In our study, the total cholesterol of the patients was 4.26(1.54)mmol/L, and only 15 percent were above the upper limit of normal. Because the overall TCH level is not high, this may be the reason why the lower the TCH, the higher the risk of frailty in our study. Ferritin is an important iron storage protein in the human body and participates in the regulation of hematopoietic and immune systems. Ferritin levels can reflect the iron reserve and nutritional status of the body, and it is related to a variety of diseases[ 34 ], [ 35 ]. We found a relationship between ferritin and frailty. A cross-sectional study in a tertiary care center also showed ferritin was an independent significant predictor of frailty[ 36 ]. The effect of ferritin on frailty may be related to factors including anemia, oxygen supply, aerobic metabolism, inflammation, immune response, and malnutrition [ 37 ], [ 38 ]. As people age, frailty has long been considered a state that accelerates the risk of adverse outcomes. Frailty is more common in patients with uremia and peritoneal dialysis[ 7 ]. Identifying biomarkers associated with frailty may benefit the care of peritoneal dialysis patients. Our center’s routine follow-up of peritoneal dialysis patients includes the complete blood count (CBC), Biochemistry Panel, and other indicators. Compared to frailty assessment scales such as FRAIL and FSQ(Frailty Screening Questionnaire), which include subjective questions about fatigue, stair climbing difficulties, and community ambulation[ 39 ], [ 40 ], these biochemical indicators are easy to obtain, stable, and objectives. Our results may help to improve the ability to identify those adults at greatest risk of frailty in the management of peritoneal dialysis patients and provide early intervention afterward. We should pay attention to the age, total cholesterol, and ferritin levels during routine examinations of peritoneal dialysis patients. Patients with frailty risk can be further examined with a frailty scale to improve the accuracy of the diagnosis (such as the FRAIL scale). However, some indicators that have diagnostic significance for frailty in other articles were not screened out in this study (such as albumin, hemoglobin, etc.) [ 36 ], [ 41 ]. The reason may be that our sample size is too small. Therefore, in the future, we plan to expand the sample size and use big data analytics to train and refine this model, and use the model to detect the peritoneal dialysis patients. The model could provide doctors with an objective tool to diagnose frailty in peritoneal dialysis patients. As the data is obtained from routine examinations, the prediction model will not bring additional burden to the work of doctors or nurses. CONCLUSION In this study, age, total cholesterol, and ferritin are the most important features associated with the frailty in peritoneal dialysis patients. This model can be used to predict frailty status and help health monitoring of peritoneal dialysis patients. In the future, we will collect more data to verify and improve the accuracy of the model. Data Availability All data produced in the present study are available upon reasonable request to the authors Funding This work was supported by Wenzhou-Kean University 2023 Internal (Faculty/Staff) Start-Up Research Grant, under ISRG2023023. Institutional Review Board Statement The study was conducted in accordance with the Declaration of Helsinki and approved by Wenzhou Central Hospital. Informed Consent Statement Written informed consent has been obtained from the patients to publish this paper. Data Availability Statement Dataset available on request from the authors Conflicts of Interest The authors declare no conflicts of interest. REFERENCES [1]. ↵ R. Gokal and N. P. Mallick , “ Peritoneal dialysis ,” The Lancet , vol. 353 , no. 9155 , pp. 823 – 828 , Mar . 