AAI_2025_Capstone_Chronicles_Combined

MENTAL HEALTH RISK DETECTION USING ML​

​

​

​

​

3

We aim to identify behavioral and environmental factors associated with mental health conditions and use AI to predict individuals at risk of experiencing mental illness. By analyzing personal, social, and occupational attributes, such as work-related stress, isolation, or economic hardship, we aim to develop a supervised machine learning model that identifies early risk indicators to support timely intervention. The core question is: Can we build an AI model that accurately predicts individuals at risk of mental health conditions using survey-based attributes? Mental health challenges are common yet often untreated due to stigma, limited access, or delayed identification. According to the World Health Organization (2023), depression alone affects over 280 million people globally. Early detection can improve outcomes, reduce personal suffering, and decrease the societal burden of untreated mental illness. This project uses AI to analyze structured survey data and support more proactive, data-driven mental health strategies in institutions such as schools and workplaces. The model is intended for mental health professionals, school counselors, wellness coordinators, and researchers. It provides predictive insights to screen for mental health risk and prioritizes follow-up care. Universities and employers could use the tool to support well-being programs through anonymous, voluntary surveys. Researchers and policymakers may also use aggregated outputs to monitor trends and allocate resources more effectively. This tool is designed to support clinical decisions, not replace them. We are using the Mental Health Dataset from Kaggle (Jikadara, 2024), which covers demographics, psychological indicators, sentiment features, and occupational context. In a real-world system, this data could be obtained from digital wellness questionnaires, school surveys, or mobile applications. Live systems must adhere to HIPAA compliance, protect user identity, obtain informed consent, and ensure the ethical handling of sensitive data.

203