Authors : Alma Thankam Raju; Dr. S. V. Annlin Jeba; Nisha Mohan

Volume/Issue : Volume 11 - 2026, Issue 4 - April

Google Scholar : https://tinyurl.com/42et8kcd

Scribd : https://tinyurl.com/4vm6zb6u

DOI : https://doi.org/10.38124/ijisrt/26apr1774

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Diabetes mellitus is a chronic metabolic disease that continues to grow in prevalence worldwide, placing immense strain on healthcare systems. Conventional diagnostic tests such as HbA1c, fasting plasma glucose, and oral glucose tolerance are invasive and often detect the disease late. Early prediction is therefore essential. This paper explores the application of generative AI, particularly the Bidirectional Encoder Representations from Transformers (BERT) model, for diabetes prediction. The model is evaluated against classical machine learning classifiers including Decision Trees, Random Forest, SVM, and AdaBoost, using the Pima Indian Diabetes dataset augmented with synthetic data generated via GANs. Results indicate that while AdaBoost achieved high baseline accuracy, BERT provided superior confidence scoring, interpretability, and adaptability. A diagnostic web interface was also developed to demonstrate real-time deployment. Findings highlight the promise of generative AI in predictive healthcare applications.

Keywords : Diabetes Prediction, Generative AI, BERT, Machine Learning, Healthcare, Predictive Analytics, Clinical Diagnosis.

References :

1. K. Abnoosian, R. Farnoosh, and M. H. Behzadi, "Prediction of diabetes disease using an ensemble of machine learning multi-classifier models," BMC Bioinformatics, vol. 24, no. 337, 2023, doi: 10.1186/s12859-023-05465-z.
2. M. Khalifa and M. Albadawy, "Artificial intelligence for diabetes: Enhancing prevention, diagnosis, and effective management," Computer Methods and Programs in Biomedicine Update, vol. 5, p. 100141, 2024, doi: 10.1016/j.cmpbup.2024.100141.
3. I. T. T. U. Nabil, S. Islam, and R. Khan, "Diabetes prediction using machine learning and explainable AI techniques," Healthcare Technology Letters, vol. 10, pp. 1–10, 2023, doi: 10.1049/htl2.12039.
4. G. Dharmarathne, T. N. Jayasinghe, M. Bogahawaththa, D. P. P. Meddage, and U. Rathnayake, "A novel machine learning approach for diagnosing diabetes with a self-explainable interface," Healthcare Analytics, vol. 5, p. 100301, 2024, doi: 10.1016/j.health.2024.100301.
5. M. K. Hasan, M. A. Alam, D. Das, E. Hossain, and M. Hasan, "Diabetes prediction using ensembling of different machine learning classifiers," IEEE Access, vol. 8, pp. 76516–76531, 2020, doi: 10.1109/ACCESS.2020.2987736.
6. R. Joshi and M. Alehegn, "Analysis and prediction of diabetes diseases using machine learning algorithm: ensemble approach," Int. Res. J. Eng. Technol., vol. 4, no. 10, pp. 2395–2402, 2017.
7. X.-H. Meng, Y.-X. Huang, D.-P. Rao, and Q. Liu, "Comparison of three data mining models for predicting diabetes or prediabetes by risk factors," Kaohsiung J. Med. Sci., vol. 29, pp. 93–99, 2013.
8. V. AnujaKumari and R. Chithra, "Classification of diabetes disease using support vector machine," Int. J. Eng. Sci., vol. 3, no. 2, pp. 1797–1801, 2013.