Comparison of Machine Learning Models for Predicting Dyslipidemia in Korean Postmenopausal Women : Analysis Using the 1st Year Data of the 9th Korea National Health and Nutrition Examination Survey

This study compared machine learning models for predicting dyslipidemia in postmenopausal women using data from the first yaer of the 9th Korea National Health and Nutrition Examination Survey. A total of 1,115 postmenopausal women were analyzed after excluding missing values. Participant characteristics were analyzed using SPSS 25.0, while machine learning analysis was conducted with the Orange 3.35 program, applying logistic regression, random forest, and gradient boosting models. Among the participants, 54 percent had dyslipidemia. The random forest model demonstrated the highest performance, achieving a precision of 0.85 and a recall of 0.82, while the gradient boosting model had the highest AUC of 0.89, indicating strong classification capability. Key predictive factors included occupation, age, obesity, family history of chronic diseases, and breastfeeding history. This study suggests that random forest and gradient boosting models can effectively predict dyslipidemia in postmenopausal women, providing essential data for addressing health concerns in this population.