<![CDATA[Early detection of mental health disorders poses a significant challenge in primary care, often hindered by conventional assessment methods that are subjective and time-consuming. This research aims to design and evaluate an intelligent system prototype for predicting mental health risks. Adopting the Cross-Industry Standard Process for Data Mining (CRISP-DM) framework , this study utilized 1,000 medical record datasets from Clinic. A predictive model was developed using the Random Forest algorithm, which is known for its robustness in handling complex data. Evaluation results indicate exceptional model performance, achieving a weighted accuracy of 99.67% on the test dataset. Feature importance analysis confirmed that social support, sleep quality, and physical activity variables are the most significant predictors. The prototype was successfully implemented as an interactive web application using Streamlit, demonstrating the feasibility of using machine learning as a rapid and accurate clinical decision support tool for mental health screening at the primary care level.]]>
Copyrights © 2025
