A machine-learning-derived online screening tool for depressive symptoms in chronic digestive system diseases patients: A cross- sectional study with temporal validation from CHARLS

A machine-learning-derived online screening tool for depressive symptoms in chronic digestive system diseases patients: A cross- sectional study with temporal validation from CHARLS | 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 A machine-learning-derived online screening tool for depressive symptoms in chronic digestive system diseases patients: A cross- sectional study with temporal validation from CHARLS Zixun Huang, Liangze Ma, Xin Wang, Mingheng Liu, Shaopeng Zheng, and 5 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9205724/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 13 You are reading this latest preprint version Abstract Chronic digestive system diseases (CDSD) are common in older adults, and depressive symptoms substantially worsen prognosis and quality of life. We developed and temporally validated a machine-learning model to identify depressive symptoms in individuals with CDSD using data from the China Health and Retirement Longitudinal Study (CHARLS). This study included 3,762 participants with CDSD from the 2011 survey and examined 46 behavioral, health, psychological, and sociodemographic variables. Feature selection was performed using logistic regression and LASSO regression, and seven machine-learning algorithms were compared. Temporal validation was conducted in newly diagnosed CDSD participants from the 2015 CHARLS wave. Among 3,762 participants, 1,900 had depressive symptoms. Thirteen variables were retained, including education, residence, life assessment, health assessment, fall history, disability, kidney disease, arthritis, heart disease, eyesight, instrumental activities of daily living, sleep duration, and grip strength. XGBoost showed the best performance in the testing set, with an area under the curve of 0.793 and an F1-score of 0.724, together with good calibration and clinical utility. These findings suggest that machine-learning approaches may support early identification of depressive symptoms in people with CDSD. Health sciences/Diseases Health sciences/Health care Health sciences/Medical research Health sciences/Risk factors Chronic digestive system diseases Depression Prediction model Machine learning Shap Website visualization Figures Figure 1 Figure 2 Figure 3 Introduction Chronic digestive system diseases (CDSD) represent a diverse and complex group of clinical conditions, including reflux esophagitis, non-erosive gastroesophageal reflux disease, Barrett's esophagus, chronic gastritis, irritable bowel syndrome (IBS), Crohn's disease, ulcerative colitis, and liver cirrhosis. These diseases impose a substantial burden on global health. Specifically, in 2019, the global age-standardized prevalence reached 95,582 cases per 100,000 individuals 1 , contributing significantly to mortality and disability-adjusted life years (DALYs). In China, the impact of CDSD is particularly severe, with 499.2 million cases reported in 2019, leading to 1.557 million deaths. Concurrently, depression, a prevalent mental health disorder, is increasingly recognized for its associated health risks. Research indicates that the prevalence of depression is markedly higher among patients with CDSD and is closely linked to poorer clinical outcomes 2 . Emerging evidence suggests a bidirectional relationship between CDSD and depression. A recent cohort study demonstrated that individuals with baseline CDSD had a 36% increased risk of developing new-onset depression, whereas those with baseline depression faced a 61% higher risk of developing CDSD 3 . While these epidemiological findings underscore a strong clinical association, the underlying biological mechanisms require further investigation. At a microscopic level, CDSD may directly influence the psychopathological processes of depression via the gut-brain axis, with proposed mechanisms involving oxidative stress and inflammatory pathways 4 – 6 . Given these compelling clinical and mechanistic interactions, assessing and predicting the risk of depression in patients with CDSD holds significant importance for informing clinical treatment strategies and enhancing patient prognosis. Despite increasing acknowledgment of the connection between Chronic Digestive System Diseases (CDSD) and depression 2 , 3 , 7 , a notable research gap remains: the development of predictive models for depression risk specifically in CDSD patients. Prior studies, often reliant on traditional regression models, may be insufficient for capturing the complex, non-linear relationships characteristic of this association. This is particularly relevant within the context of a globally aging population, where multiple health factors intersect. Machine learning (ML) presents a robust alternative, capable of autonomously identifying complex patterns from multidimensional data—including demographic, clinical, and patient-reported outcomes—without relying on pre-specified parameters. Consequently, developing an interpretable and generalizable ML model to predict depression in CDSD patients is essential for optimizing clinical decision-making and improving patient management 8 – 10 . This study employs longitudinal cohort data from the China Health and Retirement Longitudinal Study (CHARLS). By leveraging the extensive dataset within the CHARLS database, it aims to identify and predict characteristic variables associated with depression and to investigate the relationship between CDSD and the onset of depression among middle-aged and older adults. Results Patient Characteristics The 2011 CHARLS database included a total of 17,780 respondents,among whom 3,762 met the inclusion criteria for chronic digestive diseases. Of these eligible individuals,1,900 (50.5%) exhibited depressive symptoms. The mean age of the overall cohort was 59.01 ± 9.31 years, and 1,676 (44.55%)were male. As shown in Table 1 , significant differences were observed between participants with and without depressive symptoms in terms of sociodemographic characteristics, physical examination findings, laboratory test results, and comorbidities. Furthermore, no significant differences in variable distributions were found between the training set and the testing set ( Supplementary Table 2 ). The baseline characteristics of the Temporal Validation set are presented in Supplementary Table 3 , which included 778 patients, of whom 366 had depressive symptoms. Table 1 Comparison of Baseline Data Between Depressive and Non-depressive Groups in the Training and Testing set. Characteristic Training set(N = 2,634) Testing set(N = 1,128) Non-depressive symptoms (n = 1,304) Incident depressive symptoms (n = 1,330) p value Non-depressive symptoms (n = 558) Incident depressive symptoms (n = 570) p value Gender ,n(%) < 0.001 < 0.001 Female 617(47.32%) 849(63.83%) 244(43.73%) 376(65.96%) Male 687(52.68%) 481(36.17%) 314(56.27%) 194(34.04%) Marriage status ,n(%) < 0.001 0.001 Married 1,098(84.20%) 1,038(78.05%) 477(85.48%) 445(78.07%) Other 206(15.80%) 292(21.95%) 81(14.52%) 125(21.93%) Education ,n(%) < 0.001 < 0.001 Less than high school 1,135(87.04%) 1,259(94.66%) 478(85.66%) 538(94.39%) High school and above 169(12.96%) 71(5.34%) 80(14.34%) 32(5.61%) Residence ,n(%) < 0.001 0.003 Urban 527(40.41%) 382(28.72%) 217(38.89%) 173(30.35%) Rural 777(59.59%) 948(71.28%) 341(61.11%) 397(69.65%) Life assessment ,n(%) < 0.001 < 0.001 Not good 106(8.13%) 339(25.49%) 58(10.39%) 144(25.26%) Good 1,198(91.87%) 991(74.51%) 500(89.61%) 426(74.74%) Health assessment ,n(%) < 0.001 < 0.001 Not good 350(26.84%) 764(57.44%) 149(26.70%) 344(60.35%) Good 954(73.16%) 566(42.56%) 409(73.30%) 226(39.65%) Social activity ,n(%) 0.029 0.053 No 677(51.92%) 747(56.17%) 300(53.76%) 339(59.47%) Yes 627(48.08%) 583(43.83%) 258(46.24%) 231(40.53%) Standing balance ,n(%) < 0.001 < 0.001 No 248(19.02%) 420(31.58%) 101(18.10%) 162(28.42%) Yes 1,056(80.98%) 910(68.42%) 457(81.90%) 408(71.58%) Falldown ,n(%) < 0.001 < 0.001 No 1,102(84.51%) 969(72.86%) 495(88.71%) 419(73.51%) Yes 202(15.49%) 361(27.14%) 63(11.29%) 151(26.49%) Disability ,n(%) < 0.001 < 0.001 No 1,095(83.97%) 957(71.95%) 473(84.77%) 410(71.93%) Yes 209(16.03%) 373(28.05%) 85(15.23%) 160(28.07%) Hearing ,n(%) < 0.001 < 0.001 No 1,132(86.81%) 1,043(78.42%) 500(89.61%) 428(75.09%) Yes 172(13.19%) 287(21.58%) 58(10.39%) 142(24.91%) Teeth loss ,n(%) < 0.001 0.004 No 1,210(92.79%) 1,182(88.87%) 519(93.01%) 501(87.89%) Yes 94(7.21%) 148(11.13%) 39(6.99%) 69(12.11%) Asthma ,n(%) < 0.001 0.002 No 1,255(96.24%) 1,225(92.11%) 537(96.24%) 523(91.75%) Yes 49(3.76%) 105(7.89%) 21(3.76%) 47(8.25%) Cancer ,n(%) 0.078 0.587 No 1,291(99.00%) 1,306(98.20%) 553(99.10%) 563(98.77%) Yes 13(1.00%) 24(1.80%) 5(0.90%) 7(1.23%) Liver disease, n(%) < 0.001 0.184 No 1,229(94.25%) 1,204(90.53%) 526(94.27%) 526(92.28%) Yes 75(5.75%) 126(9.47%) 32(5.73%) 44(7.72%) Kidney disease, n(%) < 0.001 0.010 No 1,212(92.94%) 1,124(84.51%) 508(91.04%) 491(86.14%) Yes 92(7.06%) 206(15.49%) 50(8.96%) 79(13.86%) Dyslipid, n(%) 0.055 0.012 No 1,156(88.65%) 1,146(86.17%) 500(89.61%) 482(84.56%) Yes 148(11.35%) 184(13.83%) 58(10.39%) 88(15.44%) Arthritis ,n(%) < 0.001 < 0.001 No 761(58.36%) 491(36.92%) 317(56.81%) 242(42.46%) Yes 543(41.64%) 839(63.08%) 241(43.19%) 328(57.54%) Stroke, n(%) < 0.001 0.004 No 1,288(98.77%) 1,279(96.17%) 549(98.39%) 544(95.44%) Yes 16(1.23%) 51(3.83%) 9(1.61%) 26(4.56%) Heart disease, n(%) < 0.001 0.003 No 1,125(86.27%) 1,015(76.32%) 466(83.51%) 435(76.32%) Yes 179(13.73%) 315(23.68%) 92(16.49%) 135(23.68%) Lung disease, n(%) < 0.001 0.008 No 1,147(87.96%) 1,044(78.50%) 487(87.28%) 465(81.58%) Yes 157(12.04%) 286(21.50%) 71(12.72%) 105(18.42%) Eyesight, n(%) < 0.001 < 0.001 Nor 880(67.48%) 613(46.09%) 383(68.64%) 277(48.60%) Yes 424(32.52%) 717(53.91%) 175(31.36%) 293(51.40%) BADL, n(%) < 0.001 < 0.001 No 1,129(86.58%) 876(65.86%) 488(87.46%) 371(65.09%) Yes 175(13.42%) 454(34.14%) 70(12.54%) 199(34.91%) IADL, n(%) < 0.001 < 0.001 No 1,100(84.36%) 785(59.02%) 478(85.66%) 328(57.54%) Yes 204(15.64%) 545(40.98%) 80(14.34%) 242(42.46%) DM ,n(%) 0.069 0.959 No 1,157(88.73%) 1,149(86.39%) 484(86.74%) 495(86.84%) Yes 147(11.27%) 181(13.61%) 74(13.26%) 75(13.16%) Hypertension, n(%) 0.037 0.161 No 832(63.80%) 796(59.85%) 367(65.77%) 352(61.75%) Yes 472(36.20%) 534(40.15%) 191(34.23%) 218(38.25%) Smoking ,n(%) < 0.001 < 0.001 No 724(55.52%) 880(66.17%) 305(54.66%) 393(68.95%) Used to smoke 177(13.57%) 129(9.70%) 74(13.26%) 49(8.60%) Smoking now 403(30.90%) 321(24.14%) 179(32.08%) 128(22.46%) Drinking, n(%) < 0.001 < 0.001 No 715(54.83%) 838(63.01%) 313(56.09%) 380(66.67%) Used to drink 127(9.74%) 135(10.15%) 55(9.86%) 64(11.23%) Drinking now 462(35.43%) 357(26.84%) 190(34.05%) 126(22.11%) Age, Mean ± SD 58.18 ± 9.08 59.92 ± 9.62 < 0.001 57.75 ± 8.88 60.02 ± 9.20 < 0.001 Sleep nap, Median (IQR) 32.03 ± 40.34 27.92 ± 40.05 0.009 31.95 ± 41.09 28.04 ± 38.82 0.101 Sleep night, Median (IQR) 6.50 ± 1.67 5.38 ± 2.05 < 0.001 6.50 ± 1.69 5.51 ± 2.08 < 0.001 BMI, mean ± SD 23.26 ± 3.85 22.86 ± 3.81 0.007 23.15 ± 3.66 22.75 ± 3.78 0.078 Waist, mean ± SD 84.34 ± 9.63 83.59 ± 10.05 0.052 84.38 ± 9.81 83.22 ± 10.13 0.050 Pulse, mean ± SD 71.28 ± 9.85 71.48 ± 10.24 0.617 71.93 ± 10.16 71.85 ± 10.19 0.894 LDL, mean ± SD 115.33 ± 32.95 115.67 ± 33.48 0.789 112.77 ± 33.13 115.82 ± 32.00 0.116 HDL-C, mean ± SD 50.90 ± 14.90 52.31 ± 14.90 0.015 50.49 ± 14.63 52.35 ± 15.08 0.036 Uric acid, mean ± SD 4.44 ± 1.11 4.24 ± 1.10 < 0.001 4.46 ± 1.09 4.11 ± 1.09 < 0.001 WBC, mean ± SD 6.11 ± 1.66 6.08 ± 1.73 0.730 6.09 ± 1.65 6.00 ± 1.66 0.377 Hemoglobin, mean ± SD 14.30 ± 1.90 13.93 ± 1.86 < 0.001 14.34 ± 1.89 13.85 ± 1.84 < 0.001 PLT, mean ± SD 202.57 ± 64.59 208.32 ± 67.33 0.026 205.38 ± 64.66 208.04 ± 65.68 0.492 BUN, mean ± SD 15.58 ± 4.16 15.54 ± 4.26 0.803 15.81 ± 4.42 15.85 ± 4.36 0.882 HbA1c, mean ± SD 5.16 ± 0.46 5.16 ± 0.48 0.898 5.16 ± 0.48 5.18 ± 0.48 0.603 CRP, mean ± SD 1.70 ± 2.30 1.90 ± 2.69 0.043 1.66 ± 2.28 1.93 ± 2.64 0.069 TG, mean ± SD 131.23 ± 81.33 126.23 ± 76.06 0.103 133.97 ± 83.63 133.15 ± 82.13 0.868 TC, mean ± SD 192.73 ± 36.69 192.66 ± 37.03 0.961 189.78 ± 36.41 194.54 ± 36.51 0.029 Creatinine, mean ± SD 0.79 ± 0.18 0.76 ± 0.17 < 0.001 0.79 ± 0.19 0.75 ± 0.17 < 0.001 FBG, mean ± SD 105.19 ± 20.42 104.37 ± 18.63 0.281 105.14 ± 20.93 104.62 ± 18.82 0.660 MCV, mean ± SD 90.95 ± 7.80 90.32 ± 8.29 0.045 91.33 ± 7.82 89.37 ± 8.44 < 0.001 Hematocrit, mean ± SD 41.45 ± 5.89 40.54 ± 5.80 < 0.001 41.71 ± 5.53 40.22 ± 5.83 < 0.001 Grip strength, mean ± SD 32.35 ± 10.24 27.01 ± 9.76 < 0.001 32.91 ± 10.09 26.73 ± 9.18 < 0.001 SBP, mean ± SD 128.19 ± 20.70 128.33 ± 21.14 0.859 126.98 ± 20.03 128.62 ± 20.90 0.178 DBP, mean ± SD 75.27 ± 11.96 74.11 ± 11.68 0.012 74.56 ± 11.22 74.49 ± 11.83 0.923 Note : CHARLS, China Health and Retirement Longitudinal Study; CDSD, chronic digestive system diseases; CES-D-10, 10-item Center for Epidemiologic Studies Depression Scale; BADL, Basic Activities of Daily Living; IADL, Instrumental Activities of Daily Living; LDL, low-density lipoprotein; HDL-C, high-density lipoprotein cholesterol; WBC, white blood cell count; PLT, platelet count; BUN, blood urea nitrogen; HbA1c, glycated hemoglobin A1c; CRP, C-reactive protein; TG, triglycerides; TC, total cholesterol; FBG, fasting blood glucose; MCV, mean corpuscular volume; SBP, systolic blood pressure; DBP, diastolic blood pressure. The study population included participants with baseline CDSD from CHARLS 2011, who were randomly divided into a training set (70%) and a testing set (30%). Depressive symptoms were defined as a CES-D-10 score ≥ 10, and non-depressive symptoms were defined as a CES-D-10 score < 10. Missing data in retained variables were handled using multiple imputation before model development. Continuous variables are presented as mean ± SD, and categorical variables are presented as n (%). P values were calculated using Student’s t-test or the Wilcoxon rank-sum test for continuous variables, and the chi-square test or Fisher’s exact test for categorical variables, as appropriate. Variable Selection and model performance comparison In the univariate analysis of the development set, a total of 39 variables (Age, Sleep_nap, Sleep_night, BMI, HDL_C, Uric_acid, Hemoglobin, PLT, CRP, Creatinine, MCV, Hematocrit, Grip_strength, DBP, Gender, Marriage, Education, Residence, Life_assessment, Health_assessment, Social_activity, Standing_balance, Falldown, Disability, Hearing, Teeth_loss, Asthma, Liver_disease, Kidney_disease, Arthritis,Stroke, Heart_disease, Lung_disease, Eyesight, BADL, IADL, Hypertension, Smoking, Drinking) exhibited a P-value of less than 0.05. These variables were subsequently subjected to multivariate regression analysis,from which 15 variables were selected ( Supplementary Table 4 ).Concurrently, LASSO regression analysis was performed. Two vertical dashed lines correspond to the lambda values selected by the minimum mean squared error criterion (left line, λ = 0.0060) and the one-standard-error rule (right line, λ = 0.0241), respectively. Ten-fold cross-validation was also conducted (Fig. 2 B). Finally, the intersection of variables selected by both methods was taken, resulting in the final selection of 13 features: Education, Residence, Life assessment, Health assessment, Falldown, Disability, Kidney disease, Arthritis, Heart disease, Eyesight, IADL, Sleep night, and Grip strength. Seven machine learning algorithms were employed to predict the occurrence of depression in patients with CDSD. The performance of these models was evaluated using the Receiver Operating Characteristic (ROC)curve, Precision-Recall (PR)curve, calibration curve, Decision Curve Analysis (DCA), sensitivity, specificity, and F1 score. The specific performance metrics are presented in Table 2 . In predicting depression outcomes in the test set,the XGBoost model demonstrated the most robust predictive performance. Its Area Under the ROC Curve (AUROC) was 0.793 (95%CI:0.767–0.816), with an accuracy of 0.724 sensitivity of 0.714 precision of 0.733, specificity of 0.735, and an F1 score of 0.724. Subsequent calibration curve results indicated that the trends for the temporal validation set and the test set were largely consistent (Fig. 2 E,F). The XGBoost model also exhibited high efficacy in the validation set,with an AUROC of 0.758 (95%CI:0.725–0.790), accuracy of 0.690, sensitivity of 0.743, precision of 0.649,specificity of 0.643, and an F1 score of 0.693 (Table 2 ). Table 2 Detailed performance metrics of various machine learning models in predicting depression risk in CDSD patients within the testing and validation sets. Model AUC 95%CI Lower 95%CI Upper Accuracy Precision Sensitivity Specificity F1 Score Testing set Logistic 0.790 0.763 0.815 0.717 0.725 0.711 0.724 0.717 Decision Tree 0.746 0.717 0.773 0.691 0.684 0.721 0.659 0.702 Random Forest 0.785 0.757 0.810 0.714 0.720 0.709 0.719 0.714 XGBoost 0.793 0.767 0.816 0.724 0.733 0.714 0.735 0.724 LightGBM 0.779 0.751 0.803 0.700 0.709 0.691 0.710 0.700 SVM 0.793 0.766 0.818 0.715 0.723 0.709 0.722 0.716 ANN 0.790 0.764 0.816 0.717 0.731 0.696 0.738 0.713 Validation set Logistic 0.777 0.742 0.809 0.693 0.651 0.749 0.643 0.696 Decision Tree 0.713 0.677 0.749 0.657 0.615 0.724 0.597 0.665 Random Forest 0.757 0.732 0.800 0.695 0.649 0.768 0.631 0.703 XGBoost 0.758 0.725 0.790 0.690 0.649 0.743 0.643 0.693 LightGBM 0.799 0.713 0.782 0.679 0.642 0.716 0.646 0.677 SVM 0.768 0.744 0.811 0.703 0.662 0.754 0.658 0.705 ANN 0.776 0.741 0.807 0.699 0.656 0.760 0.646 0.704 Note: CDSD, chronic digestive system diseases; AUC, area under the receiver operating characteristic curve; CI, confidence interval; SVM, support vector machine; ANN, artificial neural network; XGBoost, extreme gradient boosting; LightGBM, light gradient boosting machine. Model performance was evaluated in the testing and validation sets using discrimination and classification metrics, including AUC, accuracy, precision, sensitivity, specificity, and F1 score. AUC values are presented with 95% confidence intervals. Higher AUC values indicate better discriminative ability, whereas higher values for accuracy, precision, sensitivity, specificity, and F1 score indicate better overall classification performance. Interpretability and application of the model SHAP values can provide deeper insights into how XGBoost models make predictions. Figure 3 A is a SHAP beeswarm plot, illustrating the impact of each feature on the target variable, depression. A higher SHAP value