• Dr.S.Shiva Prasad
• M.V Lokesh
• Ch Sindhu Rani
• S Pranay
• G. Sai Teja

Depression, a leading global mental health challenge, necessitates accurate and transparent diagnostic tools to address limitations in traditional methods such as subjectivity and accessibility. This study proposes an interpretable machine learning framework leveraging CatBoost for high-accuracy classification and SHAP (SHapley Additive exPlanations) for model explainability. Utilizing a multimodal dataset of PHQ-9 questionnaire responses, wearable device metrics (sleep duration, activity levels), and demographic variables, the model achieved 93% accuracy and an AUC-ROC of 0.96. SHAP analysis identified critical predictors, including suicidal ideation (PHQ-9 Item 9), sleep deprivation, and social isolation frequency, aligning with clinical diagnostic criteria. The integration of explainable AI bridges the gap between data- driven insights and clinician trust, offering a scalable solution for early depression detection.

Depression classification, CatBoost, SHAP explainability, PHQ-9, Interpretable machine learning, Clinical decision support, Mental health analytics

"Depression Status Classification Using CatBoost and SHAP Algorithms", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 3, page no.j443-j449, March-2025, Available :http://www.jetir.org/papers/JETIR2503958.pdf

"Depression Status Classification Using CatBoost and SHAP Algorithms", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 3, page no. ppj443-j449, March-2025, Available at : http://www.jetir.org/papers/JETIR2503958.pdf