International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | Machine Learning-Based Early Prediction of Type 2 Diabetes Mellitus using Clinical and Demographic Features: A Comparative Analysis of Classification Models |
|---|---|
| ABSTRACT | Type 2 diabetes mellitus (T2DM) is a major chronic metabolic disease in which delayed identification can increase the risk of vascular, renal, neurological and cardiovascular complications. This study evaluates the usefulness of supervised machine learning for classifying diabetes status from demographic, behavioural and routinely available clinical variables. The analysis used a publicly available Diabetes Prediction Dataset containing 100,000 observations before cleaning. After the removal of 3,854 duplicate records, 96,146 observations remained. Predictors included gender, age, hypertension, heart disease, smoking history, body mass index (BMI), HbA1c level and blood-glucose level, with diabetes status as the binary target. Categorical variables were numerically encoded, numerical predictors were scaled, and an 80:20 hold-out strategy with random state 42 was used for model development and testing. Logistic Regression, Decision Tree and Random Forest classifiers were compared using confusion-matrix-derived accuracy, precision, sensitivity, specificity and F1-score. On the reported test set of 19,230 observations, the Decision Tree achieved the highest overall accuracy (97.06%) and F1-score (80.32%) with 100% specificity, whereas Random Forest achieved the highest sensitivity for diabetes-positive cases (69.09%) and the fewest false negatives (532). Logistic Regression provided an interpretable baseline but had the lowest sensitivity (62.52%). The findings show that a model with the highest overall accuracy is not necessarily the most suitable model for screening. In early case finding, sensitivity and the false-negative burden require particular attention. The study therefore supports clinically supervised use of machine learning as a decision-support aid, subject to external validation, calibration, fairness assessment and careful deployment. |
| AUTHOR | NANCY SINGHAL, DR. SAURABH CHARAYA, DR. SANDEEP KUMAR Research Scholar, Department of Computer Science and Engineering, Om Sterling Global University, Hisar, Haryana, India Professor, Department of Computer Science, School of Engineering and Technology, Om Sterling Global University, Hisar, Haryana, India Professor and Associate Dean - Data Science, School of Computer Science & Artificial Intelligence, SR University, Warangal, Telangana, India |
| VOLUME | 188 |
| DOI | DOI: 10.15680/IJIRCCE.2026.1409008 |
| pdf/8_Machine Learning-Based Early Prediction of Type 2 Diabetes Mellitus using Clinical and Demographic Features A Comparative Analysis of Classification Models.pdf | |
| KEYWORDS | |
| References |
1. American Diabetes Association. (2024). Standards of care in diabetes-2024. Diabetes Care, 47(Supplement 1). 2. Kavakiotis, I., Tsave, O., Salifoglou, A., Maglaveras, N., Vlahavas, I., & Chouvarda, I. (2017). Machine learning and data mining methods in diabetes research. Computational and Structural Biotechnology Journal, 15, 104-116. 3. Dinh, A., Miertschin, S., Young, A., & Mohanty, S. D. (2019). A data-driven approach to predicting diabetes and cardiovascular disease with machine learning. BMC Medical Informatics and Decision Making, 19, 211. 4. Lai, H., Huang, H., Keshavjee, K., Guergachi, A., & Gao, X. (2019). Predictive models for diabetes mellitus using machine learning techniques. BMC Endocrine Disorders, 19, 101. 5. Hasan, M. K., Alam, M. A., Das, D., Hossain, E., & Hasan, M. (2020). Diabetes prediction using ensembling of different machine learning classifiers. IEEE Access, 8, 76516-76531. 6. Tigga, N. P., & Garg, S. (2020). Prediction of type 2 diabetes using machine learning classification methods. Procedia Computer Science, 167, 706-716. 7. Joshi, R. D., & Dhakal, C. K. (2021). Predicting type 2 diabetes using logistic regression and machine learning approaches. International Journal of Environmental Research and Public Health, 18(14), 7346. 8. Khanam, J. J., & Foo, S. Y. (2021). A comparison of machine learning algorithms for diabetes prediction. ICT Express, 7(4), 432-439. 9. Fregoso-Aparicio, L., Noguez, J., Montesinos, L., & García-García, J. A. (2021). Machine learning and deep learning predictive models for type 2 diabetes: A systematic review. Diabetology & Metabolic Syndrome, 13, 148. 10. Olisah, C. C., Smith, L., & Smith, M. (2022). Diabetes mellitus prediction and diagnosis from a data preprocessing and machine learning perspective. Computer Methods and Programs in Biomedicine, 220, 106773. 11. Tasin, I., Nabil, T. U., Islam, S., & Khan, R. (2023). Diabetes prediction using machine learning and explainable AI techniques. Healthcare Technology Letters, 10(1-2), 1-10. 12. Mansoori, A., Sahranavard, T., Hosseini, Z. S., et al. (2023). Prediction of type 2 diabetes mellitus using hematological factors based on machine learning approaches: A cohort study analysis. Scientific Reports, 13, 663. 13. Modak, S. K. S., & Jha, V. K. (2024). Diabetes prediction model using machine learning techniques. Multimedia Tools and Applications, 83, 38523-38549. 14. Abdollahi, J., & Aref, S. (2024). Early prediction of diabetes using feature selection and machine learning algorithms. SN Computer Science, 5, 217. 15. Rönn, T., Perfilyev, A., Oskolkov, N., & Ling, C. (2024). Predicting type 2 diabetes via machine learning integration of multiple omics from human pancreatic islets. Scientific Reports, 14, 14637. 16. Noronha, F., Singh, S., & Poojari, A. (2025). Diabetes prediction and risk analysis using machine learning techniques. Journal of Emerging Technologies and Innovative Research (JETIR), 12(3), e175–e182. |