on the x-axis indicates that the feature is more likely to increase the likelihood of depression. The color gradient from red to blue represents the magnitude of the feature values, with red indicating high feature values and blue indicating lower feature values. Longer nighttime sleep duration, higher self-rated health, greater life satisfaction,and higher grip strength all contribute to reducing the risk of depression. Conversely, factors such as Instrumental Activities of Daily Living (IADL)impairment, arthritis, poor vision, falls, rural residence, kidney disease, heart disease, disability, and low education level all increase the risk of depression. Supplementary Fig. 3 uses SHAP value visualization techniques to detail the contribution of each feature to the model’s prediction results. Figure 3 B lists the importance ranking of variables in the model, with nighttime sleep duration, self-rated health, life satisfaction, IADL, and grip strength being the top five most important variables. The waterfall plot in Fig. 3 C demonstrates how each feature drives the model’s baseline value toward the final predicted value. Red features indicate positive contributions, while blue features indicate negative influences. Interestingly, when an individual’s sleep duration was 8 hours, the SHAP value was + 0.06, indicating an increased predicted probability of depressive symptoms. This suggests that the association between sleep duration and depressive symptoms in patients with CDSD may be nonlinear. Using Streamlit, we built a deployable web platform that achieved the visualization and basic application of the prediction model, while hosting the source code on GitHub. This platform has now become an online tool for assessing depression risk in patients with chronic gastrointestinal diseases. Users can simply input the patient’s clinical characteristics into specific text boxes on the webpage to conveniently obtain corresponding prediction results. Discussion In China, the accelerated aging of the population and shifts in lifestyle patterns have contributed to a rising annual prevalence of Chronic Digestive System Diseases (CDSD), presenting a significant public health challenge. However, due to limited public awareness regarding mental health and an uneven distribution of healthcare resources, many patients do not receive timely diagnosis or effective treatment. Research indicates that individuals with chronic digestive system diseases face a substantially higher risk of developing depression compared to the general population 11 . This increased risk is likely linked to factors such as chronic pain, persistent inflammatory states, neuroendocrine dysregulation, and psychological stress 12 . Conversely, depression can worsen the symptoms of CDSD, establishing a vicious cycle that adversely affects patient prognosis and quality of life 13 . To address this issue, our study analyzed data from 3,762 middle-aged and elderly CDSD patients from the China Health and Retirement Longitudinal Study (CHARLS). Key predictive variables were identified using multivariate regression and LASSO regression analysis. An XGBoost model was subsequently employed to develop a clinical prediction model, complemented by an online prediction tool. This model aims to facilitate the early identification of CDSD patients at high risk for depression, allowing for personalized interventions to enhance mental health and quality of life. Among the 13 key characteristic variables ultimately identified, the top five in terms of predictive weight were: nighttime sleep duration, self-rated health, life satisfaction, Instrumental Activities of Daily Living (IADL), and grip strength. The circadian rhythm system is a well-established primary regulator of metabolism, precisely controlling the temporal patterns of hormone secretion, enzyme activity, and energy intake through its influence on clock gene expression. A growing body of evidence suggests that insufficient nighttime sleep duration is strongly associated with an elevated risk of depression 14 , 15 , potentially due to the impact of sleep quality on emotional regulation 16 . Disruption of this finely tuned regulatory mechanism can trap the body in a vicious cycle where CDSD and depression mutually reinforce each other 17 , 18 . Subjective well-being encompasses an individual's overall evaluation and perception of life satisfaction and self-rated health. Due to symptoms such as low mood, anhedonia, and impaired cognitive function, patients with depression often struggle to accurately assess these subjective indicators 19 . This distorted perception of well-being and self-rated health can intensify feelings of distress and helplessness, potentially contributing to the development or exacerbation of CDSD. IADL measures an individual's capacity to perform essential self-care tasks in daily life, with studies demonstrating a significant decline in this ability among depressed patients. Grip strength serves as an objective marker of physical functional status; previous research has consistently shown that lower grip strength correlates with a higher risk of depression, a finding supported by multiple studies 20 – 22 . Residence in rural areas may be linked to relatively limited access to medical resources and weaker social support networks, factors that can increase psychological burden. Lower educational attainment might indicate a lack of health literacy and coping strategies for psychological issues, rendering individuals more vulnerable to depression. Conditions such as arthritis, poor vision, falls, disability, kidney disease, and heart disease may promote depressive symptoms by restricting patients' daily activities, increasing physical discomfort and dependence, and limiting social engagement 23 . We employed a hybrid feature selection strategy that integrated LASSO regression with a multivariate regression model. Predictive modeling was conducted using logistic regression, decision tree, Random Forest, XGBoost, LightGBM, support vector machine (SVM), and artificial neural network (ANN) models, thereby ensuring diversity and robustness in model construction. Through a multidimensional evaluation framework, comprehensive metrics-including the area under the curve (AUC), accuracy, sensitivity, specificity, precision, and F1-score-were adopted. These indicators collectively assessed the predictive efficacy of the models from multiple perspectives, improving the reliability of the research findings. However, in our study, the AUC of XGBoost in the testing set was not substantially higher than that of the other models. Nevertheless, because it achieved the highest F1 score, we selected it as the best-performing model. In the temporal validation set, however, XGBoost performed comparably to simpler models. This study provides a new perspective on predicting depression outcomes among patients with CDSD. Temporal cohort validation was performed, which enhances the generalizability and representativeness of the findings. The model improves diagnostic and therapeutic efficiency, as the selected predictors are readily accessible in routine clinical practice. Furthermore, it maintains clinical interpretability, allowing healthcare providers to allocate limited resources more effectively to high-risk patients and thereby facilitate more precise and targeted care. Nevertheless, several limitations should be acknowledged. The model was developed retrospectively using a single wave of data from the China Health and Retirement Longitudinal Study (CHARLS), which lacks long-term patient follow-up, making it difficult to dynamically monitor disease progression. Additionally, depression symptoms were assessed based on self-reported CHARLS data, which may introduce reporting bias. Meanwhile, the CHARLS database used a standardized self-reported questionnaire for chronic diseases and did not provide detailed information on disease subtypes or indicators of disease activity/severity, which further limited our ability to conduct stratified analyses of related factors. Conclusion In this study, seven machine learning models were developed to identify factors predicting depression among patients with CDSD using the CHARLS database. By deploying an online prediction tool and integrating it into clinical practice, healthcare providers can more effectively allocate limited resources to high-risk patients, thereby ensuring more precise and targeted care. Methods Data source This analysis utilized data from the 2011 national baseline wave of the China Health and Retirement Longitudinal Study (CHARLS), a publicly accessible database (available at: http://charls.pku.edu.cn/ ). CHARLS is a nationally representative longitudinal survey focusing on the Chinese population aged 45 years and older. The study's comprehensive methodology has been described in detail elsewhere 24 . In summary, the survey employed a multistage, stratified, probability-proportional-to-size sampling strategy. The initial 2011–2012 baseline assessment enrolled 17,708 individuals from 10,257 households across 28 provinces, 150 counties, and 450 communities in China. Follow-up data collection occurred in 2013, 2015, and 2018. As blood biomarker data were solely available for the 2011 and 2015 waves, the 2011 cohort served as the baseline population for this study, with the 2015 data reserved for temporal validation. The participant selection process is illustrated in Fig. 1 . Exclusion criteria were: (1) age under 45 years; (2) self-report of no physician-diagnosed chronic digestive disease in the baseline survey; or (3) missing Center for Epidemiologic Studies Depression Scale (CES-D) scores. After applying these criteria, 3,762 participants were included in the final analysis. This research complied with the ethical standards outlined in the Declaration of Helsinki (2013 revision). Exposure and Outcome The identification of Chronic Digestive System Diseases (CDSD) was based on participant responses to the health status and functioning modules of the CHARLS questionnaire. Specifically, individuals were asked: "Have you ever been diagnosed by a physician with a gastrointestinal disease?" (Within the CHARLS framework, digestive diseases are classified as chronic conditions necessitating medical management, such as gastritis, gastric/duodenal ulcers, inflammatory bowel disease, liver cirrhosis, and functional gastrointestinal disorders; malignancies were excluded). Affirmative responses led to classification as having a gastrointestinal disorder. Trained interviewers administered all surveys using standardized instruments. This method of self-report via structured questionnaires is a well-validated tool for estimating the prevalence of chronic conditions, including CDSD, in middle-aged and older populations and is commonly employed in large-scale epidemiological research 2 – 5 . For analytical purposes, CDSD status was treated as a binary variable (present/absent). Depressive symptoms were evaluated using the 10-item Center for Epidemiologic Studies Depression Scale (CES-D-10), a widely used instrument with established validity for screening depression 6 . Its applicability and sensitivity have been confirmed within older Chinese populations 7 . Each of the 10 items is scored from 0 ("rarely or none of the time") to 3 ("most or all of the time"), yielding a total score between 0 and 30. Higher scores indicate more severe depressive symptomatology. A cut-off score of ≥ 10 was used to define clinically significant depression 8 . For conciseness in this study, the term "depression" refers to the presence of clinically significant depressive symptoms as defined by this threshold 9 , 10 . Based on their CES-D-10 scores, participants with CDSD were subsequently categorized into two groups: CDSD without depression and CDSD with depression. Socio-demographic and Behavioral Characteristics The socio-demographic variables incorporated into the analysis comprised age, sex (male or female), educational attainment (below high school versus high school or higher), marital status (married or other), and residential setting (urban or rural). Behavioral factors encompassed smoking status (never, former, current), alcohol consumption (never, former, current), participation in social activities within the preceding two months (yes or no), daily midday nap duration (in minutes), and nocturnal sleep duration (in hours). Health Status Drawing upon established research frameworks and informed by clinical expertise, a comprehensive array of health measures potentially linked to depressive outcomes was examined. These included physical examination parameters, laboratory findings, and comorbid conditions. Physical and functional indicators consisted of: body mass index (BMI), waist circumference, pulse rate, grip strength, systolic and diastolic blood pressure, standing balance performance, instrumental activities of daily living (IADL) and basic activities of daily living (BADL) 10 , history of falls, history of disability, hearing acuity (poor or good), visual acuity (poor or good), walking speed, and presence of dental element loss (yes or no). Self-rated health, reflecting the individual’s subjective health perception, and overall life satisfaction were each classified as either good or poor. Laboratory-based biomarkers derived from blood tests included: low-density lipoprotein (LDL), high-density lipoprotein cholesterol (HDL-C), uric acid, white blood cell count (WBC), hemoglobin level, platelet count (PLT), blood urea nitrogen (BUN), cystatin C, glycated hemoglobin (HbA1c), C-reactive protein (CRP), triglycerides (TG), total cholesterol (TC), creatinine, fasting blood glucose (FBG), mean corpuscular volume (MCV), and hematocrit 25 . Comorbidities were defined with reference to previous CHARLS-based studies on chronic digestive system diseases and included asthma, cancer, liver disease, kidney disease, dyslipidemia, arthritis, stroke, heart disease, lung disease, diabetes mellitus (DM), and hypertension 2 , 26 . Data Processing and Model Selection The distribution and prevalence of missing data are detailed in Supplementary Fig. 1. Variables exhibiting a missing data rate surpassing 35%-specifically, walking speed and Cystatin C-were omitted from subsequent analyses. Consequently, a final set of 45 variables was retained. Missing values in the remaining dataset were addressed using multiple imputation techniques 27 . To safeguard against model overfitting and to robustly assess the predictive model's generalizability, the overall sample was randomly partitioned into a development cohort (70%) and an independent test cohort (30%) 28 . All subsequent data processing and model development steps were conducted exclusively on the development set. An initial screening of potential predictor variables was performed using univariate logistic regression within the training subset, selecting all variables demonstrating a significance level of P < 0.05. These variables were then subjected to multivariate logistic regression analysis. To refine the feature set further, variables identified as significant through multivariate analysis were intersected with those selected by a Least Absolute Shrinkage and Selection Operator (LASSO) regression procedure. This process yielded a final, robust set of 13 predictor variables. Given that the proportion of individuals with and without the target outcome was approximately balanced within the training set, techniques for addressing class imbalance, such as the Synthetic Minority Over-sampling Technique (SMOTE), were deemed unnecessary. Subsequently, seven distinct machine learning algorithms were implemented to construct predictive models for depression risk: Logistic Regression (LR), Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), eXtreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), and an Artificial Neural Network (ANN). To optimize the predictive performance of each model, a comprehensive Grid Search strategy was employed for hyperparameter tuning. This systematic search aimed to identify the optimal configuration of hyperparameters for each respective algorithm (the resultant optimal parameter sets are catalogued in Supplementary Table 1 ) 29 , 30 . Statistical Analysis All statistical computations and modeling were executed using R software (version 4.5.1) and Python (version 3.12.5). Descriptive statistics for continuous variables are reported as either mean ± standard deviation (with range) or median and interquartile range (IQR). Group comparisons for these variables were conducted using Student's t-test or the non-parametric Wilcoxon rank-sum test, as appropriate based on data distribution. Categorical variables are summarized using frequency counts and percentages, with comparisons between groups performed via the Chi-square test or Fisher's exact test, depending on expected cell frequencies. A two-tailed P-value of less than 0.05 was established as the threshold for statistical significance. Declarations Competing interests The authors declare no competing interests. Ethics statement The studies involving humans were approved by the Biomedical Ethics Review Committee of Peking University (approval number: IRB00001052-11015). All participants in CHARLS provided written informed consent before participation in the original survey. This study was a secondary analysis of de-identified publicly available data and did not involve new collection of human participant data. Funding This work was supported by the XinRui Translational Oncology Research Project (grant number: chmdf2025-xrky05-15). Author Contribution Zixun Huang: Writing—original draft, supervision, project administration. Liangze Ma: Software, methodology, supervision, writing—original draft. Xin Wang: Writing—review and editing, supervision, project administration. Mingheng Liu: Writing—original draft, data curation. Shaopeng Zheng: Investigation. Shugeng Lin: Validation, formal analysis. Yukun Ma: Formal analysis. Qiangzhou Xu: Supervision, investigation, validation, formal analysis, data curation. Limin Ma and Shaobin Chen: Writing—review and editing, data curation, supervision. All authors reviewed and approved the final manuscript. Acknowledgements The authors sincerely thank the China Health and Retirement Longitudinal Study (CHARLS) team for providing access to the data and all survey participants for their valuable contributions to this research. Data Availability Publicly available datasets were analyzed in this study. These data can be found at the China Health and Retirement Longitudinal Study (CHARLS) repository: https://charls.charlsdata.com/. References Bisgaard, T. H., Allin, K. H., Keefer, L., Ananthakrishnan, A. N. & Jess, T. Depression and anxiety in inflammatory bowel disease: epidemiology, mechanisms and treatment. Nat. Rev. Gastroenterol. Hepatol. 