Branching Minds: A Random Forest Approach for Mental Health Detection

Abstract

Mental health, encompassing emotional, psychological, and social well-being, plays a vital role in shaping how individuals think, feel, and act, as well as their ability to manage stress, build relationships, and make decisions. Despite its significance, mental health is often under prioritized compared to physical health due to persistent stigma, shame, and fear of judgment. Existing detection systems typically focus on a narrow range of disorders—such as depression—while overlooking others like anxiety, bipolar disorder, post-traumatic stress disorder (PTSD), and eating disorders. Furthermore, these systems frequently lack personalization and comprehensive data integration. To address these limitations, this study proposes an inclusive mental health detection system leveraging a Random Forest algorithm to enhance diagnostic accuracy and evaluate the severity of multiple mental health conditions through a structured and adaptive questionnaire. The system incorporates four key features: (1) a Questionnaire Session to identify potential issues, (2) a Severity Check to assess the seriousness of detected conditions, (3) a Doctor Recommendation System for personalized psychiatrist suggestions, and (4) an Online/Offline Appointment Booking module to facilitate timely access to care. By integrating machine learning with personalized care and user-friendly design, the proposed solution empowers individuals to proactively monitor their mental health, seek timely intervention, and reduce stigma. This approach offers a more accurate, inclusive, and supportive model for modern mental healthcare.