AI-Based Model to Predict Bone Mineral Density from Hip and Spine X-Ray Images for Early Detection and Management of Osteoporosis in Adults

What this Trial Is About

Osteoporosis is a widespread bone condition that weakens bones and increases fracture risk, posing a major health and economic challenge globally. This research focuses on developing an artificial intelligence AI model to predict bone mineral density BMD from X-ray images, aiming to improve early osteoporosis detection especially in places like Bangladesh where the standard DEXA scan is scarce and costly. The goal is to create a reliable screening tool that can assist in preventing fractures by enabling earlier diagnosis and treatment. The study collects both retrospective and prospective data from patients undergoing hip and spine X-rays and DEXA scans at a radiology center in Bangladesh. Using convolutional neural networks, the AI model will analyze these X-ray images along with clinical data such as age, gender, menopausal status, and comorbidities to predict BMD. The models accuracy will be evaluated by comparing predictions to actual DEXA results using several statistical measures and cross-validation methods to ensure consistency. Participants will include adults of all genders with varying bone density levels, including normal, low bone mass, and osteoporosis. Data collected will include demographic, clinical history, imaging, and diagnostic results. The study will monitor primary outcomes like BMD measurements of hip and spine, along with secondary outcomes such as WHO osteoporosis classification and fracture risk assessments over about six months. The final AI tool is intended to support clinicians in identifying osteoporosis earlier and prioritizing patients for further testing, potentially improving care in resource-limited settings.

AI Model for Bone Mineral Density Prediction From X-Ray Images