<![CDATA[Adolescents are a vulnerable age group for mental disorders such as depression, anxiety, and stress. Early detection is crucial to enable timely and appropriate interventions. This study aims to design and develop a predictive artificial intelligence (AI) model capable of identifying potential mental health issues in adolescents. The research applies a quantitative experimental approach, collecting data through the locally validated DASS-21 questionnaire. The data were analyzed using Random Forest, Support Vector Machine, and Multilayer Perceptron algorithms, evaluated by accuracy, precision, recall, and F1-score metrics. The findings indicate that the Random Forest model achieved the highest accuracy at 87.4%. The system was designed with a user-friendly interface that delivers prediction results along with initial intervention recommendations. This study offers a significant contribution to preventive efforts in adolescent mental health through adaptive, accurate, and ethical AI-based technology.]]>
Copyrights © 2025
