Academic Journal
Development and external validation of interpretable machine learning models for predicting first fall risk in knee osteoarthritis patients: evidence from the CHARLS cohort and a hospital-based cohort in China.
| Τίτλος: | Development and external validation of interpretable machine learning models for predicting first fall risk in knee osteoarthritis patients: evidence from the CHARLS cohort and a hospital-based cohort in China. |
|---|---|
| Συγγραφείς: | Yin HT; Department Joints, Tianjin University Tianjin Hospital, Tianjin, China; Tianjin University, Tianjin, China., Wang W; Department of rehabilitation, Tianjin University Tianjin Hospital, Tianjin, China., Zhang YX; Department Joints, Tianjin University Tianjin Hospital, Tianjin, China; Clinical College of Orthopedics, Tianjin Medical University, Tianjin, China., Fu X; Department Joints, Tianjin University Tianjin Hospital, Tianjin, China., Wang L; Department Joints, Tianjin University Tianjin Hospital, Tianjin, China., Yang T; Department Joints, Tianjin University Tianjin Hospital, Tianjin, China; Clinical College of Orthopedics, Tianjin Medical University, Tianjin, China. Electronic address: francis_yang@126.com., Liu J; Department Joints, Tianjin University Tianjin Hospital, Tianjin, China; Department of rehabilitation, Tianjin University Tianjin Hospital, Tianjin, China; Tianjin University, Tianjin, China. Electronic address: liujun1968tju@163.com. |
| Πηγή: | Archives of gerontology and geriatrics [Arch Gerontol Geriatr] 2026 Dec; Vol. 151, pp. 106410. Date of Electronic Publication: 2026 Sep 11. |
| Τύπος έκδοσης: | Journal Article; Validation Study |
| Γλώσσα: | English |
| Στοιχεία περιοδικού: | Publisher: Elsevier Biomedical Press Country of Publication: Netherlands NLM ID: 8214379 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1872-6976 (Electronic) Linking ISSN: 01674943 NLM ISO Abbreviation: Arch Gerontol Geriatr Subsets: MEDLINE |
| Imprint Name(s): | Original Publication: Amsterdam : Elsevier Biomedical Press, c1982- |
| Ιατρικοί όροι (MeSH): | Accidental Falls*/statistics & numerical data , Accidental Falls*/prevention & control , Osteoarthritis, Knee*/complications , Osteoarthritis, Knee*/epidemiology , Machine Learning*, China/epidemiology ; Risk Assessment/methods ; Humans ; Female ; Aged ; Male ; Retrospective Studies ; Predictive Learning Models ; Risk Factors ; Boosting Machine Learning Algorithms ; Prediction Algorithms ; Middle Aged |
| Περίληψη: | Background: Knee osteoarthritis (KOA) is a prevalent degenerative joint disease that causes pain, reduced mobility, and an increased risk of falls in older adults. Predicting fall risk in this population remains difficult because of the complex interplay of multiple risk factors. Methods: Data from 1097 patients with KOA in the CHARLS cohort were retrospectively analyzed using 28 demographic, health, and behavioral variables. Ten machine learning (ML) algorithms were evaluated, and the Gradient Boosting Machine (GBM) was selected as the final model based on overall balanced performance. Model interpretability was assessed using SHapley Additive exPlanations (SHAP), which identified the main predictors. External validation was performed in an independent hospital-based cohort to assess generalizability. Results: The GBM model achieved the most balanced and stable performance (AUC = 0.836), demonstrating good discriminative ability. Sensory impairments (hearing and vision problems) and depressive symptoms were the most influential predictors of falls. SHAP analysis clarified the contribution of these features to the model's predictions. In the external cohort, the locked GBM model maintained favorable discrimination and calibration, confirming robustness and generalizability. Conclusions: An interpretable ML model was developed to predict fall risk in KOA patients. The model effectively identified key sensory and mental health factors and demonstrated reliable performance across internal and external validations, supporting its potential to assist clinicians in early identification and prevention of falls among older adults with KOA. (Copyright © 2026 Elsevier B.V. All rights reserved.) |
| Competing Interests: | Declaration of competing interest All authors of the above manuscript declare that they have no potential conflicts of interest (financial or non-financial) related to the research content, data collection, analysis, and manuscript preparation. |
| Contributed Indexing: | Keywords: CHARLS; First-fall prediction; Knee osteoarthritis; Machine learning; Shapley additive explanations |
| Entry Date(s): | Date Created: 20260918 Date Completed: 20260929 Latest Revision: 20260929 |
| Update Code: | 20260930 |
| DOI: | 10.1016/j.archger.2026.106410 |
| PMID: | 42759165 |
| Βάση Δεδομένων: | MEDLINE |
| ISSN: | 1872-6976 |
|---|---|
| DOI: | 10.1016/j.archger.2026.106410 |