Fragility fractures are a major and growing health burden, with significant personal and economic consequences, requiring urgent action for improved prevention and early identification.
In a new study from McMaster University, published in Scientific Reports, researchers compared multiple machine learning models to predict fragility fracture risk using established clinical and lifestyle risk factors. The work also highlights the key factors that are potentially associated with fracture risk.
The study was led by ASM (Sayem) Borhan, assistant professor in the Department of Health Research Methods, Evidence, and Impact (HEI), and member of the McMaster Institute for Research on Aging (MIRA). Accompanying HEI contributors include distinguished university professors, Parminder Raina and Lehana Thabane, who are also affiliated with MIRA as Director and member, respectively.
The findings will help identify individuals at higher risk and reinforce opportunities for earlier, targeted prevention strategies that could reduce both patient and health system impacts.
The study was partially funded by a fellowship award from Osteoporosis Canada and the Canadian Multicentre Osteoporosis Study.
Visit the webpage for the Department of Health Research Methods, Evidence, and Impact (HEI) on the McMaster website for the full story and to learn more: https://hei.healthsci.mcmaster.ca/researchers-use-machine-learning-to-better-predict-fractures-caused-by-weak-bones/
