An adaptive reward-based behavioral model to optimize academic stress level in medical students

Academic performance plays an important role in the domain of healthcare, as institutions aim to balance learning effectively by considering student wellness. In the medical field, academic stress is increasing every day, which affects the grade as well as the mental health of the student. There are several classic approaches for forecasting academic achievement, but data adaptability and privacy remain issues when using regulations and standards like FERPA and GDPR. This proposed study Adaptive Reward-Based Behavioral Tuning Model (ARBT) approach, is an integrated model of Federated Learning (FL) and Reinforcement Learning (RL) for academic performance prediction, along with concise data confidentiality. An open-source dataset, the Medical Student Mental Health, includes measures on mental wellness, academic performance, and lifestyle patterns. The proposed model obtains a correctness rating of 90.4%, with corresponding precision of 88%, recall of 91%, F1-score of 88.9%, and MSE of 0.14. The suggested model's success is measured by students' anxiety management and involvement rates, which are 46.87% and 4.77%, respectively. These findings demonstrate the framework's efficacy in anticipating and stress optimization variables, illuminating a significant advancement in the healthcare sector.