19 , 717–726. https://doi.org/10.1038/s41575-022-00634-6 (2022). Guo, J. et al. Longitudinal bidirectional association between gastrointestinal disease and depression symptoms among middle-aged and older adults in China. Arch. Public. Health . 83 , 171. https://doi.org/10.1186/s13690-025-01671-8 (2025). Che, J., Song, Q., Zhao, C., Yuan, Y. & Lyu, X. Associations between changes in frailty status and non-neoplastic digestive system diseases: A cohort study based on the China health and retirement longitudinal study. Exp. Gerontol. 209 , 112861. https://doi.org/10.1016/j.exger.2025.112861 (2025). Chen, D. et al. Effects of indoor air pollution from household solid fuel use on the risk of gastrointestinal and liver diseases in middle aged and elderly adults. Environ. Int. 188 , 108738. https://doi.org/10.1016/j.envint.2024.108738 (2024). Smarr, K. L. & Keefer, A. L. Measures of depression and depressive symptoms: Beck Depression Inventory-II (BDI-II), Center for Epidemiologic Studies Depression Scale (CES-D), Geriatric Depression Scale (GDS), Hospital Anxiety and Depression Scale (HADS), and Patient Health Questionnaire-9 (PHQ-9). Arthritis Care Res. 63 (Suppl 11), S454–466. https://doi.org/10.1002/acr.20556 (2011). Fu, H., Si, L. & Guo, R. What Is the Optimal Cut-Off Point of the 10-Item Center for Epidemiologic Studies Depression Scale for Screening Depression Among Chinese Individuals Aged 45 and Over? An Exploration Using Latent Profile Analysis. Front. Psychiatry . 13 , 820777. https://doi.org/10.3389/fpsyt.2022.820777 (2022). Andresen, E. M., Malmgren, J. A., Carter, W. B. & Patrick, D. L. Screening for depression in well older adults: evaluation of a short form of the CES-D (Center for Epidemiologic Studies Depression Scale). Am. J. Prev. Med. 10 , 77–84 (1994). Chen, H. & Mui, A. C. Factorial validity of the Center for Epidemiologic Studies Depression Scale short form in older population in China. Int. Psychogeriatr. 26 , 49–57. https://doi.org/10.1017/s1041610213001701 (2014). Zhao, X. et al. A machine-learning-derived online prediction model for depression risk in COPD patients: A retrospective cohort study from CHARLS. J. Affect. Disord. 377 , 284–293. https://doi.org/10.1016/j.jad.2025.02.063 (2025). Katz, S. et al. A STANDARDIZED MEASURE OF BIOLOGICAL AND PSYCHOSOCIAL FUNCTION. Jama 185 , 914–919. https://doi.org/10.1001/jama.1963.03060120024016 (1963). Cohen-Mekelburg, S. et al. Loneliness and Depressive Symptoms Are High Among Older Adults With Digestive Disease and Associated With Lower Perceived Health. Clin. Gastroenterol. hepatology: official Clin. Pract. J. Am. Gastroenterological Association . 22 , 621–629e622. https://doi.org/10.1016/j.cgh.2023.08.027 (2024). Mules, T. C. et al. The impact of disease activity on psychological symptoms and quality of life in patients with inflammatory bowel disease-results from the Stress, Anxiety and Depression with Disease Activity (SADD) Study. Aliment. Pharmacol. Ther. 55 , 201–211. https://doi.org/10.1111/apt.16616 (2022). Van Den Houte, M. et al. Predictors of Symptoms Trajectories in Newly Diagnosed Ulcerative Colitis: A 3-Year Follow-up Cohort Study. J. Crohn's colitis . 18 , 1394–1405. https://doi.org/10.1093/ecco-jcc/jjae046 (2024). Zheng, Q. Q., Yang, W. W., He, S. S. & Li, Y. R. Association between sleep duration and depression in adolescents and young adults: a system review of observational studies and a genetic research of Mendelian randomization analysis. Postgrad. Med. J. 101 , 845–853. https://doi.org/10.1093/postmj/qgaf013 (2025). Li, D. R. et al. Regular sleep patterns, not just duration, critical for mental health: association of accelerometer-derived sleep regularity with incident depression and anxiety. Psychol. Med. 55 , e239. https://doi.org/10.1017/s0033291725101281 (2025). Meyer, N. et al. The sleep-circadian interface: A window into mental disorders. Proc. Natl. Acad. Sci. U.S.A. 121 , e2214756121. https://doi.org/10.1073/pnas.2214756121 (2024). Ruan, X. et al. Depression and 24 gastrointestinal diseases: a Mendelian randomization study. Translational psychiatry . 13 , 146. https://doi.org/10.1038/s41398-023-02459-6 (2023). de Feijter, M., Kocevska, D., Ikram, M. A. & Luik, A. I. The bidirectional association of 24-h activity rhythms and sleep with depressive symptoms in middle-aged and elderly persons. Psychol. Med. 53 , 1418–1425. https://doi.org/10.1017/s003329172100297x (2023). Aye, S. et al. Health-related quality of life in subjective cognitive decline and mild cognitive impairment: a longitudinal cohort analysis. Alzheimers Res. Ther. 15 , 200. https://doi.org/10.1186/s13195-023-01344-0 (2023). Xiong, L. Y. et al. Longitudinal relationships between depressive symptoms, functional impairment, and physical activity in later late life. GeroScience 47 , 1061–1073. https://doi.org/10.1007/s11357-024-01282-1 (2025). Abay, R. J. Y., Gold, L. S., Cawthon, P. M. & Andrews, J. S. Lean mass, grip strength, and hospital-associated disability among older adults in Health ABC. Alzheimer's Dement. J. Alzheimer's Assoc. 18 , 1898–1906. https://doi.org/10.1002/alz.12527 (2022). Bellón, D. et al. Associations between muscular strength and mental health in cognitively normal older adults: a cross-sectional study from the AGUEDA trial. Int. J. Clin. health psychology: IJCHP . 24 , 100450. https://doi.org/10.1016/j.ijchp.2024.100450 (2024). Hurst, C. et al. Long-term conditions, multimorbidity, lifestyle factors and change in grip strength over 9 years of follow-up: Findings from 44,315 UK biobank participants. Age ageing . 50 , 2222–2229. https://doi.org/10.1093/ageing/afab195 (2021). Zhao, Y., Hu, Y., Smith, J. P., Strauss, J. & Yang, G. Cohort profile: the China Health and Retirement Longitudinal Study (CHARLS). Int. J. Epidemiol. 43 , 61–68. https://doi.org/10.1093/ije/dys203 (2014). Covinsky, K. E. et al. Loss of independence in activities of daily living in older adults hospitalized with medical illnesses: increased vulnerability with age. J. Am. Geriatr. Soc. 51 , 451–458. https://doi.org/10.1046/j.1532-5415.2003.51152.x (2003). Gao, Y. et al. Depressive Symptoms Trajectories and Chronic Digestive Disease in Chinese Middle-Aged and Older Adults: A Longitudinal Cohort Study. J Prev ( ) (2026).) (2026). (2022). https://doi.org/10.1007/s10935-026-00901-1 Enders, C. K. Missing data: An update on the state of the art. Psychol. Methods . 30 , 322–339. https://doi.org/10.1037/met0000563 (2025). Xu, Y. & Goodacre, R. On Splitting Training and Validation Set: A Comparative Study of Cross-Validation, Bootstrap and Systematic Sampling for Estimating the Generalization Performance of Supervised Learning. J. Anal. Test. 2 , 249–262. https://doi.org/10.1007/s41664-018-0068-2 (2018). Han, J., Gondro, C., Reid, K. & Steibel, J. P. Heuristic hyperparameter optimization of deep learning models for genomic prediction. G3 (Bethesda, Md.) 11 (2021). https://doi.org/10.1093/g3journal/jkab032 Ahanger, A. B. et al. Radiogenomics and machine learning predict oncogenic signaling pathways in glioblastoma. J. translational Med. 23 , 121. https://doi.org/10.1186/s12967-025-06101-5 (2025). Additional Declarations No competing interests reported. Supplementary Files FigureS1.tiff Supplementary Figure 1. Missing proportion of each variable. FigureS2.tif Supplementary Figure 2. Predictive performance of seven different models in training test. FigureS3.tif Supplementary Figure 3. Impact of Each Feature on Model Output. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 04 May, 2026 Reviews received at journal 28 Apr, 2026 Reviews received at journal 26 Apr, 2026 Reviewers agreed at journal 15 Apr, 2026 Reviewers agreed at journal 15 Apr, 2026 Reviewers agreed at journal 09 Apr, 2026 Reviews received at journal 09 Apr, 2026 Reviewers agreed at journal 09 Apr, 2026 Reviewers invited by journal 29 Mar, 2026 Editor invited by journal 27 Mar, 2026 Editor assigned by journal 24 Mar, 2026 Submission checks completed at journal 24 Mar, 2026 First submitted to journal 23 Mar, 2026 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-9205724","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":614327841,"identity":"b0018370-4cc4-4df3-bb6c-81754157151a","order_by":0,"name":"Zixun Huang","email":"","orcid":"","institution":"Cancer Hospital of Shantou University Medical College","correspondingAuthor":false,"prefix":"","firstName":"Zixun","middleName":"","lastName":"Huang","suffix":""},{"id":614327842,"identity":"87048c9c-c2fb-4338-af83-4dac13ae301e","order_by":1,"name":"Liangze Ma","email":"","orcid":"","institution":"The First Affiliated Hospital of Shantou University Medical College","correspondingAuthor":false,"prefix":"","firstName":"Liangze","middleName":"","lastName":"Ma","suffix":""},{"id":614327843,"identity":"295c4353-4c1b-42a1-8898-e630735c732d","order_by":2,"name":"Xin Wang","email":"","orcid":"","institution":"Cancer Hospital of Shantou University Medical College","correspondingAuthor":false,"prefix":"","firstName":"Xin","middleName":"","lastName":"Wang","suffix":""},{"id":614327844,"identity":"da6a1e47-88cb-49dc-9b83-b610d3849415","order_by":3,"name":"Mingheng Liu","email":"","orcid":"","institution":"Cancer Hospital of Shantou University Medical College","correspondingAuthor":false,"prefix":"","firstName":"Mingheng","middleName":"","lastName":"Liu","suffix":""},{"id":614327845,"identity":"c7a2f7ae-c245-4de7-8f70-50ceb31f6d69","order_by":4,"name":"Shaopeng Zheng","email":"","orcid":"","institution":"Cancer Hospital of Shantou University Medical College","correspondingAuthor":false,"prefix":"","firstName":"Shaopeng","middleName":"","lastName":"Zheng","suffix":""},{"id":614327846,"identity":"b3db4492-9856-421d-a94f-d27f38756189","order_by":5,"name":"Shugeng Lin","email":"","orcid":"","institution":"The First Affiliated Hospital of Shantou University Medical College","correspondingAuthor":false,"prefix":"","firstName":"Shugeng","middleName":"","lastName":"Lin","suffix":""},{"id":614327847,"identity":"d86a738a-0986-42ae-924a-d2c2c169f9e0","order_by":6,"name":"Yukun Ma","email":"","orcid":"","institution":"The First Affiliated Hospital of Shantou University Medical College","correspondingAuthor":false,"prefix":"","firstName":"Yukun","middleName":"","lastName":"Ma","suffix":""},{"id":614327848,"identity":"3f7451ba-5f8e-4509-bb78-116ceb930b26","order_by":7,"name":"Qiangzhou Xu","email":"","orcid":"","institution":"Cancer Hospital of Shantou University Medical College","correspondingAuthor":false,"prefix":"","firstName":"Qiangzhou","middleName":"","lastName":"Xu","suffix":""},{"id":614327849,"identity":"b29905c6-c06f-4058-ac36-fd65997bf958","order_by":8,"name":"Limin Ma","email":"","orcid":"","institution":"Cancer Hospital of Shantou University Medical College","correspondingAuthor":false,"prefix":"","firstName":"Limin","middleName":"","lastName":"Ma","suffix":""},{"id":614327850,"identity":"085ce04d-0a82-43d6-8aec-d6e1987c6d20","order_by":9,"name":"Shaobin Chen","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABBElEQVRIiWNgGAWjYDACCSBmbPhnZ9/M//HBxwaQEGPjASK0HEg2YGcwNpzZAOIDucRoYdzAz2AmzAvWwsCAVwv/7OZjD3/uuMNszsyQxmy7w6ZOt/0w0JYam2icltw5lm7Me+YZn2Uzw7HHuWfSJMzOJAK1HEvLbcChxUAix0yasY2ZmeEwY7txbtthCbMDQC2MDYfxaMn/JvmzjRmohplN2hKk5fxDQlpy2CR42w4zbjjMxga0DqjlBgFbJG6kmUnznklLlmzmYTbsbUuT3HYDaEsCHr/wz0h+Jvlzh40dP/8Zxgc/22z4zc6nP3zwocYGpxYcIIE05aNgFIyCUTAK0AAABAxhShGDsj0AAAAASUVORK5CYII=","orcid":"","institution":"Cancer Hospital of Shantou University Medical College","correspondingAuthor":true,"prefix":"","firstName":"Shaobin","middleName":"","lastName":"Chen","suffix":""}],"badges":[],"createdAt":"2026-03-24 02:27:10","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9205724/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9205724/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":106068550,"identity":"d3f7bade-67ee-4ad5-9842-e80bed062edb","added_by":"auto","created_at":"2026-04-03 06:10:42","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":1234988,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eParticipant Screening and Grouping Process for the Depression Risk Prediction Model Study in Gastrointestinal Disease Patients from the CHARLS Cohort.\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"Figure1.png","url":"https://assets-eu.researchsquare.com/files/rs-9205724/v1/c32d8fce214ddb1c2c800d83.png"},{"id":106068499,"identity":"c972d014-698f-40ad-ac30-55af6f2e5f59","added_by":"auto","created_at":"2026-04-03 06:10:30","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":8227545,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eComparison of the predictive performance of seven different prediction models. \u003c/strong\u003e(a) LASSO regression model factor selection:the left dashed line indicates the optimal λvalue (lambda·min), and the right dashed line indicates the λvalue selected within one standard error of the cross-validation error, (b) Variable selection trajectory of the LASSO regression model, (c) ROC curve of the test set, (d) ROC curve of the validation set, (e) Calibration curve of the test set, (f) Calibration curve of the validation set, (g) Decision curve analysis of the test set;(h)Decision curve analysis of the validation set.\u003c/p\u003e","description":"","filename":"Figure2.png","url":"https://assets-eu.researchsquare.com/files/rs-9205724/v1/5dd1da5cfddec2ae34fee4a0.png"},{"id":106068559,"identity":"ef5c4157-9a74-47b7-8464-cae23ba23fe1","added_by":"auto","created_at":"2026-04-03 06:10:48","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":3473953,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eSHAP of the model.\u003c/strong\u003e(a)Feature attribution in SHAP. The horizontal axis represents the SHAP values, and each row corresponds to a feature. Higher feature values are indicated by red dots, while lower feature values are indicated by blue dots. (b)Feature importance ranking plot of the XGBoost model. (c)Interpretability analysis of two independent samples.\u003c/p\u003e","description":"","filename":"Figure3.png","url":"https://assets-eu.researchsquare.com/files/rs-9205724/v1/deae73ef4abe4f371fdfe777.png"},{"id":106094942,"identity":"6d8f6f17-ec36-4788-86fa-0f7001aeb257","added_by":"auto","created_at":"2026-04-03 11:43:41","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":14857437,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9205724/v1/b4763572-f295-4841-8224-db1fe91a9f8b.pdf"},{"id":106068558,"identity":"defd686e-f062-4e6f-8976-665d03aeff8e","added_by":"auto","created_at":"2026-04-03 06:10:48","extension":"tiff","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":11917502,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eSupplementary Figure 1. Missing proportion of each variable.\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"FigureS1.tiff","url":"https://assets-eu.researchsquare.com/files/rs-9205724/v1/0d4920d7937ed859277acfd2.tiff"},{"id":106068549,"identity":"caf3215c-af68-46c7-89d8-fd3eef9a3d85","added_by":"auto","created_at":"2026-04-03 06:10:41","extension":"tif","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":40712354,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eSupplementary Figure 2. Predictive performance of seven different models in training test.\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"FigureS2.tif","url":"https://assets-eu.researchsquare.com/files/rs-9205724/v1/835276b41f4c0c6c9b4db85d.tif"},{"id":106068548,"identity":"04f803cc-89c6-45a5-891d-7872c235d0b2","added_by":"auto","created_at":"2026-04-03 06:10:40","extension":"tif","order_by":3,"title":"","display":"","copyAsset":false,"role":"supplement","size":44417910,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eSupplementary Figure 3. Impact of Each Feature on Model Output.\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"FigureS3.tif","url":"https://assets-eu.researchsquare.com/files/rs-9205724/v1/1f8d96d9435be3cd0e69dca9.tif"}],"financialInterests":"No competing interests reported.","formattedTitle":"A machine-learning-derived online screening tool for depressive symptoms in chronic digestive system diseases patients: A cross- sectional study with temporal validation from CHARLS","fulltext":[{"header":"Introduction","content":"\u003cp\u003eChronic digestive system diseases (CDSD) represent a diverse and complex group of clinical conditions, including reflux esophagitis, non-erosive gastroesophageal reflux disease, Barrett's esophagus, chronic gastritis, irritable bowel syndrome (IBS), Crohn's disease, ulcerative colitis, and liver cirrhosis. These diseases impose a substantial burden on global health. Specifically, in 2019, the global age-standardized prevalence reached 95,582 cases per 100,000 individuals \u003csup\u003e\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e\u003c/sup\u003e, contributing significantly to mortality and disability-adjusted life years (DALYs). In China, the impact of CDSD is particularly severe, with 499.2\u0026nbsp;million cases reported in 2019, leading to 1.557\u0026nbsp;million deaths. Concurrently, depression, a prevalent mental health disorder, is increasingly recognized for its associated health risks. Research indicates that the prevalence of depression is markedly higher among patients with CDSD and is closely linked to poorer clinical outcomes \u003csup\u003e\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eEmerging evidence suggests a bidirectional relationship between CDSD and depression. A recent cohort study demonstrated that individuals with baseline CDSD had a 36% increased risk of developing new-onset depression, whereas those with baseline depression faced a 61% higher risk of developing CDSD \u003csup\u003e\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e\u003c/sup\u003e. While these epidemiological findings underscore a strong clinical association, the underlying biological mechanisms require further investigation. At a microscopic level, CDSD may directly influence the psychopathological processes of depression via the gut-brain axis, with proposed mechanisms involving oxidative stress and inflammatory pathways \u003csup\u003e\u003cspan additionalcitationids=\"CR5\" citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eGiven these compelling clinical and mechanistic interactions, assessing and predicting the risk of depression in patients with CDSD holds significant importance for informing clinical treatment strategies and enhancing patient prognosis.