Development of Community Corrections From the Perspective of College Students' Mental Health

This study addresses mental health disparities in community correction systems by developing a novel psychological recognition algorithm that integrates heart rate variability and machine learning to objectively assess stress dynamics among university students—a population often overlooked in healthcare informatics. The algorithm overcomes limitations of traditional self-report methods, achieving 82.64% stress recognition accuracy (vs. 75% for support vector machine and 52% for ant colony optimization) with reduced error rates (20%), while addressing privacy via anonymized data. A mixed-methods analysis of 940 students (2009–2021) revealed gender- and grade-level disparities: 37.92% of women and 36.71% of lower-grade students exhibited mental health disorders, highlighting needs for gender-sensitive interventions. The dynamic mind–body equilibrium model links physiological responses (heart rate variability) to psychological benchmarks, enabling scalable, real-time stress detection. This work advances clinical decision support systems, telemedicine, and information technology applications in healthcare.