HabituraX: A Comprehensive Machine Learning System for Lifestyle-Based Disease Risk Prediction

Year : 2026 | Volume : 13 | Issue : 02 | Page : 12 23
By

V.S. Aarsha,

Ankita Joshi,

Shivali,

Gurmillan Singh,

Dayal Chandra Sati,

  1. Student, Department of Computer Science and Engineering, Apex-Institute of Technology, Punjab, India
  2. Student, Department of Computer Science and Engineering, Apex-Institute of Technology, Punjab, India
  3. Student, Department of Computer Science and Engineering, Apex-Institute of Technology, Punjab, India
  4. Student, Department of Computer Science and Engineering, Apex-Institute of Technology, Punjab, India
  5. Assistant Professor, Department of Computer Science and Engineering, Apex-Institute of Technology, Punjab, India

Abstract

The increased prevalence of lifestyle-related non-communicable diseases such as diabetes, obesity, and sleep disorders in the world requires the development of proactive risk-stratification tools. Recent studies indicate that there is a significant shift in favor of multimodal artificial intelligence (AI) models that comprise deep learning models such as CNNs and LSTMs, which often demonstrate high predictive accuracy, along with complex ensemble approaches. However, the necessary clinical interpretability to perform open medical decision-making and engage directly with the user is typically missing in these “black-box” models. This paper introduces HabituraX, an interpretable and modular AI system that can use lifestyle traits, which can be altered, to provide probabilistic results on the likelihood of multiple chronic diseases despite the absence of specific clinical information. The proposed solution adopts a multi-model implementation whereby varying logistic regression models are developed to represent each separate state of illness. The approach places more emphasis on the feature-level transparency than on the complexity of the models. Besides user-friendly inputs such as BMI, physical activity, and sleep time, a new feature, the carbohydrate-to-fiber ratio that better reflects the glycemic effects of raw dietary items, is included in the methodology. Probability percentages of risk in diabetes, obesity, and sleep disorders are visibly clear through the application of separate logistic regression pipelines, and they make it easier to select features that are specific to a disease, which provides the user with an understanding of how personal lifestyle choices directly influence the overall profile of risk of health problems. This paper demonstrates that bridging the gap between high-dimensional health informatics and personal health management can be effectively addressed by modular AI implementation and a focus on clinical interpretability. The paradigm offers a routine, proactive approach to early illness prevention as it focuses on modifiable behavior changes as opposed to fixed biomarkers, which is all in line with the principles of preventive medicine.

 

Keywords: Artificial intelligence, lifestyle diseases, National Health and Nutrition Examination Survey (NHANES), logistic regression, interpretability, feature engineering, multi-model architecture, preventive healthcare

[This article belongs to Journal of Multimedia Technology & Recent Advancements ]

How to cite this article: V.S. Aarsha, Ankita Joshi, Shivali, Gurmillan Singh, Dayal Chandra Sati. HabituraX: A Comprehensive Machine Learning System for Lifestyle-Based Disease Risk Prediction. Journal of Multimedia Technology & Recent Advancements. 2026; 13(02):12-23.
How to cite this URL: V.S. Aarsha, Ankita Joshi, Shivali, Gurmillan Singh, Dayal Chandra Sati. HabituraX: A Comprehensive Machine Learning System for Lifestyle-Based Disease Risk Prediction. Journal of Multimedia Technology & Recent Advancements. 2026; 13(02):12-23. Available from: https://journals.stmjournals.com/jomtra/article=2026/view=259940

