An Explainable Deterministic Framework for Preventive Health Risk Stratification with Multilingual Decision Support for Low-Resource Environments

DOI

https://www.doi.org/10.59256/indjcst.20260501023

Published In

Volume 5, Issue 1 (2026)

Published Online

January-April 2026

Pages

160-168

Article Type

Original Article

Check for updates

Preventive healthcare technologies play a crucial role in reducing the global burden of chronic diseases by enabling early awareness and timely lifestyle intervention. While contemporary health risk prediction systems frequently employ machine learning models, many such approaches operate as opaque black-box frameworks, limiting interpretability, reproducibility, and safe deployment in preventive public health contexts. This paper presents a formally defined deterministic preventive health risk stratification framework designed for multilingual and low-resource environments. The framework is grounded in clinically validated preventive health thresholds defined by the World Health Organization (WHO), American Diabetes Association (ADA), and American Heart Association (AHA). A formal deterministic risk function and algorithmic classification model are defined, analyzed for logical correctness, and evaluated for computational efficiency. The proposed system integrates a modular system architecture consisting of a weighted risk engine, classification module, explanation generator, multilingual translation layer, deterministic chatbot engine, and voice-based output interface. The mathematical formulation defines a cumulative weighted risk function and deterministic classification boundaries. Computational complexity analysis demonstrates linear-time execution, making the system suitable for low-resource deployment. Experimental validation using structured synthetic health profiles confirms deterministic reproducibility, boundary stability, multilingual mapping consistency, and algorithmic robustness. The framework prioritizes interpretability, accessibility, and responsible AI principles over predictive complexity, making it suitable for preventive awareness programs and community-level health decision support systems.