Predicting the risk of osteoporosis in older Vietnamese women using machine learning approaches.

Osteoporosis contributes significantly to health and economic burdens worldwide. However, the development of osteoporosis-related prediction tools has been limited for lower-middle-income countries, especially Vietnam. This study aims to develop prediction models for the Vietnamese population as well as evaluate the existing tools to forecast the risk of osteoporosis and evaluate the contribution of covariates that previous studies have determined to be risk factors for osteoporosis. The prediction models were developed to predict the risk of osteoporosis using machine learning algorithms. The performance of the included prediction models was evaluated based on two scenarios; in the first one, the original test parameters were directly modeled, and in the second the original test parameters were transformed into binary covariates. The area under the receiver operating characteristic curve, the Brier score, precision, recall and F1-score were calculated to evaluate the models' performance in both scenarios. The contribution of the covariates was estimated using the Permutation Feature Importance estimation. Four models, namely, Logistic Regression, Support Vector Machine, Random Forest and Neural Network, were developed through two scenarios. During the validation phase, these four models performed competitively against the reference models, with the areas under the curve above 0.81. Age, height and weight contributed the most to the risk of osteoporosis, while the correlation of the other covariates with the outcome was minor. Machine learning algorithms have a proven advantage in predicting the risk of osteoporosis among Vietnamese women over 50 years old. Additional research is required to more deeply evaluate the performance of the models on other high-risk populations.

Evaluation of community-based screening tools for the early screening of osteoporosis in postmenopausal Vietnamese women.

BACKGROUND: Osteoporosis affects people worldwide. However, there are few validated tools for the early screening of osteoporosis in Vietnam. We set out to evaluate the performance of the osteoporosis self-assessment tool for Asians (OSTA) and the osteoporosis screening tool for Chinese (OSTC) for the early screening of osteoporosis in postmenopausal Vietnamese women. METHODS: We analyzed retrospective data from 797 postmenopausal Vietnamese women. The bone mineral density (BMD) in the lumbar vertebrae (L1-L4) and the left and right femoral necks of all participants were measured using dual-energy X-ray absorptiometry (DXA). Osteoporosis was defined as the BMD (T-score) < -2.5. The OSTA and OSTC scores were calculated from the age and weight of participants. Receiver operating characteristic analysis was conducted to compare the performance of the two tools with the BMD measurements by DXA at different anatomical sites. RESULTS: The rates of osteoporosis determined by BMD varied between anatomical sites, and ranged from 43.4% to 54.7% in the lumbar vertebrae and 29.2% and 8.9% in the left and right femoral necks, respectively. For the vertebrae, the area under the curve (AUC) for OSTA ranged from 70.9% to 73.9% and for OSTC ranged from 68.7% to 71.6%. The predictive value of both tools was higher for femoral necks, with the AUC of OSTA for the left and right femoral necks being 80.0% and 85.8%, respectively. The corresponding figures for OSTC were 80.5% and 86.4%, respectively. The highest sensitivity and specificity of OSTA were 74.6% and 81.4%, while these figures for OSTC were 73.9% and 82.6%, respectively. CONCLUSION: OSTA and OSTC were shown to be useful self-assessment tools for osteoporosis detection in Vietnam postmenopausal women. Further research is encouraged to determine the applicability of tools for other populations and settings.