Machine learning models for predicting risk of depression in Korean college students: Identifying family and individual factors

Abstract

BackgroundDepression is one of the most prevalent mental illnesses among college students worldwide. Using the family triad dataset, this study investigated machine learning (ML) models to predict the risk of depression in college students and identify important family and individual factors.MethodsThis study predicted college students at risk of depression and identified significant family and individual factors in 171 family data (171 fathers, mothers, and college students). The prediction accuracy of three ML models, sparse logistic regression (SLR), support vector machine (SVM), and random forest (RF), was compared.ResultsThe three ML models showed excellent prediction capabilities. The RF model showed the best performance. It revealed five significant factors responsible for depression: self-perceived mental health of college students, neuroticism, fearful-avoidant attachment, family cohesion, and mother's depression. Additionally, the logistic regression model identified five factors responsible for depression: the severity of cancer in the father, the severity of respiratory diseases in the mother, the self-perceived mental health of college students, conscientiousness, and neuroticism.DiscussionThese findings demonstrated the ability of ML models to accurately predict the risk of depression and identify family and individual factors related to depression among Korean college students. With recent developments and ML applications, our study can improve intelligent mental healthcare systems to detect early depressive symptoms and increase access to mental health services.

Machine learning models predict the emergence of depression in Argentinean college students during periods of COVID-19 quarantine

“…SVM has consistently been identified as a high-performing algorithm in predicting depression among students (see, e.g., 49 – 51 ). However, RF also emerged as the top-performing algorithm in some studies (see, e.g., 50 – 52 ), which contrasts with the present findings where it displayed some signs of overfitting and exhibited comparative lower performance. The observed overfitting in the RF algorithm in both classification and regression tasks within this study can be attributed to various factors.…”

Machine Learning Models Predict the Emergence of Depression in Argentinean College Students during Periods of COVID-19 Quarantine

“…SVM has consistently been identified as a high-performing algorithm in predicting depression among students (see, e.g., Choudhury et al, 2019;Gil et al, 2022;Qasrawi et al, 2022). However, RF also emerged as the top-performing algorithm in some studies (see, e.g., Gil et al, 2022;Qasrawi et al 2022;Rois et al, 2021), which contrasts with the present findings where it examination of multi-versus univariate models revealed two dominant features (depression at T1 and anxiety), with the remaining features exhibiting limited significance. As for the discrepancies in algorithm performance between different studies, these may be ascribed to several factors.…”

“…As for the ML algorithms performance in this study, both SVM/SVR and LogReg/RR demonstrated the best results in both classification and regression tasks. SVM has consistently been identified as a high-performing algorithm in predicting depression among students (see, e.g., Choudhury et al, 2019; Gil et al, 2022; Qasrawi et al, 2022). However, RF also emerged as the top-performing algorithm in some studies (see, e.g., Gil et al, 2022; Qasrawi et al 2022; Rois et al, 2021), which contrasts with the present findings where it displayed overfitting and exhibited comparative lower performance.…”

“…SVM has consistently been identified as a high-performing algorithm in predicting depression among students (see, e.g., Choudhury et al, 2019; Gil et al, 2022; Qasrawi et al, 2022). However, RF also emerged as the top-performing algorithm in some studies (see, e.g., Gil et al, 2022; Qasrawi et al 2022; Rois et al, 2021), which contrasts with the present findings where it displayed overfitting and exhibited comparative lower performance. The observed overfitting in the RF algorithm in both classification and regression tasks within this study can be attributed to various factors.…”

Artificial intelligence significantly facilitates development in the mental health of college students: a bibliometric analysis

“…As AI rapidly transforms the landscape of medicine, academic research on the intersection of AI and college student mental health has significantly increased in recent years ( Gil et al, 2022 ; Wang, 2023 ). This necessitates a comprehensive review of the research trends in this field.…”