Predicting Depression om Adults using a Random Forest Model : Focusing on the 8th Korean National Health and Nutrition Examination Survey 랜덤 포레스트 모델을 이용한 성인의 우울증 예측원문보기
This study attempted to predict depression in adults using a random forest model, a type of machine learning. The research subjects for training the model were 1,086 subjects with depression for more than 2 weeks and 8,826 subjects without depression, totaling 9,896 subjects from the 8th Korea Natio...
This study attempted to predict depression in adults using a random forest model, a type of machine learning. The research subjects for training the model were 1,086 subjects with depression for more than 2 weeks and 8,826 subjects without depression, totaling 9,896 subjects from the 8th Korea National Health and Nutrition Examination Survey (2019-2021), and 20 input variables. For model building and evaluation in this study, all code was written in Python 3.9.7, and packages SciPy 1.614, ELI5, and Scikit-learn 1.2.2 were used for statistics and model building. The analysis evaluated the correlations, means, standard deviations, frequencies, proportions, and values of the variables affecting the prediction of the model and the overall performance of the model. The results showed that stress, gender, occupation, physical activity, and health status were identified as factors affecting the prediction of depression, with stress being the most influential (0.099±0.008; 0.081±0.008). The overall performance (AUC) of the model was 0.920 (95% CI, 0.919-0.921) with an accuracy of 0.921 (95% CI, 0.920-0.922). The built model was able to detect patterns of depression and could support rapid and accurate decisions in screening for depression in clinical settings.
This study attempted to predict depression in adults using a random forest model, a type of machine learning. The research subjects for training the model were 1,086 subjects with depression for more than 2 weeks and 8,826 subjects without depression, totaling 9,896 subjects from the 8th Korea National Health and Nutrition Examination Survey (2019-2021), and 20 input variables. For model building and evaluation in this study, all code was written in Python 3.9.7, and packages SciPy 1.614, ELI5, and Scikit-learn 1.2.2 were used for statistics and model building. The analysis evaluated the correlations, means, standard deviations, frequencies, proportions, and values of the variables affecting the prediction of the model and the overall performance of the model. The results showed that stress, gender, occupation, physical activity, and health status were identified as factors affecting the prediction of depression, with stress being the most influential (0.099±0.008; 0.081±0.008). The overall performance (AUC) of the model was 0.920 (95% CI, 0.919-0.921) with an accuracy of 0.921 (95% CI, 0.920-0.922). The built model was able to detect patterns of depression and could support rapid and accurate decisions in screening for depression in clinical settings.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.