Evaluation of blood- and urine-derived biomarkers for machine learning prediction models of osteoarthritis in elderly patients: A feasibility study

• Published in: Computer methods and programs in biomedicine Vol. 266; p. 108779
• Main Author: Kim, Jun-hee
• Format: Journal Article
• Language: English
• Published: Ireland Elsevier B.V 01.06.2025
• Subjects: Aged; Aged, 80 and over; Algorithms; Biomarker; Biomarkers - blood; Biomarkers - urine; Blood; Derived variable; Feasibility Studies; Female; Humans; Machine Learning; Male; Middle Aged; Osteoarthritis; Osteoarthritis - blood; Osteoarthritis - diagnosis; Osteoarthritis - urine; Support Vector Machine; Urine; Urine; Biomarker; Osteoarthritis; Blood; Machine learning; Derived variable
• ISSN: 0169-2607; 1872-7565; 1872-7565
• DOI: 10.1016/j.cmpb.2025.108779

•The study evaluated the feasibility of using blood and urine-derived biomarkers to develop machine learning models for early detection and diagnosis of osteoarthritis (OA) in the elderly.•Models were developed using various machine learning algorithms, with the support vector machine showing the highest accuracy for the blood model (0.6245), and random forest performing best for the urine model (0.5770).•The derived biomarker model, developed by combining key features from SHAP analysis, outperformed the total biomarker model in all evaluation metrics. Logistic regression showed the highest accuracy in the derived model (0.6450), compared to gradient boosting in the total model (0.6342).•Derived biomarkers were created by combining the most important features identified through SHAP analysis from both blood and urine models, improving the predictive accuracy of OA diagnosis. Osteoarthritis (OA) is a common degenerative joint disease, particularly affecting individuals aged >50 years. It deteriorates quality of life and restricts physical activity in the elderly. Early diagnosis of OA is crucial for effective management, slowing disease progression, and alleviating symptoms. This study evaluated the feasibility of utilizing biomarkers derived from blood and urine in developing predictive models for OA diagnosis in the elderly population. Additionally, we compared the derived biomarker model with a model using standard blood and urine variables to assess the impact of the derived biomarkers on OA diagnosis. Data from 10,743 participants were analyzed, including variables from blood and urine tests. Machine learning algorithms were used to develop the models. Derived biomarkers were identified based on the most significant features highlighted by Shapley Additive exPlanations (SHAP) analysis. The performance of models based on blood and urine biomarkers was compared with that of models based on derived biomarkers, and important variables were analyzed using SHAP. The support vector machine demonstrated the highest accuracy (0.6245) and F1 score (0.6232) for the blood dataset, whereas the random forest model achieved the best performance (0.5770) for the urine dataset. The derived biomarker model, which combined biomarkers of high importance from the best-performing models, showed improved predictive performance compared with the model using all blood and urine variables. The derived biomarker model achieved the highest performance metrics, with the logistic regression algorithm yielding an accuracy of 0.6450, precision of 0.6443, recall of 0.6450, and F1 score of 0.6430. Biomarkers derived from routinely available blood and urine tests show promise for the early detection and comprehensive diagnosis of OA in older patients. These biomarkers are practical for clinical use, as they can be integrated into routine testing, potentially aiding early detection and improving patient outcomes.