1999 , doi: 10.1016/S0140-6736(98)09410-0 . OpenUrl CrossRef PubMed Web of Science [2]. ↵ K. Rockwood et al. , “ A global clinical measure of fitness and frailty in elderly people ,” CMAJ , vol. 173 , no. 5 , pp. 489 – 495 , Aug . 2005 , doi: 10.1503/cmaj.050051 . OpenUrl Abstract / FREE Full Text [3]. ↵ M. G. Shlipak et al. , “ The presence of frailty in elderly persons with chronic renal insufficiency ,” American Journal of Kidney Diseases , vol. 43 , no. 5 , pp. 861 – 867 , May 2004 , doi: 10.1053/j.ajkd.2003.12.049 . OpenUrl CrossRef PubMed Web of Science [4]. G. C.-K. Chan , J. K.-C. Ng , P. M.-S. Cheng , K.-M. Chow , C.-C. Szeto , and P. K.-T. Li , “ Dietary Micronutrient Intake and Its Relationship with the Malnutrition–Inflammation– Frailty Complex in Patients Undergoing Peritoneal Dialysis ,” Nutrients , vol. 15 , no. 23 , Art. no. 23 , Jan . 2023 , doi: 10.3390/nu15234934 . OpenUrl CrossRef [5]. J. J. Carrero et al. , “ Muscle atrophy, inflammation and clinical outcome in incident and prevalent dialysis patients ,” Clinical Nutrition , vol. 27 , no. 4 , pp. 557 – 564 , Aug . 2008 , doi: 10.1016/j.clnu.2008.04.007 . OpenUrl CrossRef PubMed Web of Science [6]. ↵ D. Fouque et al. , “ A proposed nomenclature and diagnostic criteria for protein-energy wasting in acute and chronic kidney disease ,” Kidney Int , vol. 73 , no. 4 , pp. 391 – 398 , Feb . 2008 , doi: 10.1038/sj.ki.5002585 . OpenUrl CrossRef PubMed Web of Science [7]. ↵ G. C.-K. Chan et al. , “ Progression in Physical Frailty in Peritoneal Dialysis Patients ,” Kidney and Blood Pressure Research , vol. 46 , no. 3 , pp. 342 – 351 , May 2021 , doi: 10.1159/000515635 . OpenUrl CrossRef [8]. ↵ G. C.-K. Chan , W. W.-S. Fung , C.-C. Szeto , and J. K.-C. Ng , “ From MIA to FIFA: The vicious matrix of frailty, inflammation, fluid overload and atherosclerosis in peritoneal dialysis ,” Nephrology (Carlton) , vol. 28 , no. 4 , pp. 215 – 226 , Apr . 2023 , doi: 10.1111/nep.14150 . OpenUrl CrossRef [9]. ↵ G. C.-K. Chan et al. , “ Polypharmacy Predicts Onset and Transition of Frailty, Malnutrition, and Adverse Outcomes in Peritoneal Dialysis Patients ,” The Journal of nutrition, health and aging , vol. 26 , no. 12 , pp. 1054 – 1060 , Dec . 2022 , doi: 10.1007/s12603-022-1859-8 . OpenUrl CrossRef [10]. ↵ J. Song , G. Tong , and W. Zhu , “ A Detecting System for Abrupt Changes in Temporal Incidence Rate of COVID-19 and Other Pandemics ,” Stats , vol. 6 , no. 3 , Art. no. 3 , Sep . 2023 , doi: 10.3390/stats6030058 . OpenUrl CrossRef [11]. ↵ K. A. Bhavsar , J. Singla , Y. D. Al-Otaibi , O. Y. Song , Y. B. Zikria , and A. K. Bashir , “ Medical diagnosis using machine learning: a statistical review ,” Computers, Materials and Continua , vol. 67 , no. 1 , Art. no. 1 , Jan . 2021 . OpenUrl [12]. ↵ J. Woo , R. Yu , M. Wong , F. Yeung , M. Wong , and C. Lum , “ Frailty Screening in the Community Using the FRAIL Scale ,” J Am Med Dir Assoc , vol. 16 , no. 5 , pp. 412 – 419 , May 2015 , doi: 10.1016/j.jamda.2015.01.087 . OpenUrl CrossRef PubMed [13]. ↵ E. Dent et al. , “ Physical Frailty: ICFSR International Clinical Practice Guidelines for Identification and Management ,” The Journal of nutrition, health and aging , vol. 23 , no. 9 , pp. 771 – 787 , Nov . 2019 , doi: 10.1007/s12603-019-1273-z . OpenUrl CrossRef PubMed [14]. ↵ E. M. S. Barbosa et al. , “ Comparison between FRAIL Scale and Clinical Frailty Scale in predicting hospitalization in hemodialysis patients ,” J Nephrol , vol. 36 , no. 3 , pp. 687 – 693 , Apr . 