Application of Machine Learning to Osteoporosis and Osteopenia Screening Using Hand Radiographs

Anna Luan; Zeshaan Maan; Kun-Yi Lin; Jeffrey Yao

doi:10.1016/j.jhsa.2024.09.008

Application of Machine Learning to Osteoporosis and Osteopenia Screening Using Hand Radiographs

J Hand Surg Am. 2024 Nov 15:S0363-5023(24)00432-5. doi: 10.1016/j.jhsa.2024.09.008. Online ahead of print.

Authors

Anna Luan¹, Zeshaan Maan¹, Kun-Yi Lin², Jeffrey Yao³

Affiliations

¹ Division of Plastic and Reconstructive Surgery, Department of Surgery, Stanford University School of Medicine, Stanford, CA.
² Department of Orthopedics, Tri-Service General Hospital, National Defense Medical Center, Taipei, Taiwan, Republic of China.
³ Department of Orthopaedic Surgery, Stanford University School of Medicine, Stanford, CA; Robert A. Chase Hand and Upper Limb Center, Department of Orthopaedic Surgery, Stanford University Medical Center, Redwood City, CA. Electronic address: jyao@stanford.edu.

PMID: 39556066
DOI: 10.1016/j.jhsa.2024.09.008

Abstract

Purpose: Fragility fractures associated with osteoporosis and osteopenia are a common cause of morbidity and mortality. Current methods of diagnosing low bone mineral density require specialized dual x-ray absorptiometry (DXA) scans. Plain hand radiographs may have utility as an alternative screening tool, although optimal diagnostic radiographic parameters are unknown, and measurement is prone to human error. The aim of the present study was to develop and validate an artificial intelligence algorithm to screen for osteoporosis and osteopenia using standard hand radiographs.

Methods: A cohort of patients with both a DXA scan and a plain hand radiograph within 12 months of one another was identified. Hand radiographs were labeled as normal, osteopenia, or osteoporosis based on corresponding DXA hip T-scores. A deep learning algorithm was developed using the ResNet-50 framework and trained to predict the presence of osteoporosis or osteopenia on hand radiographs using labeled images. The results from the algorithm were validated using a separate balanced validation set, with the calculation of sensitivity, specificity, accuracy, and receiver operating characteristic curve using definitions from corresponding DXA scans as the reference standard.

Results: There was a total of 687 images in the normal category, 607 images in the osteopenia category, and 130 images in the osteoporosis category for a total of 1,424 images. When predicting low bone density (osteopenia or osteoporosis) versus normal bone density, sensitivity was 88.5%, specificity was 65.4%, overall accuracy was 80.8%, and the area under the curve was 0.891, at the standard threshold of 0.5. If optimizing for both sensitivity and specificity, at a threshold of 0.655, the model achieved a sensitivity of 84.6% at a specificity of 84.6%.

Conclusions: The findings represent a possible step toward more accessible, cost-effective, automated diagnosis and therefore earlier treatment of osteoporosis/osteopenia.

Type of study/level of evidence: Diagnostic II.

Keywords: Artificial intelligence; bone mineral density; machine learning; osteopenia; osteoporosis.