Investigating osteoporosis diagnosis using clinical and hip X-ray data from the Syrian population
- 1Department of Biomedical Engineering, Faculty of Mechanical and Electrical Engineering, Damascus University
- 2Department of Medicine and Surgery, University of Parma
Abstract
Osteoporosis diagnosis remains challenging due to variability in imaging quality, clinical factors, and population diversity. This study evaluated osteoporosis classification using clinical data and hip radiographs (HXR) from the Syrian population, with external validation on an independent Indian dataset. Among clinical models, the neural network achieved the highest testing accuracy of 84.04% and a balanced overall performance, while random forest and ensemble classifiers demonstrated competitive sensitivity. Deep learning using ResNet50 on contrast-enhanced HXR images reached 94.12% accuracy, outperforming EfficientNet-B0 (92.76%) and YOLOv9 (85.10%). A hybrid model combining clinical and image-derived features further achieved 93.21% accuracy, confirming the diagnostic value of multimodal integration. Cross-dataset validation performed on clinical data revealed reduced performance between the Syrian and Indian cohorts, reflecting the influence of diagnostic standards and demographic variability. These findings demonstrate that combining clinical and radiographic information can enhance osteoporosis detection while underscoring the need for standardized, population-specific validation of artificial intelligence models.
Related
- Investigating the pathogenicity of missense spliceogenic variants using whole-genome sequencing, RNA-sequencing, and proteomics data from population and clinical research cohorts
- Assessing theoretical knowledge related to surgical and clinical skills in Syrian medical students : A cross-sectional study.
- The Pivotal Role of Consultant Physicians in the Early Screening, Diagnosis, and Management of Osteopenia and Osteoporosis: An Expert Opinion.
- COMBINING CHEST X-RAY AND CLINICAL COVARIATES FOR OSTEOPOROSIS SCREENING: A MULTIMODAL DEEP LEARNING APPROACH
- Diagnostic efficacy of a novel bedside dual-energy X-ray absorptiometry device for the diagnosis of osteoporosis: a prospective cohort study
BibTeX
@article{sweekat2026investigating,
title = {{Investigating osteoporosis diagnosis using clinical and hip X-ray data from the Syrian population}},
author = {Kholoud Sweekat and Ebrahim Ismaiel and Rasha Massoud and Mamdouh Monif},
journal = {Scientific Reports},
year = {2026},
month = aug,
doi = {10.1038/s41598-026-65200-5},
url = {https://doi.org/10.1038/s41598-026-65200-5},
note = {CC BY},
}
RIS
TY - JOUR
TI - Investigating osteoporosis diagnosis using clinical and hip X-ray data from the Syrian population
AU - Kholoud Sweekat
AU - Ebrahim Ismaiel
AU - Rasha Massoud
AU - Mamdouh Monif
PY - 2026
DA - 2026/08/01
JO - Scientific Reports
DO - 10.1038/s41598-026-65200-5
UR - https://doi.org/10.1038/s41598-026-65200-5
AB - Osteoporosis diagnosis remains challenging due to variability in imaging quality, clinical factors, and population diversity. This study evaluated osteoporosis classification using clinical data and hip radiographs (HXR) from the Syrian population, with external validation on an independent Indian dataset. Among clinical models, the neural network achieved the highest testing accuracy of 84.04% and a balanced overall performance, while random forest and ensemble classifiers demonstrated competitive sensitivity. Deep learning using ResNet50 on contrast-enhanced HXR images reached 94.12% accuracy, outperforming EfficientNet-B0 (92.76%) and YOLOv9 (85.10%). A hybrid model combining clinical and image-derived features further achieved 93.21% accuracy, confirming the diagnostic value of multimodal integration. Cross-dataset validation performed on clinical data revealed reduced performance between the Syrian and Indian cohorts, reflecting the influence of diagnostic standards and demographic variability. These findings demonstrate that combining clinical and radiographic information can enhance osteoporosis detection while underscoring the need for standardized, population-specific validation of artificial intelligence models.
SN - 2045-2322
ER -