2023 , doi: 10.1007/s40620-022-01532-5 . OpenUrl CrossRef [15]. ↵ M. P. LaValley , “ Logistic Regression ,” Circulation , vol. 117 , no. 18 , pp. 2395 – 2399 , May 2008 , doi: 10.1161/CIRCULATIONAHA.106.682658 . OpenUrl FREE Full Text [16]. ↵ M. A. Babyak , “ What You See May Not Be What You Get: A Brief, Nontechnical Introduction to Overfitting in Regression-Type Models ,” Psychosomatic Medicine , vol. 66 , no. 3 , p. 411 , Jun . 2004 . OpenUrl Abstract / FREE Full Text [17]. ↵ J. Friedman , T. Hastie , and R. Tibshirani , “ Regularization Paths for Generalized Linear Models via Coordinate Descent ,” J Stat Softw , vol. 33 , no. 1 , pp. 1 – 22 , 2010 . OpenUrl CrossRef PubMed Web of Science [18]. ↵ J. K. Tay , B. Narasimhan , and T. Hastie , “ Elastic Net Regularization Paths for All Generalized Linear Models ,” J Stat Softw , vol. 106 , p. 1 , 2023 , doi: 10.18637/jss.v106.i01 . OpenUrl CrossRef [19]. ↵ T. Chen and C. Guestrin , “ XGBoost: A Scalable Tree Boosting System ,” in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, in KDD ‘16 . New York, NY, USA : Association for Computing Machinery , Aug . 2016 , pp. 785 – 794 . doi: 10.1145/2939672.2939785 . OpenUrl CrossRef [20]. ↵ Y. Zhang et al. , “ Comparison of Prediction Models for Acute Kidney Injury Among Patients with Hepatobiliary Malignancies Based on XGBoost and LASSO-Logistic Algorithms ,” International Journal of General Medicine , vol. 14 , pp. 1325 – 1335 , Apr . 2021 , doi: 10.2147/IJGM.S302795 . OpenUrl CrossRef [21]. ↵ J. K.-C. Ng et al. , “ Frailty in Chinese Peritoneal Dialysis Patients: Prevalence and Prognostic Significance ,” Kidney and Blood Pressure Research , vol. 41 , no. 6 , pp. 736 – 745 , Oct . 2016 , doi: 10.1159/000450563 . OpenUrl CrossRef [22]. ↵ L. P. Fried et al. , “ Frailty in Older Adults: Evidence for a Phenotype ,” The Journals of Gerontology: Series A , vol. 56 , no. 3 , pp. M146 – M157 , Mar . 2001 , doi: 10.1093/gerona/56.3.M146 . OpenUrl CrossRef PubMed Web of Science [23]. ↵ J. Walston et al. , “ Research agenda for frailty in older adults: toward a better understanding of physiology and etiology: summary from the American Geriatrics Society/National Institute on Aging Research Conference on Frailty in Older Adults ,” J Am Geriatr Soc , vol. 54 , no. 6 , pp. 991 – 1001 , Jun . 2006 , doi: 10.1111/j.1532-5415.2006.00745.x . OpenUrl CrossRef PubMed Web of Science [24]. ↵ A. Clegg , J. Young , S. Iliffe , M. O. Rikkert , and K. Rockwood , “ Frailty in elderly people ,” The Lancet , vol. 381 , no. 9868 , pp. 752 – 762 , Mar . 2013 , doi: 10.1016/S0140-6736(12)62167-9 . OpenUrl CrossRef PubMed Web of Science [25]. ↵ S.-M. Kim et al. , “ Comparison of hemodialysis and peritoneal dialysis patients’ dietary behaviors ,” BMC Nephrology , vol. 21 , Mar . 2020 , doi: 10.1186/s12882-020-01744-6 . OpenUrl CrossRef [26]. ↵ J. Wang and Z. Hong , “ Low Plasma Total Cholesterol Concentration: A Sensitive Evaluation Marker in Hospitalized Patients with Nutritional Deficiency Malnutrition ,” JFNR , vol. 2 , no. 9 , pp. 551 – 555 , Aug . 2014 , doi: 10.12691/jfnr-2-9-4 . OpenUrl CrossRef [27]. ↵ B. W. M. Schalk , M. Visser , D. J. H. Deeg , and L. M. Bouter , “ Lower levels of serum albumin and total cholesterol and future decline in functional performance in older persons: the Longitudinal Aging Study Amsterdam ,” Age Ageing , vol. 33 , no. 3 , pp. 266 – 272 , May 2004 , doi: 10.1093/ageing/afh073 . OpenUrl CrossRef PubMed Web of Science [28]. ↵ Y. Liu et al. , “ Association Between Cholesterol Level and Mortality in Dialysis PatientsRole of Inflammation and Malnutrition ,” JAMA , vol. 291 , no. 4 , pp. 451 – 459 , Jan . 2004 , doi: 10.1001/jama.291.4.451 . OpenUrl CrossRef PubMed Web of Science [29]. ↵ M. Yin et al. , “ Cholesterol alone or in combination is associated with frailty among community-dwelling older adults: A cross-sectional study ,” Exp Gerontol , vol. 180 , p. 112254 , Sep . 