Comparison of the performance of machine learning-based algorithms for predicting depression and anxiety among University Students in Bangladesh: A result of the first wave of the COVID-19 pandemic

Abstract

Introduction: The purpose of this research was to predict mental illness among university students using various machine learning (ML) algorithms. Methods: A structured questionnaire-based online survey was conducted on 2121 university students (private and public) living in Bangladesh. After obtaining informed consent, the participants completed a web-based survey examining sociodemographic variables and behavioral tests (including the Patient Health Questionnaire (PHQ-9) scale and the Generalized Anxiety Disorder Assessment-7 scale). This study applied six well-known ML algorithms, namely logistic regression, random forest (RF), support vector machine (SVM), linear discriminate analysis, K-nearest neighbors, Naïve Bayes, and which were used to predict mental illness among university students from Dhaka city in Bangladesh. Results: Of the 2121 eligible respondents, 45% were male and 55% were female, and approximately 76.9% were 21–25 years old. The prevalence of severe depression and severe anxiety was higher for women than for men. Based on various performance parameters, the results of the accuracy assessment showed that RF outperformed other models for the prediction of depression (89% accuracy), while SVM provided the best result than other models for the prediction of anxiety (91.49% accuracy). Conclusion: Based on these findings, we recommend that the RF algorithm and the SVM algorithm were more moderate than any other ML algorithm used in this study to predict the mental health status of university students in Bangladesh (depression and anxiety, respectively). Finally, this study proposes to apply RF and SVM classification when the prediction of mental illness status is the core interest.