Adolescent depression and anxiety are major mental health concerns that can affect academic performance, emotional stability, social relationships, and long-term quality of life. Early identification of at-risk adolescents is essential because delayed intervention may lead to social isolation, self-harm, suicidal ideation, substance abuse, and chronic psychological difficulties. This study presents a machine learning-based approach for predicting mental health risks in adolescents, focusing on depression and anxiety. The proposed framework uses clinical, demographic, psychosocial, academic, behavioral, lifestyle, and digital indicators to classify adolescents into risk and non-risk categories. The study applies an Extreme Gradient Boosting model integrated with ReLU activation to improve nonlinear learning and enhance predictive accuracy. The methodology includes model initialization, residual computation, weak learner fitting, ReLU-based correction, iterative prediction updating, final risk probability estimation, and model evaluation. Performance is assessed using accuracy, precision, recall, and F1-score. Comparative results show that traditional Linear/Logistic Regression achieved the lowest performance, whereas SVM, ANN, and Random Forest showed improved predictive ability. The proposed XGBoost–ReLU model achieved the highest performance with 91.80% accuracy, 91.20% precision, 92.40% recall, and 91.79% F1-score. The high recall value indicates strong capability in identifying adolescents who are genuinely at risk, which is crucial for early counseling and preventive intervention. The findings suggest that advanced machine learning models can support data-driven mental health screening, counseling prioritization, and timely intervention planning. Future work should focus on larger datasets, clinical validation, explainable AI, privacy protection, and real-world deployment in schools and healthcare systems.
Adolescent Mental Health, Depression, Anxiety, Machine Learning, XGBoost–ReLU.
International Journal of Trend in Scientific Research and Development - IJTSRD having
online ISSN 2456-6470. IJTSRD is a leading Open Access, Peer-Reviewed International
Journal which provides rapid publication of your research articles and aims to promote
the theory and practice along with knowledge sharing between researchers, developers,
engineers, students, and practitioners working in and around the world in many areas
like Sciences, Technology, Innovation, Engineering, Agriculture, Management and
many more and it is recommended by all Universities, review articles and short communications
in all subjects. IJTSRD running an International Journal who are proving quality
publication of peer reviewed and refereed international journals from diverse fields
that emphasizes new research, development and their applications. IJTSRD provides
an online access to exchange your research work, technical notes & surveying results
among professionals throughout the world in e-journals. IJTSRD is a fastest growing
and dynamic professional organization. The aim of this organization is to provide
access not only to world class research resources, but through its professionals
aim to bring in a significant transformation in the real of open access journals
and online publishing.