Intelligent Assessment of College Students' Mental Health based on Hybrid Decision Tree Algorithm

Mental health issues in college students, such as stress, anxiety, and depression, have a strong influence on academic achievement and quality of life. Conventional screening procedures are usually slow, subjective, and inefficient at early recognition. To solve this, an intelligent hybrid model integrating Decision Trees, Gradient Boosting (Groves), Support Vector Machines (SVM), and Logistic Regression (LR) is suggested for accurate and automated mental health evaluation. Decision Trees offer explainability and accommodate mixed data types, whereas ensemble approaches such as Groves add predictive strength. SVM enhances classification resistance, and LR provides probabilistic information. The hybrid model attains remarkable performance with 96.4% accuracy, 96.1% precision, and 96.5% recall, surpassing traditional methods. Important measures like F1-score (96.0%) and specificity (95.3%) provide accurate and unbiased prediction. Integration of real-time data and adaptive learning additionally improve diagnostic accuracy over time. This method facilitates early intervention while providing open, rule-governed rationale for evaluations to benefit counselors and universities. Utilizing hybrid machine learning, the system improves student welfare monitoring without violating ethical requirements, showing the promise of intelligent systems in mental health services.