\u003c/p\u003e \u003cp\u003eDespite increasing acknowledgment of the connection between Chronic Digestive System Diseases (CDSD) and depression \u003csup\u003e\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e,\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e,\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e\u003c/sup\u003e, a notable research gap remains: the development of predictive models for depression risk specifically in CDSD patients. Prior studies, often reliant on traditional regression models, may be insufficient for capturing the complex, non-linear relationships characteristic of this association. This is particularly relevant within the context of a globally aging population, where multiple health factors intersect. Machine learning (ML) presents a robust alternative, capable of autonomously identifying complex patterns from multidimensional data\u0026mdash;including demographic, clinical, and patient-reported outcomes\u0026mdash;without relying on pre-specified parameters. Consequently, developing an interpretable and generalizable ML model to predict depression in CDSD patients is essential for optimizing clinical decision-making and improving patient management \u003csup\u003e\u003cspan additionalcitationids=\"CR9\" citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eThis study employs longitudinal cohort data from the China Health and Retirement Longitudinal Study (CHARLS). By leveraging the extensive dataset within the CHARLS database, it aims to identify and predict characteristic variables associated with depression and to investigate the relationship between CDSD and the onset of depression among middle-aged and older adults.\u003c/p\u003e"},{"header":"Results","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e \u003ch2\u003ePatient Characteristics\u003c/h2\u003e \u003cp\u003eThe 2011 CHARLS database included a total of 17,780 respondents,among whom 3,762 met the inclusion criteria for chronic digestive diseases. Of these eligible individuals,1,900 (50.5%) exhibited depressive symptoms. The mean age of the overall cohort was 59.01\u0026thinsp;\u0026plusmn;\u0026thinsp;9.31 years, and 1,676 (44.55%)were male. As shown in Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e, significant differences were observed between participants with and without depressive symptoms in terms of sociodemographic characteristics, physical examination findings, laboratory test results, and comorbidities. Furthermore, no significant differences in variable distributions were found between the training set and the testing set (\u003cb\u003eSupplementary Table\u0026nbsp;2\u003c/b\u003e). The baseline characteristics of the Temporal Validation set are presented in \u003cb\u003eSupplementary Table\u0026nbsp;3\u003c/b\u003e, which included 778 patients, of whom 366 had depressive symptoms.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eComparison of Baseline Data Between Depressive and Non-depressive Groups in the Training and Testing set.\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"7\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eCharacteristic\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eTraining set(N\u0026thinsp;=\u0026thinsp;2,634)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/th\u003e \u003cth align=\"left\" colspan=\"2\" nameend=\"c6\" namest=\"c5\"\u003e \u003cp\u003eTesting set(N\u0026thinsp;=\u0026thinsp;1,128)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/th\u003e \u003c/tr\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eNon-depressive symptoms\u003c/p\u003e \u003cp\u003e(n\u0026thinsp;=\u0026thinsp;1,304)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eIncident depressive symptoms\u003c/p\u003e \u003cp\u003e(n\u0026thinsp;=\u0026thinsp;1,330)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u003cem\u003ep\u003c/em\u003e value\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003eNon-depressive symptoms\u003c/p\u003e \u003cp\u003e(n\u0026thinsp;=\u0026thinsp;558)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c6\"\u003e \u003cp\u003eIncident depressive symptoms\u003c/p\u003e \u003cp\u003e(n\u0026thinsp;=\u0026thinsp;570)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u003cem\u003ep\u003c/em\u003e value\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eGender ,n(%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eFemale\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e617(47.32%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e849(63.83%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e244(43.73%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e376(65.96%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMale\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e687(52.68%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e481(36.17%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e314(56.27%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e194(34.04%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMarriage status ,n(%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMarried\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1,098(84.20%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1,038(78.05%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e477(85.48%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e445(78.07%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eOther\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e206(15.80%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e292(21.95%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e81(14.52%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e125(21.93%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eEducation ,n(%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLess than high school\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1,135(87.04%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1,259(94.66%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e478(85.66%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e538(94.39%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHigh school and above\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e169(12.96%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e71(5.34%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e80(14.34%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e32(5.61%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eResidence ,n(%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.003\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eUrban\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e527(40.41%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e382(28.72%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e217(38.89%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e173(30.35%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRural\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e777(59.59%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e948(71.28%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e341(61.11%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e397(69.65%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLife assessment ,n(%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNot good\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e106(8.13%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e339(25.49%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e58(10.39%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e144(25.26%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eGood\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1,198(91.87%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e991(74.51%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e500(89.61%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e426(74.74%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHealth assessment ,n(%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNot good\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e350(26.84%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e764(57.44%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e149(26.70%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e344(60.35%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eGood\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e954(73.16%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e566(42.56%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e409(73.30%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e226(39.65%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSocial activity ,n(%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.029\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.053\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e677(51.92%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e747(56.17%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e300(53.76%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e339(59.47%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e627(48.08%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e583(43.83%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e258(46.24%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e231(40.53%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eStanding balance ,n(%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e248(19.02%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e420(31.58%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e101(18.10%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e162(28.42%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1,056(80.98%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e910(68.42%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e457(81.90%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e408(71.58%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eFalldown ,n(%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1,102(84.51%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e969(72.86%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e495(88.71%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e419(73.51%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e202(15.49%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e361(27.14%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e63(11.29%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e151(26.49%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDisability ,n(%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1,095(83.97%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e957(71.95%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e473(84.77%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e410(71.93%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e209(16.03%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e373(28.05%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e85(15.23%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e160(28.07%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHearing ,n(%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1,132(86.81%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1,043(78.42%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e500(89.61%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e428(75.09%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e172(13.19%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e287(21.58%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e58(10.39%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e142(24.91%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTeeth loss ,n(%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.004\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1,210(92.79%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1,182(88.87%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e519(93.01%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e501(87.89%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e94(7.21%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e148(11.13%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e39(6.99%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e69(12.11%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAsthma ,n(%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.002\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1,255(96.24%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1,225(92.11%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e537(96.24%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e523(91.75%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e49(3.76%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e105(7.89%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e21(3.76%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e47(8.25%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCancer ,n(%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.078\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.587\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1,291(99.00%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1,306(98.20%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e553(99.10%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e563(98.77%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e13(1.00%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e24(1.80%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e5(0.90%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e7(1.23%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLiver disease, n(%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.184\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1,229(94.25%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1,204(90.53%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e526(94.27%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e526(92.28%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e75(5.75%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e126(9.47%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e32(5.73%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e44(7.72%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eKidney disease, n(%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.010\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1,212(92.94%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1,124(84.51%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e508(91.04%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e491(86.14%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e92(7.06%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e206(15.49%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e50(8.96%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e79(13.86%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDyslipid, n(%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.055\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.012\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1,156(88.65%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1,146(86.17%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e500(89.61%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e482(84.56%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e148(11.35%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e184(13.83%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e58(10.39%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e88(15.44%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eArthritis ,n(%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e761(58.36%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e491(36.92%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e317(56.81%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e242(42.46%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e543(41.64%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e839(63.08%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e241(43.19%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e328(57.54%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eStroke, n(%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.004\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1,288(98.77%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1,279(96.17%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e549(98.39%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e544(95.44%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e16(1.23%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e51(3.83%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e9(1.61%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e26(4.56%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHeart disease, n(%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.003\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1,125(86.27%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1,015(76.32%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e466(83.51%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e435(76.32%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e179(13.73%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e315(23.68%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e92(16.49%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e135(23.68%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLung