EUVIMEDEUVIMED entdecken
Systematische ÜbersichtMetaanalyse

Comparing Machine Learning Algorithms for Prediction of Osteoporosis: A Systematic Review and Meta-Analysis Study

Esmat Mashoof, Khadijeh Moulaei, Naser Nasiri

Advances in Medical Informatics · 10.02.2026

DOI: 10.22034/aimi.2026.17.9 ↗

Kurz gefasst

Systematische Übersicht in der Zeitschrift Advances in Medical Informatics, erschienen am 10.02.2026. Verfasst von Esmat Mashoof und 2 weiteren Autor:innen.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Osteoporosis is a prevalent bone disease that affects millions of individuals worldwide. Early identification and prediction of osteoporosis can enable timely interventions and preventive measures. This study investigates the potential of machine learning algorithms to accurately predict osteoporosis. Material and Methods: This study is a systematic review and meta-analysis conducted by searching in three databases. Our search encompassed databases such as Web of Science, PubMed, and Scopus. Pertinent information from the selected studies was independently extracted by two authors. The PRISMA guidelines were followed to ensure a rigorous review process. The PROBAST tool was utilized to assess the risk of bias in the included studies. Data analysis was performed using Stata (v.17.1).

Results

A total of 63 algorithms from 18 studies were evaluated. In terms of predicting osteoporosis, support vector machine (SVM) and random forest (RF) algorithms demonstrated the highest sensitivity. For SVM, the sensitivity and diagnostic odds ratio (DOR) were 83.0% (95% confidence interval (CI): 76.0-88.0) and 10.4 (95% CI: 6.0-18.2), respectively. Similarly, in the case of RF algorithm, the sensitivity and DOR were 81.0% (95% CI: 74.0-87.0) and 13.0 (95% CI: 7.7-21.2), respectively. The artificial neoural networks (ANN), RF, and K-nearest neighbors (KNN) algorithms exhibited the highest specificity values: ANN- specificity of 79.0% (95% CI: 71.0-85.0) and DOR of 12.0 (7.3-18.7); RF- specificity of 75.0% (95% CI: 62.0-84.0) and DOR of 13.0 (7.7-21.2); KNN- specificity of 75.0% (95% CI: 67.0-82.0) and DOR of 7.7(6.6-9.0).

Conclusion

Our study highlights the promising potential of machine learning algorithms for the accurate prediction of osteoporosis. ANN model and SVM, RF, and KNN algorithms have emerged as the most robust predictors. These findings demonstrate substantial potential for aiding early detection and intervention strategies against osteoporosis.

Schlagwörter

osteoporosis risk predictionmachine learning algorithmssupport vector machinerandom forestartificial neural networksk-nearest neighborsdiagnostic accuracysensitivity and specificitybone disease

Zitieren

APA

Mashoof, E., Moulaei, K., & Nasiri, N. (2026). Comparing Machine Learning Algorithms for Prediction of Osteoporosis: A Systematic Review and Meta-Analysis Study. Advances in Medical Informatics. https://doi.org/10.22034/aimi.2026.17.9

Vancouver

Mashoof E, Moulaei K, Nasiri N. Comparing Machine Learning Algorithms for Prediction of Osteoporosis: A Systematic Review and Meta-Analysis Study. Advances in Medical Informatics. 2026. doi:10.22034/aimi.2026.17.9

BibTeX
@article{Mashoof2026,
  author = {Mashoof, Esmat and Moulaei, Khadijeh and Nasiri, Naser},
  title = {Comparing Machine Learning Algorithms for Prediction of Osteoporosis: A Systematic Review and Meta-Analysis Study},
  journal = {Advances in Medical Informatics},
  year = {2026},
  doi = {10.22034/aimi.2026.17.9}
}
Kostenlos starten →