2023 , doi: 10.1016/j.exger.2023.112254 . OpenUrl CrossRef [30]. ↵ A. Solomon et al. , “ Serum cholesterol changes after midlife and late-life cognition ,” Neurology , vol. 68 , no. 10 , pp. 751 – 756 , Mar . 2007 , doi: 10.1212/01.wnl.0000256368.57375.b7 . OpenUrl CrossRef PubMed [31]. ↵ A. H. Abdelhafiz , B. E. Loo , N. Hensey , C. Bailey , and A. Sinclair , “ The U-shaped Relationship of Traditional Cardiovascular Risk Factors and Adverse Outcomes in Later Life ,” Aging Dis , vol. 3 , no. 6 , pp. 454 – 464 , Oct . 2012 . OpenUrl [32]. ↵ U. M. Vischer et al. , “ Cardiometabolic determinants of mortality in a geriatric population: Is there a ‘reverse metabolic syndrome’? ,” Diabetes & Metabolism , vol. 35 , no. 2 , pp. 108 – 114 , Apr . 2009 , doi: 10.1016/j.diabet.2008.08.006 . OpenUrl CrossRef PubMed Web of Science [33]. ↵ P. Ranieri , R. Rozzini , S. Franzoni , P. Barbisoni , and M. Trabucchi , “ Serum Cholesterol Levels as a Measure of Frailty in Elderly Patients ,” Experimental Aging Research , vol. 24 , no. 2 , pp. 169 – 179 , Mar . 1998 , doi: 10.1080/036107398244300 . OpenUrl CrossRef PubMed Web of Science [34]. ↵ W. Wang , M. A. Knovich , L. G. Coffman , F. M. Torti , and S. V. Torti , “ Serum ferritin: Past, present and future ,” Biochim Biophys Acta , vol. 1800 , no. 8 , pp. 760 – 769 , Aug . 2010 , doi: 10.1016/j.bbagen.2010.03.011 . OpenUrl CrossRef PubMed [35]. ↵ M. N. Garcia-Casal , S.-R. Pasricha , R. X. Martinez , L. Lopez-Perez , and J. P. Peña-Rosas , “ Serum or plasma ferritin concentration as an index of iron deficiency and overload ,” Cochrane Database of Systematic Reviews , no. 5 , 2021 , doi: 10.1002/14651858.CD011817.pub2 . OpenUrl CrossRef [36]. ↵ A. Kumar , M. Dhar , M. Agarwal , A. Mukherjee , and V. Saxena , “ Predictors of Frailty in the Elderly Population: A Cross-Sectional Study at a Tertiary Care Center ,” Cureus , vol. 14 , no. 10 , p. e30557 , Oct . 2022 , doi: 10.7759/cureus.30557 . OpenUrl CrossRef [37]. ↵ C. Dugan , K. Cabolis , L. F. Miles , and T. Richards , “ Systematic review and meta-analysis of intravenous iron therapy for adults with non-anaemic iron deficiency: An abridged Cochrane review ,” J Cachexia Sarcopenia Muscle , vol. 13 , no. 6 , pp. 2637 – 2649 , Dec . 2022 , doi: 10.1002/jcsm.13114 . OpenUrl CrossRef [38]. ↵ O. A. Abulseoud et al. , “ Attenuated initial serum ferritin concentration in critically ill coronavirus disease 2019 geriatric patients with comorbid psychiatric conditions ,” Front Psychiatry , vol. 13 , p. 1035986 , 2022 , doi: 10.3389/fpsyt.2022.1035986 . OpenUrl CrossRef [39]. ↵ K.-U. Saum , H. Müller , C. Stegmaier , K. Hauer , E. Raum , and H. Brenner , “ Development and Evaluation of a Modification of the Fried Frailty Criteria Using Population-Independent Cutpoints ,” Journal of the American Geriatrics Society , vol. 60 , no. 11 , pp. 2110 – 2115 , 2012 , doi: 10.1111/j.1532-5415.2012.04192.x . OpenUrl CrossRef PubMed [40]. ↵ I. Palomo et al. , “ Characterization by Gender of Frailty Syndrome in Elderly People according to Frail Trait Scale and Fried Frailty Phenotype ,” Journal of Personalized Medicine , vol. 12 , no. 5 , Art. no. 5 , May 2022 , doi: 10.3390/jpm12050712 . OpenUrl CrossRef [41]. ↵ K. Jayanama , O. Theou , J. M. Blodgett , L. Cahill , and K. Rockwood , “ Frailty, nutrition-related parameters, and mortality across the adult age spectrum ,” BMC Med , vol. 16 , no. 1 , p. 188 , Oct . 