disease, n(%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.008\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1,147(87.96%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1,044(78.50%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e487(87.28%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e465(81.58%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e157(12.04%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e286(21.50%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e71(12.72%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e105(18.42%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eEyesight, n(%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNor\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e880(67.48%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e613(46.09%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e383(68.64%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e277(48.60%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e424(32.52%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e717(53.91%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e175(31.36%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e293(51.40%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBADL, n(%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1,129(86.58%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e876(65.86%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e488(87.46%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e371(65.09%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e175(13.42%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e454(34.14%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e70(12.54%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e199(34.91%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eIADL, n(%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1,100(84.36%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e785(59.02%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e478(85.66%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e328(57.54%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e204(15.64%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e545(40.98%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e80(14.34%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e242(42.46%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDM ,n(%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.069\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.959\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1,157(88.73%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1,149(86.39%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e484(86.74%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e495(86.84%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e147(11.27%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e181(13.61%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e74(13.26%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e75(13.16%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHypertension, n(%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.037\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.161\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e832(63.80%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e796(59.85%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e367(65.77%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e352(61.75%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e472(36.20%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e534(40.15%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e191(34.23%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e218(38.25%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSmoking ,n(%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e724(55.52%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e880(66.17%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e305(54.66%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e393(68.95%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eUsed to smoke\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e177(13.57%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e129(9.70%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e74(13.26%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e49(8.60%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSmoking now\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e403(30.90%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e321(24.14%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e179(32.08%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e128(22.46%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDrinking, n(%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e715(54.83%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e838(63.01%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e313(56.09%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e380(66.67%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eUsed to drink\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e127(9.74%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e135(10.15%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e55(9.86%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e64(11.23%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDrinking now\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e462(35.43%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e357(26.84%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e190(34.05%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e126(22.11%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAge, Mean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e58.18\u0026thinsp;\u0026plusmn;\u0026thinsp;9.08\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e59.92\u0026thinsp;\u0026plusmn;\u0026thinsp;9.62\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e57.75\u0026thinsp;\u0026plusmn;\u0026thinsp;8.88\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e60.02\u0026thinsp;\u0026plusmn;\u0026thinsp;9.20\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSleep nap, Median (IQR)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e32.03\u0026thinsp;\u0026plusmn;\u0026thinsp;40.34\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e27.92\u0026thinsp;\u0026plusmn;\u0026thinsp;40.05\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.009\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e31.95\u0026thinsp;\u0026plusmn;\u0026thinsp;41.09\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e28.04\u0026thinsp;\u0026plusmn;\u0026thinsp;38.82\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.101\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSleep night, Median (IQR)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e6.50\u0026thinsp;\u0026plusmn;\u0026thinsp;1.67\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e5.38\u0026thinsp;\u0026plusmn;\u0026thinsp;2.05\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e6.50\u0026thinsp;\u0026plusmn;\u0026thinsp;1.69\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e5.51\u0026thinsp;\u0026plusmn;\u0026thinsp;2.08\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBMI, mean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e23.26\u0026thinsp;\u0026plusmn;\u0026thinsp;3.85\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e22.86\u0026thinsp;\u0026plusmn;\u0026thinsp;3.81\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.007\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e23.15\u0026thinsp;\u0026plusmn;\u0026thinsp;3.66\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e22.75\u0026thinsp;\u0026plusmn;\u0026thinsp;3.78\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.078\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eWaist, mean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e84.34\u0026thinsp;\u0026plusmn;\u0026thinsp;9.63\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e83.59\u0026thinsp;\u0026plusmn;\u0026thinsp;10.05\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.052\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e84.38\u0026thinsp;\u0026plusmn;\u0026thinsp;9.81\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e83.22\u0026thinsp;\u0026plusmn;\u0026thinsp;10.13\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.050\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePulse, mean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e71.28\u0026thinsp;\u0026plusmn;\u0026thinsp;9.85\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e71.48\u0026thinsp;\u0026plusmn;\u0026thinsp;10.24\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.617\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e71.93\u0026thinsp;\u0026plusmn;\u0026thinsp;10.16\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e71.85\u0026thinsp;\u0026plusmn;\u0026thinsp;10.19\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.894\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLDL, mean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e115.33\u0026thinsp;\u0026plusmn;\u0026thinsp;32.95\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e115.67\u0026thinsp;\u0026plusmn;\u0026thinsp;33.48\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.789\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e112.77\u0026thinsp;\u0026plusmn;\u0026thinsp;33.13\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e115.82\u0026thinsp;\u0026plusmn;\u0026thinsp;32.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.116\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHDL-C, mean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e50.90\u0026thinsp;\u0026plusmn;\u0026thinsp;14.90\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e52.31\u0026thinsp;\u0026plusmn;\u0026thinsp;14.90\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.015\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e50.49\u0026thinsp;\u0026plusmn;\u0026thinsp;14.63\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e52.35\u0026thinsp;\u0026plusmn;\u0026thinsp;15.08\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.036\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eUric acid, mean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e4.44\u0026thinsp;\u0026plusmn;\u0026thinsp;1.11\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e4.24\u0026thinsp;\u0026plusmn;\u0026thinsp;1.10\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e4.46\u0026thinsp;\u0026plusmn;\u0026thinsp;1.09\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e4.11\u0026thinsp;\u0026plusmn;\u0026thinsp;1.09\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eWBC, mean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e6.11\u0026thinsp;\u0026plusmn;\u0026thinsp;1.66\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e6.08\u0026thinsp;\u0026plusmn;\u0026thinsp;1.73\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.730\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e6.09\u0026thinsp;\u0026plusmn;\u0026thinsp;1.65\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e6.00\u0026thinsp;\u0026plusmn;\u0026thinsp;1.66\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.377\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHemoglobin, mean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e14.30\u0026thinsp;\u0026plusmn;\u0026thinsp;1.90\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e13.93\u0026thinsp;\u0026plusmn;\u0026thinsp;1.86\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e14.34\u0026thinsp;\u0026plusmn;\u0026thinsp;1.89\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e13.85\u0026thinsp;\u0026plusmn;\u0026thinsp;1.84\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePLT, mean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e202.57\u0026thinsp;\u0026plusmn;\u0026thinsp;64.59\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e208.32\u0026thinsp;\u0026plusmn;\u0026thinsp;67.33\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.026\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e205.38\u0026thinsp;\u0026plusmn;\u0026thinsp;64.66\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e208.04\u0026thinsp;\u0026plusmn;\u0026thinsp;65.68\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.492\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBUN, mean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e15.58\u0026thinsp;\u0026plusmn;\u0026thinsp;4.16\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e15.54\u0026thinsp;\u0026plusmn;\u0026thinsp;4.26\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.803\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e15.81\u0026thinsp;\u0026plusmn;\u0026thinsp;4.42\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e15.85\u0026thinsp;\u0026plusmn;\u0026thinsp;4.36\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.882\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHbA1c, mean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e5.16\u0026thinsp;\u0026plusmn;\u0026thinsp;0.46\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e5.16\u0026thinsp;\u0026plusmn;\u0026thinsp;0.48\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.898\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e5.16\u0026thinsp;\u0026plusmn;\u0026thinsp;0.48\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e5.18\u0026thinsp;\u0026plusmn;\u0026thinsp;0.48\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.603\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCRP, mean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1.70\u0026thinsp;\u0026plusmn;\u0026thinsp;2.30\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1.90\u0026thinsp;\u0026plusmn;\u0026thinsp;2.69\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.043\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e1.66\u0026thinsp;\u0026plusmn;\u0026thinsp;2.28\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e1.93\u0026thinsp;\u0026plusmn;\u0026thinsp;2.64\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.069\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTG, mean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e131.23\u0026thinsp;\u0026plusmn;\u0026thinsp;81.33\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e126.23\u0026thinsp;\u0026plusmn;\u0026thinsp;76.06\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.103\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e133.97\u0026thinsp;\u0026plusmn;\u0026thinsp;83.63\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e133.15\u0026thinsp;\u0026plusmn;\u0026thinsp;82.13\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.868\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTC, mean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e192.73\u0026thinsp;\u0026plusmn;\u0026thinsp;36.69\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e192.66\u0026thinsp;\u0026plusmn;\u0026thinsp;37.03\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.961\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e189.78\u0026thinsp;\u0026plusmn;\u0026thinsp;36.41\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e194.54\u0026thinsp;\u0026plusmn;\u0026thinsp;36.51\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.029\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCreatinine, mean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.79\u0026thinsp;\u0026plusmn;\u0026thinsp;0.18\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.76\u0026thinsp;\u0026plusmn;\u0026thinsp;0.17\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.79\u0026thinsp;\u0026plusmn;\u0026thinsp;0.19\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.75\u0026thinsp;\u0026plusmn;\u0026thinsp;0.17\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eFBG, mean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e105.19\u0026thinsp;\u0026plusmn;\u0026thinsp;20.42\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e104.37\u0026thinsp;\u0026plusmn;\u0026thinsp;18.63\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.281\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e105.14\u0026thinsp;\u0026plusmn;\u0026thinsp;20.93\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e104.62\u0026thinsp;\u0026plusmn;\u0026thinsp;18.82\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.660\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMCV, mean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e90.95\u0026thinsp;\u0026plusmn;\u0026thinsp;7.80\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e90.32\u0026thinsp;\u0026plusmn;\u0026thinsp;8.29\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.045\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e91.33\u0026thinsp;\u0026plusmn;\u0026thinsp;7.82\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e89.37\u0026thinsp;\u0026plusmn;\u0026thinsp;8.44\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHematocrit, mean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e41.45\u0026thinsp;\u0026plusmn;\u0026thinsp;5.89\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e40.54\u0026thinsp;\u0026plusmn;\u0026thinsp;5.80\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e41.71\u0026thinsp;\u0026plusmn;\u0026thinsp;5.53\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e40.22\u0026thinsp;\u0026plusmn;\u0026thinsp;5.83\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eGrip strength, mean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e32.35\u0026thinsp;\u0026plusmn;\u0026thinsp;10.24\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e27.01\u0026thinsp;\u0026plusmn;\u0026thinsp;9.76\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e32.91\u0026thinsp;\u0026plusmn;\u0026thinsp;10.09\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e26.73\u0026thinsp;\u0026plusmn;\u0026thinsp;9.18\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSBP, mean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e128.19\u0026thinsp;\u0026plusmn;\u0026thinsp;20.70\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e128.33\u0026thinsp;\u0026plusmn;\u0026thinsp;21.14\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.859\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e126.98\u0026thinsp;\u0026plusmn;\u0026thinsp;20.03\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e128.62\u0026thinsp;\u0026plusmn;\u0026thinsp;20.90\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.178\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDBP, mean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e75.27\u0026thinsp;\u0026plusmn;\u0026thinsp;11.96\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e74.11\u0026thinsp;\u0026plusmn;\u0026thinsp;11.68\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.012\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e74.56\u0026thinsp;\u0026plusmn;\u0026thinsp;11.22\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e74.49\u0026thinsp;\u0026plusmn;\u0026thinsp;11.83\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.923\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003ctfoot\u003e \u003ctr\u003e\u003ctd colspan=\"7\"\u003e\u003cb\u003eNote\u003c/b\u003e: CHARLS, China Health and Retirement Longitudinal Study; CDSD, chronic digestive system diseases; CES-D-10, 10-item Center for Epidemiologic Studies Depression Scale; BADL, Basic Activities of Daily Living; IADL, Instrumental Activities of Daily Living; LDL, low-density lipoprotein; HDL-C, high-density lipoprotein cholesterol; WBC, white blood cell count; PLT, platelet count; BUN, blood urea nitrogen; HbA1c, glycated hemoglobin A1c; CRP, C-reactive protein; TG, triglycerides; TC, total cholesterol; FBG, fasting blood glucose; MCV, mean corpuscular volume; SBP, systolic blood pressure; DBP, diastolic blood pressure. The study population included participants with baseline CDSD from CHARLS 2011, who were randomly divided into a training set (70%) and a testing set (30%). Depressive symptoms were defined as a CES-D-10 score\u0026thinsp;\u0026ge;\u0026thinsp;10, and non-depressive symptoms were defined as a CES-D-10 score\u0026thinsp;\u0026lt;\u0026thinsp;10. Missing data in retained variables were handled using multiple imputation before model development. Continuous variables are presented as mean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD, and categorical variables are presented as n (%). P values were calculated using Student\u0026rsquo;s t-test or the Wilcoxon rank-sum test for continuous variables, and the chi-square test or Fisher\u0026rsquo;s exact test for categorical variables, as appropriate.