A hip fracture can have severe consequences for the individual including a 50% risk of morbidity and a 25 % mortality within the first 12 months post-fracture. Current clinical methods that are used to identify individuals at high risk of fracturing their hip only consider the skeletal health of the person, which influences the force that is needed to break the hip. However, the vast majority of hip fractures in the elderly do not occur due to natural loading on the femur, but are the result of a fall from standing height or lower. This project is a collaboration between ETH-Zurich and the Icelandic Heart Association, Kopavogur, Iceland. The goal is to use machine learning to develop a novel algorithm for assessing the risk of fracturing the hip based on a combination of the patient data available at the Icelandic Heart Association and mechanical models developed at ETH Zurich. This algorithm will then be used in the second part of the project to explore the efficacy of available preventive treatment options for the individual.