Comprehensive prediction of osteoporotic fractures through machine learning and DXA imaging

Project Summary

Osteoporosis is a common condition in older adults, leading to weakened bones and increased susceptibility to fractures. The disease often remains unnoticed until a debilitating fracture occurs, particularly in critical areas like the hip and spine. Currently, the primary diagnostic method for osteoporosis is Bone Mineral Density (BMD) measurement using DXA imaging. However, BMD alone has proven insufficient for accurately predicting fracture risk. This project proposes a novel approach to combine machine learning with advanced DXA image analysis, creating a comprehensive tool for fracture prediction. Our group successfully developed the tool with a smaller dataset, which will be used to analyze all CLSA baseline scans and derive fracture risk variables. Subsequent linkage with provincial health registries will enable validation by comparing derived risk scores with actual fracture occurrences. This project will be the first predictive tool for fracture risk to feature a large dataset.