Key points are not available for this paper at this time.
Mental health issues are increasingly affecting peo-ple worldwide. Efforts are taken to address these issues, however, similar importance is not always taken for all demographics. Medical students are particularly susceptible to being impacted by anxiety, depression, and burnout due to the intense pressures of their educational and practical settings. These mental health problems become worse because of the demanding workload of medical school, the emotional toll of patient care, and the competitive atmosphere. These problems have adverse effects on student's academic performance, personal wellness, and future prospective role as empathetic healthcare providers, which re-inforces the need for introduction of special care and interventions in medical education. This study uses a dataset of 886 Swiss medical students to automate the screening procedure for anxiety, depression, and burnout using Machine Learning (ML) and Deep Learning (DL) approaches. The analysis juxtaposes the performance of two advanced computational models: an Ensemble classifier, integrating Random Forest (RF), Naive Bayes (NB), and Light Gradient-Boosting Machine (LightGBM), and a Deep Neural Network (DNN). The study's cornerstone lies in its evaluation of these models' predictive prowess, underpinned by meticulous feature selection via Information Gain and an ablation study. The DNN model emerges as a frontrunner demonstrating accuracy rates of 81.4 % for depression, 76.65 % for anxiety, and 73.59 % for burnout. Comparative analyses further validate the DNN's efficacy against the Ensemble classifier, thereby providing a promising method for automated clinical diagnosis for mental health professionals. Thus, the ultimate objective is to bridge the gap between undetected mental health issues and accessible, effective care highlighting the indispensable role of Artificial Intelligence (AI) in shaping the future of mental health services.
Rashid et al. (Mon,) studied this question.