A clinical prediction model for 10-year risk of self-reported osteoporosis diagnosis in pre- and perimenopausal women.

Abstract

The aim of this study was to incorporate demographic, metabolic, and imaging risk factors into a model for long-term prediction of self-reported osteoporosis diagnosis. This was a secondary analysis of 1685 patients from the longitudinal Study of Women's Health Across the Nation using data collected between 1996 and 2008. Participants were pre- or perimenopausal women between 42 and 52 years of age. A machine learning model was trained using 14 baseline risk factors-age, height, weight, body mass index, waist circumference, race, menopausal status, maternal osteoporosis history, maternal spine fracture history, serum estradiol level, serum dehydroepiandrosterone level, serum thyroid-stimulating hormone level, total spine bone mineral density, and total hip bone mineral density. The self-reported outcome was whether a doctor or other provider had told participants they have osteoporosis or treated them for osteoporosis. At 10-year follow-up, a clinical osteoporosis diagnosis was reported by 113 (6.7%) women. Area under the receiver operating characteristic curve of the model was 0.83 (95% confidence interval, 0.73-0.91) and Brier score was 0.054 (95% confidence interval, 0.035-0.074). Total spine bone mineral density, total hip bone mineral density, and age had the largest contributions to predicted risk. Using two discrimination thresholds, stratification into low, medium, and high risk, respectively, was associated with likelihood ratios of 0.23, 3.2, and 6.8. At the lower threshold, sensitivity was 0.81, and specificity was 0.82. The model developed in this analysis integrates clinical data, serum biomarker levels, and bone mineral densities to predict 10-year risk of osteoporosis with good performance.