\u003c/td\u003e\u003c/tr\u003e \u003c/tfoot\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003c/div\u003e\n\u003ch3\u003eVariable Selection and model performance comparison\u003c/h3\u003e\n\u003cp\u003eIn the univariate analysis of the development set, a total of 39 variables (Age, Sleep_nap, Sleep_night, BMI, HDL_C, Uric_acid, Hemoglobin, PLT, CRP, Creatinine, MCV, Hematocrit, Grip_strength, DBP, Gender, Marriage, Education, Residence, Life_assessment, Health_assessment, Social_activity, Standing_balance, Falldown, Disability, Hearing, Teeth_loss, Asthma, Liver_disease, Kidney_disease, Arthritis,Stroke, Heart_disease, Lung_disease, Eyesight, BADL, IADL, Hypertension, Smoking, Drinking) exhibited a \u003cem\u003eP-value\u003c/em\u003e of less than 0.05. These variables were subsequently subjected to multivariate regression analysis,from which 15 variables were selected (\u003cb\u003eSupplementary Table\u0026nbsp;4\u003c/b\u003e).Concurrently, LASSO regression analysis was performed. Two vertical dashed lines correspond to the lambda values selected by the minimum mean squared error criterion (left line, λ\u0026thinsp;=\u0026thinsp;0.0060) and the one-standard-error rule (right line, λ\u0026thinsp;=\u0026thinsp;0.0241), respectively. Ten-fold cross-validation was also conducted (Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e2\u003c/span\u003eB). Finally, the intersection of variables selected by both methods was taken, resulting in the final selection of 13 features: Education, Residence, Life assessment, Health assessment, Falldown, Disability, Kidney disease, Arthritis, Heart disease, Eyesight, IADL, Sleep night, and Grip strength.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eSeven machine learning algorithms were employed to predict the occurrence of depression in patients with CDSD. The performance of these models was evaluated using the Receiver Operating Characteristic (ROC)curve, Precision-Recall (PR)curve, calibration curve, Decision Curve Analysis (DCA), sensitivity, specificity, and F1 score. The specific performance metrics are presented in Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e. In predicting depression outcomes in the test set,the XGBoost model demonstrated the most robust predictive performance. Its Area Under the ROC Curve (AUROC) was 0.793 (95%CI:0.767\u0026ndash;0.816), with an accuracy of 0.724 sensitivity of 0.714 precision of 0.733, specificity of 0.735, and an F1 score of 0.724. Subsequent calibration curve results indicated that the trends for the temporal validation set and the test set were largely consistent (Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e2\u003c/span\u003eE,F). The XGBoost model also exhibited high efficacy in the validation set,with an AUROC of 0.758 (95%CI:0.725\u0026ndash;0.790), accuracy of 0.690, sensitivity of 0.743, precision of 0.649,specificity of 0.643, and an F1 score of 0.693 (Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e).\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab2\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eDetailed performance metrics of various machine learning models in predicting depression risk in CDSD patients within the testing and validation sets.\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"10\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c8\" colnum=\"8\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c9\" colnum=\"9\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c10\" colnum=\"10\"\u003e\u003c/div\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eModel\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eAUC\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e95%CI Lower\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e95%CI Upper\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eAccuracy\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003ePrecision\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003eSensitivity\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003eSpecificity\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003eF1 Score\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"6\" rowspan=\"7\"\u003e \u003cp\u003eTesting set\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eLogistic\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.790\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.763\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.815\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0.717\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.725\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e0.711\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e0.724\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e0.717\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eDecision Tree\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.746\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.717\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.773\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0.691\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.684\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e0.721\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e0.659\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e0.702\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eRandom Forest\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.785\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.757\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.810\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0.714\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.720\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e0.709\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e0.719\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e0.714\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eXGBoost\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.793\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.767\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.816\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0.724\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.733\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e0.714\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e0.735\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e0.724\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eLightGBM\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.779\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.751\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.803\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0.700\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.709\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e0.691\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e0.710\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e0.700\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSVM\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.793\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.766\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.818\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0.715\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.723\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e0.709\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e0.722\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e0.716\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eANN\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.790\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.764\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.816\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0.717\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.731\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e0.696\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e0.738\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e0.713\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"6\" rowspan=\"7\"\u003e \u003cp\u003eValidation set\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eLogistic\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.777\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.742\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.809\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0.693\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.651\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e0.749\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e0.643\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e0.696\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eDecision Tree\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.713\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.677\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.749\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0.657\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.615\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e0.724\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e0.597\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e0.665\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eRandom Forest\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.757\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.732\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.800\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0.695\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.649\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e0.768\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e0.631\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e0.703\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eXGBoost\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.758\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.725\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.790\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0.690\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.649\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e0.743\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e0.643\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e0.693\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eLightGBM\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.799\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.713\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.782\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0.679\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.642\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e0.716\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e0.646\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e0.677\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSVM\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.768\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.744\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.811\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0.703\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.662\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e0.754\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e0.658\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e0.705\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eANN\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.776\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.741\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.807\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0.699\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.656\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e0.760\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e0.646\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e0.704\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e\u003cp\u003e\u003cstrong\u003eNote:\u0026nbsp;\u003c/strong\u003eCDSD, chronic digestive system diseases; AUC, area under the receiver operating characteristic curve; CI, confidence interval; SVM, support vector machine; ANN, artificial neural network; XGBoost, extreme gradient boosting; LightGBM, light gradient boosting machine. Model performance was evaluated in the testing and validation sets using discrimination and classification metrics, including AUC, accuracy, precision, sensitivity, specificity, and F1 score. AUC values are presented with 95% confidence intervals. Higher AUC values indicate better discriminative ability, whereas higher values for accuracy, precision, sensitivity, specificity, and F1 score indicate better overall classification performance.\u003c/p\u003e\n\u003cp\u003e\u003cbr\u003e\u003c/p\u003e\n\u003ch3\u003eInterpretability and application of the model\u003c/h3\u003e\n\u003cp\u003eSHAP values can provide deeper insights into how XGBoost models make predictions. Figure\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e3\u003c/span\u003eA is a SHAP beeswarm plot, illustrating the impact of each feature on the target variable, depression. A higher SHAP value on the x-axis indicates that the feature is more likely to increase the likelihood of depression. The color gradient from red to blue represents the magnitude of the feature values, with red indicating high feature values and blue indicating lower feature values. Longer nighttime sleep duration, higher self-rated health, greater life satisfaction,and higher grip strength all contribute to reducing the risk of depression. Conversely, factors such as Instrumental Activities of Daily Living (IADL)impairment, arthritis, poor vision, falls, rural residence, kidney disease, heart disease, disability, and low education level all increase the risk of depression. \u003cb\u003eSupplementary Fig.\u0026nbsp;3\u003c/b\u003e uses SHAP value visualization techniques to detail the contribution of each feature to the model\u0026rsquo;s prediction results. Figure\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e3\u003c/span\u003eB lists the importance ranking of variables in the model, with nighttime sleep duration, self-rated health, life satisfaction, IADL, and grip strength being the top five most important variables. The waterfall plot in Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e3\u003c/span\u003eC demonstrates how each feature drives the model\u0026rsquo;s baseline value toward the final predicted value. Red features indicate positive contributions, while blue features indicate negative influences. Interestingly, when an individual\u0026rsquo;s sleep duration was 8 hours, the SHAP value was +\u0026thinsp;0.06, indicating an increased predicted probability of depressive symptoms. This suggests that the association between sleep duration and depressive symptoms in patients with CDSD may be nonlinear.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eUsing Streamlit, we built a deployable web platform that achieved the visualization and basic application of the prediction model, while hosting the source code on GitHub. This platform has now become an online tool for assessing depression risk in patients with chronic gastrointestinal diseases. Users can simply input the patient\u0026rsquo;s clinical characteristics into specific text boxes on the webpage to conveniently obtain corresponding prediction results.\u003c/p\u003e"},{"header":"Discussion","content":"\u003cp\u003eIn China, the accelerated aging of the population and shifts in lifestyle patterns have contributed to a rising annual prevalence of Chronic Digestive System Diseases (CDSD), presenting a significant public health challenge. However, due to limited public awareness regarding mental health and an uneven distribution of healthcare resources, many patients do not receive timely diagnosis or effective treatment. Research indicates that individuals with chronic digestive system diseases face a substantially higher risk of developing depression compared to the general population \u003csup\u003e\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e\u003c/sup\u003e. This increased risk is likely linked to factors such as chronic pain, persistent inflammatory states, neuroendocrine dysregulation, and psychological stress \u003csup\u003e\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e\u003c/sup\u003e. Conversely, depression can worsen the symptoms of CDSD, establishing a vicious cycle that adversely affects patient prognosis and quality of life \u003csup\u003e\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e\u003c/sup\u003e. To address this issue, our study analyzed data from 3,762 middle-aged and elderly CDSD patients from the China Health and Retirement Longitudinal Study (CHARLS). Key predictive variables were identified using multivariate regression and LASSO regression analysis. An XGBoost model was subsequently employed to develop a clinical prediction model, complemented by an online prediction tool. This model aims to facilitate the early identification of CDSD patients at high risk for depression, allowing for personalized interventions to enhance mental health and quality of life.