Background: Predicting the risk of osteoporotic fractures is vital for prevention. Traditional methods such as the Fracture Risk Assessment Tool (FRAX) model use clinical factors. This study examined the predictive power of the FRAX score and machine-learning algorithms trained on FRAX parameters. Methods: We analyzed the data of 2,147 female participants from the Ansan cohort study. The FRAX parameters employed in this study included age, sex (female), height and weight, current smoking status, excessive alcohol consumption (>3 units/d of alcohol), and diagnosis of rheumatoid arthritis. Osteoporotic fracture was defined as one or more fractures of the hip, spine, or wrist during a 10-year observation period. Machine-learning algorithms, such as gradient boosting, random forest, decision tree, and logistic regression, were employed to predict osteoporotic fractures with a 70:30 training-to-test set ratio. We evaluated the area under the receiver operating characteristic curve (AUROC) scores to assess and compare the performance of these algorithms with the FRAX score. Results: Of the 2,147 participants, 3.5% experienced osteoporotic fractures. Those with fractures were older, shorter in height, and had a higher prevalence of rheumatoid arthritis, as well as higher FRAX scores. The AUROC for the FRAX was 0.617. The machine-learning algorithms showed AUROC values of 0.662, 0.652, 0.648, and 0.637 for gradient boosting, logistic regression, decision tree, and random forest, respectively. Conclusion This study highlighted the immense potential of machine-learning algorithms to improve osteoporotic fracture risk prediction in women when complete FRAX parameter information is unavailable.

BACKGROUND: The relationship between serum homocysteine levels and non-alcoholic fatty liver disease is poorly understood. This study aims to investigate the sex-specific relationship between serum homocysteine level and non-alcoholic fatty liver disease in the Korean population. METHODS: This cross-sectional study included 150 men and 132 women who participated in medical examination programs in Korea from January 2014 to December 2014. Patients were screened for fatty liver by abdominal ultrasound and patient blood samples were collected to measure homocysteine levels. Patients that consumed more than 20 grams of alcohol per day were excluded from this study. RESULTS: The homocysteine level (11.56 vs. 8.05 nmol/L) and the proportion of non-alcoholic fatty liver disease (60.7% vs. 19.7%) were significantly higher in men than in women. In men, elevated serum homocysteine levels were associated with a greater prevalence of non-alcoholic fatty liver disease (quartile 1, 43.6%; quartile 4, 80.6%; P=0.01); however, in females, there was no significant association between serum homocysteine levels and the prevalence of non-alcoholic fatty liver disease. In the logistic regression model adjusted for age and potential confounding parameters, the odds ratio for men was significantly higher in the uppermost quartile (model 3, quartile 4: odds ratio, 6.78; 95% confidential interval, 1.67 to 27.56); however, serum homocysteine levels in women were not associated with non-alcoholic fatty liver disease in the crude model or in models adjusted for confounders. CONCLUSION: Serum homocysteine levels were associated with the prevalence of non-alcoholic fatty liver disease in men.
Cross-Sectional Studies ; Fatty Liver ; Female ; Homocysteine* ; Humans ; Korea ; Logistic Models ; Male ; Non-alcoholic Fatty Liver Disease* ; Odds Ratio ; Prevalence ; Sex Characteristics* ; Ultrasonography