Predictive Modelling of Health Risks Using Logistic Regression for Personalized Dietary Recommendations

The prevalence of diet-related chronic diseases such as Type 2 Diabetes Mellitus (T2DM) and hypertension necessitates the development of intelligent nutritional systems that go beyond user preference to prioritize clinical safety. Traditional food recommender systems often suffer from a "health-blind" bias, optimizing primarily for taste or popularity. This paper proposes a novel Risk-Aware Diet Recommendation System (RADRS) that integrates Logistic Regression (LR) for interpretable health risk assessment with Linear Programming (LP) for dietary optimization. By training LR models on the NHANES and Pima Indians Diabetes datasets, the system calculates individual disease probabilities. These probabilities dynamically configure nutritional constraints—specifically modifying sodium, carbohydrate, and saturated fat limits—within an LP solver. The proposed architecture bridges the gap between predictive health analytics and personalized meal planning, ensuring that recommendations are both palatable and medically compliant. Keywords—Health Informatics, Logistic Regression, Recommender Systems, Linear Programming, Personalized Nutrition, Chronic Disease Management.

Computer Science and Engineering (Health Informatics, Machine Learning)

1. M. Elsweiler, et al., “Bringing the ‘healthy’ into food recommenders,” CEUR Workshop Proceedings, 2015. [Google Scholar] [Crossref]

2. S. Tarima, “Logistic Regression: A Mathematical Approach,” CTSI Biostatistics, 2011. [Google Scholar] [Crossref]

3. Y. Chen, et al., “Personalized Food Recommendation as Constrained Question Answering over a Large-scale Food Knowledge Graph,” in Proc. WSDM ’21, 2021. [Google Scholar] [Crossref]

4. G. Adomavicius and A. Tuzhilin, “Toward the next generation of recommender systems: A survey,” IEEE Transactions on Knowledge and Data Engineering, 2005. [Google Scholar] [Crossref]

5. L. Li, et al., “Health-Aware Food Recommendation Based on Knowledge Graph and Multi-Task Learning,” IEEE Access, 2023. [Google Scholar] [Crossref]

6. A. S. Abdalrada, et al., “Logistic Regression Model for Predicting the Progression of Diabetes,” Iraqi Journal for Computer Science and Mathematics, 2024. [Google Scholar] [Crossref]

7. Z. Xie, et al., “Building Risk Prediction Models for Type 2 Diabetes Using Machine Learning Techniques,” Preventing Chronic Disease, 2019. [Google Scholar] [Crossref]

8. G. Stigler, “The Cost of Subsistence,” Journal of Farm Economics, 1945. [Google Scholar] [Crossref]

9. Centers for Disease Control and Prevention (CDC), “National Health and Nutrition Examination Survey Data,” National Center for Health Statistics, 2017–2020. [Google Scholar] [Crossref]

10. N. V. Chawla, et al., “SMOTE: Synthetic Minority Over-sampling Technique,” Journal of Artificial Intelligence Research, 2002. [Google Scholar] [Crossref]

11. National Cancer Institute (NCI), “Healthy Eating Index–2020,” 2023. [Google Scholar] [Crossref]

12. UCI Machine Learning Repository, “Pima Indians Diabetes Database,” 2016. [Google Scholar] [Crossref]

13. National Heart, Lung, and Blood Institute (NHLBI), “Framingham Heart Study,” 2023. [Google Scholar] [Crossref]

14. D. Dooley, et al., “FoodOn: A harmonized food ontology,” NPJ Science of Food, 2018. [Google Scholar] [Crossref]

15. T. Fawcett, “An introduction to ROC analysis,” Pattern Recognition Letters, 2006. [Google Scholar] [Crossref]

• "Towards GDP to GEP-Centric Model: A Proposed GEP Index Framework and Its Application in Haryana"
• Physicochemical Analysis of Petroleum Products in Selected Depots in Calabar Metropolis Cross River State and The Effects on Motor Engine
• Impact of Employee Welfare Measures on Workforce Well-Being in SBI: Insights from the Public Banking Sector
• Problem of Small-Scale Farmers in Agricutlure Sector in Tirunelveli Taluk
• Globalization, Economic Development, and Ecological Footprint in Tunisia: A QARDL Approach