Sistema explicable de detección preventiva de indicadores de riesgo en salud mental adulta mediante aprendizaje automático multisalida y agentes de inteligencia artificial generativa a partir del dataset NSDUH 2024 / Exp
This project presents an explainable academic prototype for the preventive detection of four indicators related to adult mental health using the National Survey on Drug Use and Health (NSDUH) 2024. The final system combines a hybrid Machine Learning and Deep Learning predictive solution, SHAP-based explainability, and a generative AI agent layer integrating structured validation, retrieval-augmented generation (RAG), LangGraph, Mistral, and guardrails. The repository includes the five main project notebooks, experimental results, final inference files, reproducibility documentation, productization components, and a local demonstration dashboa
Resource information
- Format
- zip
- Original repository
- 22277709
- DOI
- 10.5281/zenodo.22277709
- Credit basis
- Creators in Zenodo record metadata
- Access
- Open files available from the original Zenodo deposit
- Last checked
- Nov 5, 2026
- License
- mit-license
- Last record update
- Nov 5, 2026
About this resource
This project presents an explainable academic prototype for the preventive detection of four indicators related to adult mental health using the National Survey on Drug Use and Health (NSDUH) 2024. The final system combines a hybrid Machine Learning and Deep Learning predictive solution, SHAP-based explainability, and a generative AI agent layer integrating structured validation, retrieval-augmented generation (RAG), LangGraph, Mistral, and guardrails. The repository includes the five main project notebooks, experimental results, final inference files, reproducibility documentation, productization components, and a local demonstration dashboard. The system is intended exclusively for academic and preventive research purposes and does not constitute a clinical diagnostic tool.