\u003c/p\u003e \u003cp\u003eAmong the 13 key characteristic variables ultimately identified, the top five in terms of predictive weight were: nighttime sleep duration, self-rated health, life satisfaction, Instrumental Activities of Daily Living (IADL), and grip strength. The circadian rhythm system is a well-established primary regulator of metabolism, precisely controlling the temporal patterns of hormone secretion, enzyme activity, and energy intake through its influence on clock gene expression. A growing body of evidence suggests that insufficient nighttime sleep duration is strongly associated with an elevated risk of depression \u003csup\u003e\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e,\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e\u003c/sup\u003e, potentially due to the impact of sleep quality on emotional regulation \u003csup\u003e\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e\u003c/sup\u003e. Disruption of this finely tuned regulatory mechanism can trap the body in a vicious cycle where CDSD and depression mutually reinforce each other \u003csup\u003e\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e,\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e\u003c/sup\u003e. Subjective well-being encompasses an individual's overall evaluation and perception of life satisfaction and self-rated health. Due to symptoms such as low mood, anhedonia, and impaired cognitive function, patients with depression often struggle to accurately assess these subjective indicators \u003csup\u003e\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e\u003c/sup\u003e. This distorted perception of well-being and self-rated health can intensify feelings of distress and helplessness, potentially contributing to the development or exacerbation of CDSD. IADL measures an individual's capacity to perform essential self-care tasks in daily life, with studies demonstrating a significant decline in this ability among depressed patients. Grip strength serves as an objective marker of physical functional status; previous research has consistently shown that lower grip strength correlates with a higher risk of depression, a finding supported by multiple studies \u003csup\u003e\u003cspan additionalcitationids=\"CR21\" citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e\u003c/sup\u003e. Residence in rural areas may be linked to relatively limited access to medical resources and weaker social support networks, factors that can increase psychological burden. Lower educational attainment might indicate a lack of health literacy and coping strategies for psychological issues, rendering individuals more vulnerable to depression. Conditions such as arthritis, poor vision, falls, disability, kidney disease, and heart disease may promote depressive symptoms by restricting patients' daily activities, increasing physical discomfort and dependence, and limiting social engagement \u003csup\u003e\u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eWe employed a hybrid feature selection strategy that integrated LASSO regression with a multivariate regression model. Predictive modeling was conducted using logistic regression, decision tree, Random Forest, XGBoost, LightGBM, support vector machine (SVM), and artificial neural network (ANN) models, thereby ensuring diversity and robustness in model construction. Through a multidimensional evaluation framework, comprehensive metrics-including the area under the curve (AUC), accuracy, sensitivity, specificity, precision, and F1-score-were adopted. These indicators collectively assessed the predictive efficacy of the models from multiple perspectives, improving the reliability of the research findings. However, in our study, the AUC of XGBoost in the testing set was not substantially higher than that of the other models. Nevertheless, because it achieved the highest F1 score, we selected it as the best-performing model. In the temporal validation set, however, XGBoost performed comparably to simpler models.\u003c/p\u003e \u003cp\u003eThis study provides a new perspective on predicting depression outcomes among patients with CDSD. Temporal cohort validation was performed, which enhances the generalizability and representativeness of the findings. The model improves diagnostic and therapeutic efficiency, as the selected predictors are readily accessible in routine clinical practice. Furthermore, it maintains clinical interpretability, allowing healthcare providers to allocate limited resources more effectively to high-risk patients and thereby facilitate more precise and targeted care.\u003c/p\u003e \u003cp\u003eNevertheless, several limitations should be acknowledged. The model was developed retrospectively using a single wave of data from the China Health and Retirement Longitudinal Study (CHARLS), which lacks long-term patient follow-up, making it difficult to dynamically monitor disease progression. Additionally, depression symptoms were assessed based on self-reported CHARLS data, which may introduce reporting bias. Meanwhile, the CHARLS database used a standardized self-reported questionnaire for chronic diseases and did not provide detailed information on disease subtypes or indicators of disease activity/severity, which further limited our ability to conduct stratified analyses of related factors.\u003c/p\u003e"},{"header":"Conclusion","content":"\u003cp\u003eIn this study, seven machine learning models were developed to identify factors predicting depression among patients with CDSD using the CHARLS database. By deploying an online prediction tool and integrating it into clinical practice, healthcare providers can more effectively allocate limited resources to high-risk patients, thereby ensuring more precise and targeted care.\u003c/p\u003e \u003cdiv id=\"Sec8\" class=\"Section2\"\u003e \u003cdiv id=\"Sec9\" class=\"Section3\"\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e \u003c/div\u003e"},{"header":"Methods","content":"\u003ch2\u003eData source\u003c/h2\u003e\u003cp\u003eThis analysis utilized data from the 2011 national baseline wave of the China Health and Retirement Longitudinal Study (CHARLS), a publicly accessible database (available at: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttp://charls.pku.edu.cn/\u003c/span\u003e\u003cspan class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e). CHARLS is a nationally representative longitudinal survey focusing on the Chinese population aged 45 years and older. The study's comprehensive methodology has been described in detail elsewhere\u003csup\u003e\u003cspan class=\"CitationRef\"\u003e24\u003c/span\u003e\u003c/sup\u003e. In summary, the survey employed a multistage, stratified, probability-proportional-to-size sampling strategy. The initial 2011–2012 baseline assessment enrolled 17,708 individuals from 10,257 households across 28 provinces, 150 counties, and 450 communities in China. Follow-up data collection occurred in 2013, 2015, and 2018. As blood biomarker data were solely available for the 2011 and 2015 waves, the 2011 cohort served as the baseline population for this study, with the 2015 data reserved for temporal validation. The participant selection process is illustrated in Fig.\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e1\u003c/span\u003e. Exclusion criteria were: (1) age under 45 years; (2) self-report of no physician-diagnosed chronic digestive disease in the baseline survey; or (3) missing Center for Epidemiologic Studies Depression Scale (CES-D) scores. After applying these criteria, 3,762 participants were included in the final analysis. This research complied with the ethical standards outlined in the Declaration of Helsinki (2013 revision).\u003c/p\u003e\n\u003ch3\u003eExposure and Outcome\u003c/h3\u003e\n\u003cp\u003eThe identification of Chronic Digestive System Diseases (CDSD) was based on participant responses to the health status and functioning modules of the CHARLS questionnaire. Specifically, individuals were asked: \"Have you ever been diagnosed by a physician with a gastrointestinal disease?\" (Within the CHARLS framework, digestive diseases are classified as chronic conditions necessitating medical management, such as gastritis, gastric/duodenal ulcers, inflammatory bowel disease, liver cirrhosis, and functional gastrointestinal disorders; malignancies were excluded). Affirmative responses led to classification as having a gastrointestinal disorder. Trained interviewers administered all surveys using standardized instruments. This method of self-report via structured questionnaires is a well-validated tool for estimating the prevalence of chronic conditions, including CDSD, in middle-aged and older populations and is commonly employed in large-scale epidemiological research \u003csup\u003e\u003cspan additionalcitationids=\"CR3 CR4\" citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e\u003c/sup\u003e. For analytical purposes, CDSD status was treated as a binary variable (present/absent).\u003c/p\u003e \u003cp\u003eDepressive symptoms were evaluated using the 10-item Center for Epidemiologic Studies Depression Scale (CES-D-10), a widely used instrument with established validity for screening depression \u003csup\u003e\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e\u003c/sup\u003e. Its applicability and sensitivity have been confirmed within older Chinese populations \u003csup\u003e\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e\u003c/sup\u003e. Each of the 10 items is scored from 0 (\"rarely or none of the time\") to 3 (\"most or all of the time\"), yielding a total score between 0 and 30. Higher scores indicate more severe depressive symptomatology. A cut-off score of \u0026ge;\u0026thinsp;10 was used to define clinically significant depression \u003csup\u003e\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e\u003c/sup\u003e. For conciseness in this study, the term \"depression\" refers to the presence of clinically significant depressive symptoms as defined by this threshold \u003csup\u003e\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e,\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e\u003c/sup\u003e. Based on their CES-D-10 scores, participants with CDSD were subsequently categorized into two groups: CDSD without depression and CDSD with depression.\u003c/p\u003e \u003cdiv id=\"Sec11\" class=\"Section2\"\u003e \u003ch2\u003eSocio-demographic and Behavioral Characteristics\u003c/h2\u003e \u003cp\u003eThe socio-demographic variables incorporated into the analysis comprised age, sex (male or female), educational attainment (below high school versus high school or higher), marital status (married or other), and residential setting (urban or rural). Behavioral factors encompassed smoking status (never, former, current), alcohol consumption (never, former, current), participation in social activities within the preceding two months (yes or no), daily midday nap duration (in minutes), and nocturnal sleep duration (in hours).\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec12\" class=\"Section2\"\u003e \u003ch2\u003eHealth Status\u003c/h2\u003e \u003cp\u003eDrawing upon established research frameworks and informed by clinical expertise, a comprehensive array of health measures potentially linked to depressive outcomes was examined. These included physical examination parameters, laboratory findings, and comorbid conditions.\u003c/p\u003e \u003cp\u003ePhysical and functional indicators consisted of: body mass index (BMI), waist circumference, pulse rate, grip strength, systolic and diastolic blood pressure, standing balance performance, instrumental activities of daily living (IADL) and basic activities of daily living (BADL) \u003csup\u003e\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e\u003c/sup\u003e, history of falls, history of disability, hearing acuity (poor or good), visual acuity (poor or good), walking speed, and presence of dental element loss (yes or no). Self-rated health, reflecting the individual\u0026rsquo;s subjective health perception, and overall life satisfaction were each classified as either good or poor.\u003c/p\u003e \u003cp\u003eLaboratory-based biomarkers derived from blood tests included: low-density lipoprotein (LDL), high-density lipoprotein cholesterol (HDL-C), uric acid, white blood cell count (WBC), hemoglobin level, platelet count (PLT), blood urea nitrogen (BUN), cystatin C, glycated hemoglobin (HbA1c), C-reactive protein (CRP), triglycerides (TG), total cholesterol (TC), creatinine, fasting blood glucose (FBG), mean corpuscular volume (MCV), and hematocrit \u003csup\u003e\u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eComorbidities were defined with reference to previous CHARLS-based studies on chronic digestive system diseases and included asthma, cancer, liver disease, kidney disease, dyslipidemia, arthritis, stroke, heart disease, lung disease, diabetes mellitus (DM), and hypertension\u003csup\u003e\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e,\u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec13\" class=\"Section2\"\u003e \u003ch2\u003eData Processing and Model Selection\u003c/h2\u003e \u003cp\u003eThe distribution and prevalence of missing data are detailed in Supplementary Fig.\u0026nbsp;1. Variables exhibiting a missing data rate surpassing 35%-specifically, walking speed and Cystatin C-were omitted from subsequent analyses. Consequently, a final set of 45 variables was retained. Missing values in the remaining dataset were addressed using multiple imputation techniques \u003csup\u003e\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eTo safeguard against model overfitting and to robustly assess the predictive model's generalizability, the overall sample was randomly partitioned into a development cohort (70%) and an independent test cohort (30%) \u003csup\u003e28\u003c/sup\u003e. All subsequent data processing and model development steps were conducted exclusively on the development set. An initial screening of potential predictor variables was performed using univariate logistic regression within the training subset, selecting all variables demonstrating a significance level of P\u0026thinsp;\u0026lt;\u0026thinsp;0.05. These variables were then subjected to multivariate logistic regression analysis. To refine the feature set further, variables identified as significant through multivariate analysis were intersected with those selected by a Least Absolute Shrinkage and Selection Operator (LASSO) regression procedure. This process yielded a final, robust set of 13 predictor variables. Given that the proportion of individuals with and without the target outcome was approximately balanced within the training set, techniques for addressing class imbalance, such as the Synthetic Minority Over-sampling Technique (SMOTE), were deemed unnecessary.\u003c/p\u003e \u003cp\u003eSubsequently, seven distinct machine learning algorithms were implemented to construct predictive models for depression risk: Logistic Regression (LR), Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), eXtreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), and an Artificial Neural Network (ANN). To optimize the predictive performance of each model, a comprehensive Grid Search strategy was employed for hyperparameter tuning. This systematic search aimed to identify the optimal configuration of hyperparameters for each respective algorithm (the resultant optimal parameter sets are catalogued in \u003cb\u003eSupplementary Table\u0026nbsp;1\u003c/b\u003e) \u003csup\u003e\u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e29\u003c/span\u003e,\u003cspan citationid=\"CR30\" class=\"CitationRef\"\u003e30\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec14\" class=\"Section2\"\u003e \u003ch2\u003eStatistical Analysis\u003c/h2\u003e \u003cp\u003e \u003cdiv class=\"BlockQuote\"\u003e \u003cp\u003eAll statistical computations and modeling were executed using R software (version 4.5.1) and Python (version 3.12.5). Descriptive statistics for continuous variables are reported as either mean\u0026thinsp;\u0026plusmn;\u0026thinsp;standard deviation (with range) or median and interquartile range (IQR). Group comparisons for these variables were conducted using Student's t-test or the non-parametric Wilcoxon rank-sum test, as appropriate based on data distribution. Categorical variables are summarized using frequency counts and percentages, with comparisons between groups performed via the Chi-square test or Fisher's exact test, depending on expected cell frequencies. A two-tailed P-value of less than 0.05 was established as the threshold for statistical significance.\u003c/p\u003e \u003c/div\u003e \u003c/p\u003e \u003c/div\u003e"},{"header":"Declarations","content":"\u003cp\u003e \u003ch2\u003eCompeting interests\u003c/h2\u003e \u003cp\u003eThe authors declare no competing interests.\u003c/p\u003e \u003c/p\u003e \u003cdiv id=\"Sec15\" class=\"Section2\"\u003e \u003ch2\u003eEthics statement\u003c/h2\u003e \u003cp\u003eThe studies involving humans were approved by the Biomedical Ethics Review Committee of Peking University (approval number: IRB00001052-11015). All participants in CHARLS provided written informed consent before participation in the original survey. This study was a secondary analysis of de-identified publicly available data and did not involve new collection of human participant data.\u003c/p\u003e \u003c/div\u003e\u003ch2\u003eFunding\u003c/h2\u003e\u003cp\u003eThis work was supported by the XinRui Translational Oncology Research Project (grant number: chmdf2025-xrky05-15).\u003c/p\u003e\n\u003ch2\u003eAuthor Contribution\u003c/h2\u003e\u003cp\u003eZixun Huang: Writing\u0026mdash;original draft, supervision, project administration. Liangze Ma: Software, methodology, supervision, writing\u0026mdash;original draft. Xin Wang: Writing\u0026mdash;review and editing, supervision, project administration. Mingheng Liu: Writing\u0026mdash;original draft, data curation. Shaopeng Zheng: Investigation. Shugeng Lin: Validation, formal analysis. Yukun Ma: Formal analysis. Qiangzhou Xu: Supervision, investigation, validation, formal analysis, data curation. Limin Ma and Shaobin Chen: Writing\u0026mdash;review and editing, data curation, supervision. All authors reviewed and approved the final manuscript.\u003c/p\u003e\u003ch2\u003eAcknowledgements\u003c/h2\u003e \u003cp\u003eThe authors sincerely thank the China Health and Retirement Longitudinal Study (CHARLS) team for providing access to the data and all survey participants for their valuable contributions to this research.\u003c/p\u003e\u003ch2\u003eData Availability\u003c/h2\u003e\u003cp\u003ePublicly available datasets were analyzed in this study. These data can be found at the China Health and Retirement Longitudinal Study (CHARLS) repository: https://charls.charlsdata.com/.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eBisgaard, T. H., Allin, K. H., Keefer, L., Ananthakrishnan, A. N. \u0026amp; Jess, T. Depression and anxiety in inflammatory bowel disease: epidemiology, mechanisms and treatment. \u003cem\u003eNat. Rev. Gastroenterol. Hepatol.\u003c/em\u003e \u003cb\u003e19\u003c/b\u003e, 717\u0026ndash;726. