Abstract
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.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
