Construction of a clinical prediction model for osteoporosis in asymptomatic elderly population based on machine learning algorithm - Research study

Aug 5, 2026

Osteoporosis is a common metabolic bone disorder driven by reduced bone mass, leading to fractures and substantial clinical and socioeconomic burden, while many cases remain undetected until fragility fractures occur. A clinical prediction model was developed and validated for osteoporosis risk in asymptomatic elderly individuals using machine learning methods integrated with SHAP interpretability. Model performance was assessed with ROC, calibration, and decision curve analysis, and the best-performing KNN+RF combination was selected. A Shiny web application was built to support efficient screening and diagnosis.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages14

Reading Time35 min

AccessFree to download

Introduction

Background and significance of osteoporosis

Current diagnostic methods and limitations

Method

Data source and cohort description

Machine learning model development

Model evaluation and validation (ROC, calibration, DCA)

SHAP interpretation

Shiny web application

Results

Comparison of machine learning algorithm combinations

Performance metrics and clinical utility

Conclusions

TYPE Original Research PUBLISHED 12 September 2025 DOI 10. 3389/fmed.2025.1607734 OPEN ACCESS EDITED BY Jinhui Liu, Nanjing Medical University, China REVIEWED BY Thaqif El Khassawna, University of Giessen, Germany Xinzhou Huang, The 3201 Hospital Affiliated to the Medical School of Xi’an Jiaotong University, China *CORRESPONDENCE Tongping Shen [shentp2010@ahtcm.edu.cn](shentp2010@ahtcm.edu.cn)[ ](shentp2010@ahtcm.edu.cn)Shihao Wang [wshlcm2003@126.com](wshlcm2003@126.com) RECEIVED 08 April 2025 ACCEPTED 11 August 2025 PUBLISHED 12 September 2025 CITATION Wang J, Zhao S, Shen T and Wang S (2025) Construction of a clinical prediction model for osteoporosis in asymptomatic elderly population based on machine learning algorithm. Front. Med. 12:1607734 . doi: 10.3389/fmed.2025.1607734 COPYRIGHT © 2025 Wang, Zhao, Shen and Wang. This isan open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. Construction of a clinical prediction model for osteoporosis in asymptomatic elderly population based on machine learning algorithm Jiaming Wang1 , Siyuan Zhao2 , Tongping Shen1* and Shihao Wang1* 1 School of Information Engineering, Anhui University of Chinese Medicine, Hefei, China, 2 School of Pharmaceutical Economics and Management, Anhui University of Chinese Medicine, Hefei, China Background: Osteoporosis is a metabolic bone disease characterized by a decrease in the amount of bone per unit volume. It is highly prevalent and has a harsh impact on patients’ lives. The development of accurate predictive models for osteoporosis is beneﬁcial in helping physicians improve the accuracy of clinical diagnosis and provide a high-quality treatment experience for older adults. Method: In this study, a robust and accurate prediction model for osteoporosis was developed and validated based on machine learning and SHAP techniques. We validated the model using ROC, calibration, and DCA curves. The data in this paper were obtained from elderly participants in several communities in Beijing from June 2021 to May 2022, including 161 (27.6%) males and 423 (72.4%) females, 248 (42 .47%) with osteoporosis and 336 (57 . 53%) without osteoporosis. Results: Upon comparing and assessing the predictive outcomes of 135 models utilizing a combination of 10 machine learning algorithms, we found that the KNN+RF combination algorithm performs the best in terms of prediction performance. The Sensitivity, Speciﬁcity, PPV, NPV, Precision, Recall, F1, Detection Prevalence, AUC, and Brier metrics of this combined algorithm are 0. 7500, 0 .6634, 0 .6136, 0 . 7614, 0 .6136, 0 . 7200, 0 .6626, 0 . 5000, 0 .904, and 0 .1601. Calibration and decision curve analyses further demonstrated the model’s potential clinical utility. Ultimately, we created the Shiny web application for osteoporosis diagnosis. Conclusions: The osteoporosis prediction model is readily generalizable and can aid physicians in efficiently screening for osteoporosis in the broader older demographic. This will facilitate rapid detection and diagnosis of the disease, as well as the formulation of improved therapeutic treatment strategies for patients. KEYWORDS osteoporosis, elderly, machine learning, SHAP, early diagnosis, shiny 1 Introduction Osteoporosis is a systemic skeletal disease, and as one of the most prevalent metabolic disorders, its pathogenesis is characterized by a decrease in the amount of bone per unit volume, which leads to fractures. Osteoporosis has, therefore, received progressively increased attention in orthopedics and endocrinology ( 1, 2) . In recent ye

FAQs

Why is an osteoporosis clinical prediction model needed for asymptomatic elderly people?

Osteoporosis often remains undetected early and late, leading to diagnosis after fragility fractures. A predictive tool can improve screening and support earlier clinical decision-making.

Which machine learning approach performed best in the study?

Among 135 models built from combinations of 10 machine learning algorithms, the KNN+RF combination achieved the best predictive performance.

How was the model’s performance and clinical usability evaluated?

Performance was assessed using ROC, calibration, and decision curve analysis (DCA), and SHAP techniques were used to support interpretability of the model outputs.

Aug 5, 2026

Upload by Clementine