References

  1. Fahmy AM. Exploring the role of AI in predicting chronic disease progression: Diabetes and cardiovascular diseases. Premier J Public Health. 2025;2(3). doi:10.70389/PJPH.100021.
  2. Huang W, Ying TW, Chin WLC, Baskaran L, Marcus OEH, Yeo KK, et al. Application of ensemble machine learning algorithms on lifestyle factors and wearables for cardiovascular risk prediction. Sci Rep. 2022;12(1):1033. doi:10.1038/s41598-021-04649-y. PMID:35058500.
  3. Patil M, Lobo VB, Puranik P, Pawaskar A, Pai A, Mishra R. A proposed model for lifestyle disease prediction using support vector machine. In: 9th International Conference on Computing, Communication and Networking Technologies (ICCCNT); 2018. p. 1-6. doi:10.1109/ICCCNT.2018.8493897.
  4. Polineni TNS, Ganti VKAT, Maguluri KK, Rani PR. AI-driven analysis of lifestyle patterns for early detection of metabolic disorders. J Comput Anal Appl. 2024;33(8):1338-52.
  5. Shahbazi Z, Nowaczyk S. Towards personalized cardiometabolic risk prediction: A fusion of exposome and AI. Heliyon. 2025;11:e40859. doi:10.1016/j.heliyon.2024.e40859. PMID:39834417.
  6. Yadav Y, Tajne S, Malhotra V. AI-powered mobile applications for early detection of chronic diseases: A federated learning approach. In: International Conference on ICT for Sustainable Development. Cham: Springer Nature Switzerland; 2025. p. 48-56.
  7. Manik MM, Hossain S, Bhuiyan MM, Ahmed MK, Miah MA, Saimon AS. Leveraging AI-powered predictive analytics for early detection of chronic diseases: A data-driven approach to personalized medicine. Nanotechnol Perceptions. 2021;17(3):269-88. doi:10.62441/nano-ntp.v17i3.5444.
  8. Yang Z, Xu Y, Wang J, Li W, Zhang X, Pan H. Application of artificial intelligence in medical risk prediction: Bibliometric analysis. Digit Health. 2025;11:20552076251380652. doi:10.1177/20552076251380652. PMID:40979694.
  9. Rojek I, Kotlarz P, Kozielski M, Jagodziński M, Królikowski Z. Development of AI-based prediction of heart attack risk as an element of preventive medicine. Electronics. 2024;13:272. doi:10.3390/electronics13020272.
  10. Aravazhi PS, Gunasekaran P, Benjamin NZY, Thai A, Chandrasekar KK, Kolanu ND, et al. The integration of artificial intelligence into clinical medicine: Trends, challenges, and future directions. Dis Mon. 2025;71(6):101882. doi:10.1016/j.disamonth.2025.101882. PMID:40140300.
  11. Muse ED, Topol EJ. Transforming the cardiometabolic disease landscape: Multimodal AI-powered approaches in prevention and management. Cell Metab. 2024;36:670-83. doi:10.1016/j.cmet.2024.02.002. PMID:38428435.
  12. Chen SF, Loguercio S, Chen KY, Lee SE, Park JB, Liu S, et al. Artificial intelligence for risk assessment on primary prevention of coronary artery disease. Curr Cardiovasc Risk Rep. 2023;17(12):215-31. doi:10.1007/s12170-023-00731-4.
  13. Dogan A, Li Y, Peter Odo CP, Sonawane K, Lin Y, Liu C. A utility-based machine learning-driven personalized lifestyle recommendation for cardiovascular disease prevention. J Biomed Inform. 2023;141:104342. doi:10.1016/j.jbi.2023.104342. PMID:36963450.
  14. Mohsen F, Al-Absi HRH, Yousri NA, El Hajj N, Shah Z. A scoping review of artificial intelligence-based methods for diabetes risk prediction. NPJ Digit Med. 2023;6(1):197. doi:10.1038/s41746-023-00933-5. PMID:37880301.
  15. Ganesh CS, Kishore RS, Goud KV, Kethireddy B, Rout SK, Reddy SR. Data-driven disease prediction and lifestyle monitoring system. In: 1st International Conference on Cognitive, Green and Ubiquitous Computing (IC-CGU); 2024. p. 1-8. doi:10.1109/IC-CGU58078.2024.10530759.
  16. Das A, Choudhury D, Sen A. A collaborative empirical analysis on machine learning based disease prediction in health care system. Int J Inf Technol. 2024;16(1):261-70. doi:10.1007/s41870-023-01556-5.
  17. Sharma A, Gupta S, Dubey SK. Analysis on symptoms driven disease risk assessment using artificial intelligence approach. In: 11th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO); 2024. p. 1-7. doi:10.1109/ICRITO61523.2024.10522221.
  18. Lan GC, Lee CH, Lee YY, Tseng VS, Wu JS, Chin CY, et al. Disease risk prediction by mining personalized health trend patterns: A case study on diabetes. In: Conference on Technologies and Applications of Artificial Intelligence; 2012. p. 27-32. doi:10.1109/TAAI.2012.53.
  19. Khan N, Deshpande N, Singh P, Kadam P. A review of AI-based health prediction using Apple Watch and Fitbit data. Discov Appl Sci. 2025;7(10):1217. doi:10.1007/s42452-025-07783-8.
  20. Ganie SM, Malik MB. A lifestyle-based fuzzy-enhanced ANN model for early prediction of type 2 diabetes and personalized management in the North Indian population. Diagnostics (Basel). 2025;15:3139. doi:10.3390/diagnostics15243139. PMID:41464140.

 

Regular Issue Subscription Review Article
Volume 13
Issue 02
Received 24/06/2026
Accepted 29/07/2026
Published 10/08/2026
Publication Time 47 Days

Login

My IP

PlumX Metrics

Support