Optimization of academic performance and mental health in college students through an AI-driven personalized physical exercise and mindfulness intervention system

This research examines an artificial intelligence-driven personalized intervention system that integrates physical exercise and mindfulness practices to support academic performance and psychological wellbeing among university students in eastern China. A 16-week controlled intervention study enrolled 328 undergraduate students from three comprehensive universities, comparing three conditions: AI-personalized interventions (n = 110), standardized interventions (n = 108), and controls (n = 110). The AI system employed machine learning algorithms to analyze multidimensional student data and generate tailored recommendations. Results indicated that the AI-personalized group was associated with larger improvements across academic metrics (10.28% GPA increase, 95% CI [8.94, 11.62], d = 0.89, p < 0.001), psychological parameters (36.7% stress reduction, 95% CI [33.2, 40.1], d = 1.42, p < 0.001), and physiological indicators (28.4% HRV improvement, 95% CI [24.8, 32.0], d = 1.13, p < 0.001) compared to standardized interventions and controls. Regression analysis identified intervention adherence, sleep quality improvement, and stress reduction as factors associated with outcomes. The hybrid neural network architecture combining student feature analysis, exercise matching, and mindfulness adaptation offers a framework for personalized health interventions in academic settings. These findings, while promising, are specific to Chinese university contexts with particular cultural and technological characteristics, and cross-cultural validation remains necessary before broader generalization.