RESUMO
Fracture prediction is essential in managing patients with osteoporosis and is an integral component of many fracture prevention guidelines. We aimed to identify the most relevant clinical fracture risk factors in contemporary populations by training and validating short- and long-term fracture risk prediction models in 2 cohorts. We used traditional and machine learning survival models to predict risks of vertebral, hip, and any fractures on the basis of clinical risk factors, T-scores, and treatment history among participants in a nationwide Swiss Osteoporosis Registry (N = 5944 postmenopausal women, median follow-up of 4.1 yr between January 2015 and October 2022; a total of 1190 fractures during follow-up). The independent validation cohort comprised 5474 postmenopausal women from the UK Biobank with 290 incident fractures during follow-up. Uno's C-index and the time-dependent area under the receiver operating characteristics curve were calculated to evaluate the performance of different machine learning models (Random survival forest and eXtreme Gradient Boosting). In the independent validation set, the C-index was 0.74 [0.58, 0.86] for vertebral fractures, 0.83 [0.7, 0.94] for hip fractures, and 0.63 [0.58, 0.69] for any fractures at year 2, and these values further increased for longer estimations of up to 7 yr. In comparison, the 10-yr fracture probability calculated with FRAX Switzerland was 0.60 [0.55, 0.64] for major osteoporotic fractures and 0.62 [0.49, 0.74] for hip fractures. The most important variables identified with Shapley additive explanations values were age, T-scores, and prior fractures, while number of falls was an important predictor of hip fractures. Performances of both traditional and machine learning models showed similar C-indices. We conclude that fracture risk can be improved by including the lumbar spine T-score, trabecular bone score, numbers of falls and recent fractures, and treatment information has a significant impact on fracture prediction.
Fracture prediction is essential in managing patients with osteoporosis. We developed and validated traditional and machine learning models to predict short- and long-term fracture risk and identify the most relevant clinical fracture risk factors for vertebral, hip, and any fractures in contemporary populations. We used data from 5944 postmenopausal women in a Swiss Osteoporosis Registry and validated our findings with 5474 women from the UK Biobank. Our machine learning models performed well, with C-index values of 0.74 for vertebral fractures, 0.83 for hip fractures, and 0.63 for any fractures at year 2, and these values further increased for longer estimations of up to 7 years. In contrast, FRAX Switzerland had lower C-index values (0.60 for major fractures and 0.62 for hip fracture probabilities over 10 years). Key predictors identified included age, T-scores, prior fractures, and number of falls. We conclude that incorporating a broader range of clinical factors, as well as lumbar spine T-scores, fall history, recent fractures, and treatment information, can improve fracture risk assessments in osteoporosis management. Both traditional and machine learning models showed similar effectiveness in predicting fractures.