|
Study on Risk Prediction of Comorbidity of Major Chronic Diseases in Rural Elderly in China Based on Multi-label Deep Learning |
|---|---|
| รหัสดีโอไอ | |
| Creator | Fen Fu |
| Title | Study on Risk Prediction of Comorbidity of Major Chronic Diseases in Rural Elderly in China Based on Multi-label Deep Learning |
| Contributor | Kittiya Suthiprapa, Kanyarat Kwiecien |
| Publisher | Department of Information Science Faculty of Humanities and Social Sciences, Khon Kaen University |
| Publication Year | 2569 |
| Journal Title | Journal of Information Science Research and Practice |
| Journal Vol. | 44 |
| Page no. | 49-77 |
| Keyword | Deep learning, Multi-label learning, Chronic disease risk prediction, Rural older adults, CHARLS |
| URL Website | https://so03.tci-thaijo.org/index.php/jiskku |
| Website title | Journal of Information Science Research and Practice |
| ISSN | 3027-6586 |
| Abstract | Purpose: To develop and evaluate a multi-label deep learning framework for simultaneously predicting five major chronic diseases.Methodology: Using CHARLS data supplemented with rural health examination records (n=38,569, aged ≥60), a fully connected multi-label deep neural network was trained using weighted binary cross-entropy and disease-specific threshold optimization. Five-fold cross-validation and an independent test set (15%) were used for evaluation.Findings: The model achieved a macro AUC-ROC of 0.8587 and a macro F1-score of 0.6676 on the independent test set, outperforming logistic regression and XGBoost while achieving competitive performance compared to random forest. SHAP analysis identified systolic blood pressure, BMI, and fasting glucose as the top predictors.Applications of this study: The proposed framework demonstrates the feasibility for transforming population-level survey data into actionable multimorbidity risk tools for resource-constrained rural primary care. |
