A machine learning-based tool for predicting depression in college students: An example of interdisciplinary integration for future skills development : Research project final report

Abstract

This project presents a machine learning-based approach for depression detection in college students, aiming to create an innovation that serves as an example of interdisciplinary integration. By addressing the limitations of traditional methods such as visiting mental health experts or completing standard questionnaires, the proposed approach offers a more comfortable and efficient screening process. The model is trained on demographic information, physical health problems, relationships, and university life aspects, excluding direct mental health questions. The results demonstrate over 90% prediction accuracy, highlighting the potential of machine learning-based approaches for depression screening. The success of the predictive model can be attributed to the integration of knowledge from the fields of information technology and health science. User satisfaction survey on evaluating the predictive model as a learning tool for interdisciplinary integration was also conducted. The study population included a sample of fifty nursing students enrolled at Mae Fah Luang University. High user satisfaction ratings further support the success of this project.