Life · 4 authors, 3 centres
This summary was generated by AI from a single paper. It has not been reviewed by a clinician and is not clinical advice. Verify against the source before acting on it.
This retrospective study analyzed 222 patient records to test whether machine learning models could predict low-energy osteoporotic fractures using clinical and lifestyle risk factors. The analysis identified age, chronic kidney disease, neck T-score, and serum phosphate level as the most important risk factors, but the models achieved only moderate predictive performance.
The study retrospectively analyzed documentation from 222 osteoporosis clinic patients (206 women, 16 men) to identify risk factors for low-energy fractures and test predictive models. Using logistic regression and recursive feature elimination, a ranking identified age, chronic kidney disease, neck T-score, and serum phosphate level as the most important factors. Key limitations include the small, single-center sample and the models' unsatisfactory predictive performance.
