Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{199597,
        author = {Aryan Raina and Tanisha Sawalkar and Nisha Shetty and Anand Maha and Dr. Vivek Bhartiya},
        title = {HealthNet: A Framework for an AI-Powered Personalized Preventive Health Dashboard Aligned with the Ayushman Bharat Digital Mission},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {15681-15687},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=199597},
        abstract = {India’s Ayushman Bharat Digital Mission (ABDM) provides a national framework for digital health records through ABHA (Ayushman Bharat Health Account) identifiers, but most citizens lack a unified, intelligent interface that converts dispersed health data into actionable insights. This paper presents HealthNet, a framework and partial-prototype implementation of a personalized preventive health dashboard designed to align with ABDM principles. The proposed system combines a structured health questionnaire, a rule-based risk indicator panel, a context-aware Large Language Model (LLM) chatbot, and a Government Benefit Mapper that recommends eligible public health schemes. To validate the feasibility of the AI risk-scoring module, we trained and evaluated four supervised classifiers (Logistic Regression, Decision Tree, Random Forest, and Gradient Boosting) on the publicly available PIMA Indians Diabetes dataset using stratified 80/20 split with 5-fold cross-validation. The Gradient Boosting classifier achieved the highest ROC-AUC of 0.8278 with 75.97% test accuracy and an F1-score of 0.6337, demonstrating that the planned risk-scoring engine is technically viable and consistent with results reported in the literature on the same benchmark. The paper contributes (i) a modular system architecture for ABDM-aligned preventive care platforms, (ii) a working frontend prototype with chatbot and benefit-mapping modules, and (iii) a reproducible evaluation of the underlying risk-prediction approach. Limitations and a phased roadmap for live ABDM integration are discussed.},
        keywords = {Ayushman Bharat Digital Mission, ABHA, digital health, preventive care, health dashboard, machine learning, diabetes risk prediction, conversational AI, LLM chatbot, government scheme mapping.},
        month = {April},
        }