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1038/s41575-022-00634-6\u003c/span\u003e\u003cspan address=\"10.1038/s41575-022-00634-6\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2022).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGuo, J. et al. Longitudinal bidirectional association between gastrointestinal disease and depression symptoms among middle-aged and older adults in China. \u003cem\u003eArch. Public. Health\u003c/em\u003e. \u003cb\u003e83\u003c/b\u003e, 171. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1186/s13690-025-01671-8\u003c/span\u003e\u003cspan address=\"10.1186/s13690-025-01671-8\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2025).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChe, J., Song, Q., Zhao, C., Yuan, Y. \u0026amp; Lyu, X. Associations between changes in frailty status and non-neoplastic digestive system diseases: A cohort study based on the China health and retirement longitudinal study. \u003cem\u003eExp. Gerontol.\u003c/em\u003e \u003cb\u003e209\u003c/b\u003e, 112861. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.exger.2025.112861\u003c/span\u003e\u003cspan address=\"10.1016/j.exger.2025.112861\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2025).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChen, D. et al. Effects of indoor air pollution from household solid fuel use on the risk of gastrointestinal and liver diseases in middle aged and elderly adults. \u003cem\u003eEnviron. Int.\u003c/em\u003e \u003cb\u003e188\u003c/b\u003e, 108738. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.envint.2024.108738\u003c/span\u003e\u003cspan address=\"10.1016/j.envint.2024.108738\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2024).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSmarr, K. L. \u0026amp; Keefer, A. L. Measures of depression and depressive symptoms: Beck Depression Inventory-II (BDI-II), Center for Epidemiologic Studies Depression Scale (CES-D), Geriatric Depression Scale (GDS), Hospital Anxiety and Depression Scale (HADS), and Patient Health Questionnaire-9 (PHQ-9). \u003cem\u003eArthritis Care Res.\u003c/em\u003e \u003cb\u003e63\u003c/b\u003e (Suppl 11), S454\u0026ndash;466. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1002/acr.20556\u003c/span\u003e\u003cspan address=\"10.1002/acr.20556\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2011).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eFu, H., Si, L. \u0026amp; Guo, R. What Is the Optimal Cut-Off Point of the 10-Item Center for Epidemiologic Studies Depression Scale for Screening Depression Among Chinese Individuals Aged 45 and Over? An Exploration Using Latent Profile Analysis. \u003cem\u003eFront. Psychiatry\u003c/em\u003e. \u003cb\u003e13\u003c/b\u003e, 820777. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.3389/fpsyt.2022.820777\u003c/span\u003e\u003cspan address=\"10.3389/fpsyt.2022.820777\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2022).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAndresen, E. M., Malmgren, J. A., Carter, W. B. \u0026amp; Patrick, D. L. Screening for depression in well older adults: evaluation of a short form of the CES-D (Center for Epidemiologic Studies Depression Scale). \u003cem\u003eAm. J. Prev. Med.\u003c/em\u003e \u003cb\u003e10\u003c/b\u003e, 77\u0026ndash;84 (1994).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChen, H. \u0026amp; Mui, A. C. Factorial validity of the Center for Epidemiologic Studies Depression Scale short form in older population in China. \u003cem\u003eInt. Psychogeriatr.\u003c/em\u003e \u003cb\u003e26\u003c/b\u003e, 49\u0026ndash;57. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1017/s1041610213001701\u003c/span\u003e\u003cspan address=\"10.1017/s1041610213001701\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2014).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhao, X. et al. A machine-learning-derived online prediction model for depression risk in COPD patients: A retrospective cohort study from CHARLS. \u003cem\u003eJ. Affect. Disord.\u003c/em\u003e \u003cb\u003e377\u003c/b\u003e, 284\u0026ndash;293. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.jad.2025.02.063\u003c/span\u003e\u003cspan address=\"10.1016/j.jad.2025.02.063\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2025).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKatz, S. et al. A STANDARDIZED MEASURE OF BIOLOGICAL AND PSYCHOSOCIAL FUNCTION. \u003cem\u003eJama\u003c/em\u003e \u003cb\u003e185\u003c/b\u003e, 914\u0026ndash;919. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1001/jama.1963.03060120024016\u003c/span\u003e\u003cspan address=\"10.1001/jama.1963.03060120024016\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (1963).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCohen-Mekelburg, S. et al. Loneliness and Depressive Symptoms Are High Among Older Adults With Digestive Disease and Associated With Lower Perceived Health. \u003cem\u003eClin. Gastroenterol. hepatology: official Clin. Pract. J. Am. Gastroenterological Association\u003c/em\u003e. \u003cb\u003e22\u003c/b\u003e, 621\u0026ndash;629e622. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.cgh.2023.08.027\u003c/span\u003e\u003cspan address=\"10.1016/j.cgh.2023.08.027\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2024).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMules, T. C. et al. The impact of disease activity on psychological symptoms and quality of life in patients with inflammatory bowel disease-results from the Stress, Anxiety and Depression with Disease Activity (SADD) Study. \u003cem\u003eAliment. Pharmacol. Ther.\u003c/em\u003e \u003cb\u003e55\u003c/b\u003e, 201\u0026ndash;211. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1111/apt.16616\u003c/span\u003e\u003cspan address=\"10.1111/apt.16616\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2022).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eVan Den Houte, M. et al. Predictors of Symptoms Trajectories in Newly Diagnosed Ulcerative Colitis: A 3-Year Follow-up Cohort Study. \u003cem\u003eJ. Crohn's colitis\u003c/em\u003e. \u003cb\u003e18\u003c/b\u003e, 1394\u0026ndash;1405. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1093/ecco-jcc/jjae046\u003c/span\u003e\u003cspan address=\"10.1093/ecco-jcc/jjae046\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2024).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZheng, Q. Q., Yang, W. W., He, S. S. \u0026amp; Li, Y. R. Association between sleep duration and depression in adolescents and young adults: a system review of observational studies and a genetic research of Mendelian randomization analysis. \u003cem\u003ePostgrad. Med. J.\u003c/em\u003e \u003cb\u003e101\u003c/b\u003e, 845\u0026ndash;853. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1093/postmj/qgaf013\u003c/span\u003e\u003cspan address=\"10.1093/postmj/qgaf013\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2025).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLi, D. R. et al. Regular sleep patterns, not just duration, critical for mental health: association of accelerometer-derived sleep regularity with incident depression and anxiety. \u003cem\u003ePsychol. Med.\u003c/em\u003e \u003cb\u003e55\u003c/b\u003e, e239. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1017/s0033291725101281\u003c/span\u003e\u003cspan address=\"10.1017/s0033291725101281\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2025).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMeyer, N. et al. The sleep-circadian interface: A window into mental disorders. \u003cem\u003eProc. Natl. Acad. Sci. U.S.A.\u003c/em\u003e \u003cb\u003e121\u003c/b\u003e, e2214756121. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1073/pnas.2214756121\u003c/span\u003e\u003cspan address=\"10.1073/pnas.2214756121\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2024).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRuan, X. et al. Depression and 24 gastrointestinal diseases: a Mendelian randomization study. \u003cem\u003eTranslational psychiatry\u003c/em\u003e. \u003cb\u003e13\u003c/b\u003e, 146. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1038/s41398-023-02459-6\u003c/span\u003e\u003cspan address=\"10.1038/s41398-023-02459-6\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2023).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ede Feijter, M., Kocevska, D., Ikram, M. A. \u0026amp; Luik, A. I. The bidirectional association of 24-h activity rhythms and sleep with depressive symptoms in middle-aged and elderly persons. \u003cem\u003ePsychol. Med.\u003c/em\u003e \u003cb\u003e53\u003c/b\u003e, 1418\u0026ndash;1425. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1017/s003329172100297x\u003c/span\u003e\u003cspan address=\"10.1017/s003329172100297x\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2023).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAye, S. et al. Health-related quality of life in subjective cognitive decline and mild cognitive impairment: a longitudinal cohort analysis. \u003cem\u003eAlzheimers Res. Ther.\u003c/em\u003e \u003cb\u003e15\u003c/b\u003e, 200. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1186/s13195-023-01344-0\u003c/span\u003e\u003cspan address=\"10.1186/s13195-023-01344-0\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2023).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eXiong, L. Y. et al. Longitudinal relationships between depressive symptoms, functional impairment, and physical activity in later late life. \u003cem\u003eGeroScience\u003c/em\u003e \u003cb\u003e47\u003c/b\u003e, 1061\u0026ndash;1073. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/s11357-024-01282-1\u003c/span\u003e\u003cspan address=\"10.1007/s11357-024-01282-1\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2025).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAbay, R. J. Y., Gold, L. S., Cawthon, P. M. \u0026amp; Andrews, J. S. Lean mass, grip strength, and hospital-associated disability among older adults in Health ABC. \u003cem\u003eAlzheimer's Dement. J. Alzheimer's Assoc.\u003c/em\u003e \u003cb\u003e18\u003c/b\u003e, 1898\u0026ndash;1906. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1002/alz.12527\u003c/span\u003e\u003cspan address=\"10.1002/alz.12527\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2022).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBell\u0026oacute;n, D. et al. Associations between muscular strength and mental health in cognitively normal older adults: a cross-sectional study from the AGUEDA trial. \u003cem\u003eInt. J. Clin. health psychology: IJCHP\u003c/em\u003e. \u003cb\u003e24\u003c/b\u003e, 100450. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.ijchp.2024.100450\u003c/span\u003e\u003cspan address=\"10.1016/j.ijchp.2024.100450\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2024).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHurst, C. et al. Long-term conditions, multimorbidity, lifestyle factors and change in grip strength over 9 years of follow-up: Findings from 44,315 UK biobank participants. \u003cem\u003eAge ageing\u003c/em\u003e. \u003cb\u003e50\u003c/b\u003e, 2222\u0026ndash;2229. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1093/ageing/afab195\u003c/span\u003e\u003cspan address=\"10.1093/ageing/afab195\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2021).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhao, Y., Hu, Y., Smith, J. P., Strauss, J. \u0026amp; Yang, G. Cohort profile: the China Health and Retirement Longitudinal Study (CHARLS). \u003cem\u003eInt. J. Epidemiol.\u003c/em\u003e \u003cb\u003e43\u003c/b\u003e, 61\u0026ndash;68. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1093/ije/dys203\u003c/span\u003e\u003cspan address=\"10.1093/ije/dys203\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2014).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCovinsky, K. E. et al. Loss of independence in activities of daily living in older adults hospitalized with medical illnesses: increased vulnerability with age. \u003cem\u003eJ. Am. Geriatr. Soc.\u003c/em\u003e \u003cb\u003e51\u003c/b\u003e, 451\u0026ndash;458. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1046/j.1532-5415.2003.51152.x\u003c/span\u003e\u003cspan address=\"10.1046/j.1532-5415.2003.51152.x\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2003).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGao, Y. et al. Depressive Symptoms Trajectories and Chronic Digestive Disease in Chinese Middle-Aged and Older Adults: A Longitudinal Cohort Study. \u003cem\u003eJ Prev (\u003c/em\u003e) (2026).) (2026). (2022). \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/s10935-026-00901-1\u003c/span\u003e\u003cspan address=\"10.1007/s10935-026-00901-1\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eEnders, C. K. Missing data: An update on the state of the art. \u003cem\u003ePsychol. Methods\u003c/em\u003e. \u003cb\u003e30\u003c/b\u003e, 322\u0026ndash;339. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1037/met0000563\u003c/span\u003e\u003cspan address=\"10.1037/met0000563\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2025).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eXu, Y. \u0026amp; Goodacre, R. On Splitting Training and Validation Set: A Comparative Study of Cross-Validation, Bootstrap and Systematic Sampling for Estimating the Generalization Performance of Supervised Learning. \u003cem\u003eJ. Anal. Test.\u003c/em\u003e \u003cb\u003e2\u003c/b\u003e, 249\u0026ndash;262. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/s41664-018-0068-2\u003c/span\u003e\u003cspan address=\"10.1007/s41664-018-0068-2\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2018).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHan, J., Gondro, C., Reid, K. \u0026amp; Steibel, J. P. Heuristic hyperparameter optimization of deep learning models for genomic prediction. \u003cem\u003eG3 (Bethesda, Md.)\u003c/em\u003e 11 (2021). \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1093/g3journal/jkab032\u003c/span\u003e\u003cspan address=\"10.1093/g3journal/jkab032\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAhanger, A. B. et al. Radiogenomics and machine learning predict oncogenic signaling pathways in glioblastoma. \u003cem\u003eJ. translational Med.\u003c/em\u003e \u003cb\u003e23\u003c/b\u003e, 121. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1186/s12967-025-06101-5\u003c/span\u003e\u003cspan address=\"10.1186/s12967-025-06101-5\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2025).\u003c/span\u003e\u003c/li\u003e \u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"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":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Chronic digestive system diseases, Depression, Prediction model, Machine learning, Shap, Website visualization","lastPublishedDoi":"10.21203/rs.3.rs-9205724/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9205724/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eChronic digestive system diseases (CDSD) are common in older adults, and depressive symptoms substantially worsen prognosis and quality of life. We developed and temporally validated a machine-learning model to identify depressive symptoms in individuals with CDSD using data from the China Health and Retirement Longitudinal Study (CHARLS). This study included 3,762 participants with CDSD from the 2011 survey and examined 46 behavioral, health, psychological, and sociodemographic variables. Feature selection was performed using logistic regression and LASSO regression, and seven machine-learning algorithms were compared. Temporal validation was conducted in newly diagnosed CDSD participants from the 2015 CHARLS wave. Among 3,762 participants, 1,900 had depressive symptoms. Thirteen variables were retained, including education, residence, life assessment, health assessment, fall history, disability, kidney disease, arthritis, heart disease, eyesight, instrumental activities of daily living, sleep duration, and grip strength. XGBoost showed the best performance in the testing set, with an area under the curve of 0.793 and an F1-score of 0.724, together with good calibration and clinical utility. These findings suggest that machine-learning approaches may support early identification of depressive symptoms in people with CDSD.\u003c/p\u003e","manuscriptTitle":"A machine-learning-derived online screening tool for depressive symptoms in chronic digestive system diseases patients: A cross- sectional study with temporal validation from CHARLS","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-03 06:09:15","doi":"10.21203/rs.3.rs-9205724/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-05-04T07:14:21+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-28T07:19:27+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-26T16:08:58+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"42581173665944903272413543172212289631","date":"2026-04-15T08:40:13+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"242282441349248954134567817544682879583","date":"2026-04-15T07:00:25+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"106411311666283496984378545908850487407","date":"2026-04-09T10:35:30+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-09T06:25:00+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"54453842595195545370407876539369544604","date":"2026-04-09T06:22:39+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-03-29T07:31:41+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2026-03-27T06:10:49+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-03-24T12:19:18+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-03-24T12:18:43+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2026-03-24T02:13:09+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"665cfa52-e956-4c15-a346-3e2044c2234d","owner":[],"postedDate":"April 3rd, 2026","published":true,"recentEditorialEvents":[{"type":"decision","content":"Revision requested","date":"2026-05-04T07:14:21+00:00","index":"","fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":65367563,"name":"Health sciences/Diseases"},{"id":65367564,"name":"Health sciences/Health care"},{"id":65367565,"name":"Health sciences/Medical research"},{"id":65367566,"name":"Health sciences/Risk factors"}],"tags":[],"updatedAt":"2026-05-13T05:08:13+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-03 06:09:15","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9205724","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9205724","identity":"rs-9205724","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}