2018 , doi: 10.1186/s12916-018-1176-6 . OpenUrl CrossRef View the discussion thread. Back to top Previous Next Posted July 31, 2024. Download PDF Data/Code Email Thank you for your interest in spreading the word about medRxiv. NOTE: Your email address is requested solely to identify you as the sender of this article. Your Email * Your Name * Send To * Enter multiple addresses on separate lines or separate them with commas. You are going to email the following Analysis of Frailty in Peritoneal Dialysis Patients Based on Logistic Regression Model and XGBoost Model Message Subject (Your Name) has forwarded a page to you from medRxiv Message Body (Your Name) thought you would like to see this page from the medRxiv website. Your Personal Message CAPTCHA This question is for testing whether or not you are a human visitor and to prevent automated spam submissions. Share Analysis of Frailty in Peritoneal Dialysis Patients Based on Logistic Regression Model and XGBoost Model Qi Liu , Guanchao Tong , Qiong Ye medRxiv 2024.07.29.24311190; doi: https://doi.org/10.1101/2024.07.29.24311190 Share This Article: Copy Citation Tools Analysis of Frailty in Peritoneal Dialysis Patients Based on Logistic Regression Model and XGBoost Model Qi Liu , Guanchao Tong , Qiong Ye medRxiv 2024.07.29.24311190; doi: https://doi.org/10.1101/2024.07.29.24311190 Citation Manager Formats BibTeX Bookends EasyBib EndNote (tagged) EndNote 8 (xml) Medlars Mendeley Papers RefWorks Tagged Ref Manager RIS Zotero Tweet Widget Facebook Like Google Plus One Subject Area Endocrinology (including Diabetes Mellitus and Metabolic Disease) Subject Areas All Articles Addiction Medicine (572) Allergy and Immunology (864) Anesthesia (302) Cardiovascular Medicine (4448) Dentistry and Oral Medicine (444) Dermatology (383) Emergency Medicine (609) Endocrinology (including Diabetes Mellitus and Metabolic Disease) (1515) Epidemiology (15240) Forensic Medicine (30) Gastroenterology (1130) Genetic and Genomic Medicine (6614) Geriatric Medicine (669) Health Economics (1000) Health Informatics (4550) Health Policy (1372) Health Systems and Quality Improvement (1613) Hematology (543) HIV/AIDS (1268) Infectious Diseases (except HIV/AIDS) (15928) Intensive Care and Critical Care Medicine (1106) Medical Education (624) Medical Ethics (147) Nephrology (668) Neurology (6622) Nursing (346) Nutrition (999) Obstetrics and Gynecology (1147) Occupational and Environmental Health (957) Oncology (3343) Ophthalmology (977) Orthopedics (369) Otolaryngology (421) Pain Medicine (436) Palliative Medicine (130) Pathology (665) Pediatrics (1695) Pharmacology and Therapeutics (693) Primary Care Research (714) Psychiatry and Clinical Psychology (5459) Public and Global Health (9249) Radiology and Imaging (2205) Rehabilitation Medicine and Physical Therapy (1371) Respiratory Medicine (1197) Rheumatology (597) Sexual and Reproductive Health (715) Sports Medicine (530) Surgery (714) Toxicology (99) Transplantation (289) Urology (265) (function(){function c(){var b=a.contentDocument||a.contentWindow.document;if(b){var d=b.createElement('script');d.innerHTML="window.__CF$cv$params={r:'a02901917a2c3fe2',t:'MTc3OTkyNjcwOQ=='};var a=document.createElement('script');a.src='/cdn-cgi/challenge-platform/scripts/jsd/main.js';document.getElementsByTagName('head')[0].appendChild(a);";b.getElementsByTagName('head')[0].appendChild(d)}}if(document.body){var a=document.createElement('iframe');a.height=1;a.width=1;a.style.position='absolute';a.style.top=0;a.style.left=0;a.style.border='none';a.style.visibility='hidden';document.body.appendChild(a);if('loading'!==document.readyState)c();else if(window.addEventListener)document.addEventListener('DOMContentLoaded',c);else{var e=document.onreadystatechange||function(){};document.onreadystatechange=function(b){e(b);'loading'!==document.readyState&&(document.onreadystatechange=e,c())}}}})();