Abstract

This study compares traditional statistical models, tree-based ensembles, and neural networks to examine machine-learning methods for Type-2 diabetes prediction in healthcare systems. We employ stringent preprocessing (missing-value techniques, feature engineering, imbalance handling) on public and clinical datasets (e.g., Pima Indians, regional EHR cohorts), and we assess models using nested cross-validation and measures that are resistant to class imbalance (ROC-AUC, F1, recall, MCC). Top predictors (HbA1c, fasting glucose, BMI, age, and waist circumference) are identified using explainability techniques (SHAP/feature permutation), and clinical value is evaluated using calibration and decision-curve analysis. We demonstrate model fairness across age/sex subgroups and suggest an ensemble stacking process (base learners: logistic regression, Random Forest, XGBoost, LightGBM; meta learner: calibrated logistic regression). In addition to offering suggestions for incorporation into EHR decision support with privacy and bias prevention principles, the results will quantify tradeoffs between accuracy, interpretability, and clinical readiness.

References

• G. Dharmarathne, S. Islam and others, “A novel machine learning approach for diagnosing diabetes with a self-explanatory interface,” Healthcare Analytics, vol. 5, 2024.
• M. Jichkar, R. Shende, O. Bonde, P. Agrawal, G. K. Gupta and A. K. Singh, “Diabetes Prediction Using Machine Learning,” in Proc. 2024 IEEE Silchar Subsection Conference (SILCON), Silchar, India, Nov. 2024
• O. Taylan, A. Alkabaa, H. Alqabbaa, E. Pamukçu and V. Leiva, "Early prediction in classification of cardiovascular diseases with machine learning neuro-fuzzy and statistical methods", Biology, vol. 12, no. 1, pp. 117, 2023.
• R. Bhavani, V. Ramkumar, V. Ravindran, R. Sindhuja and K. Swaminathan, "An efficient SAR image detection based on deep dense-mobile net method", 7th International Conference on Computing in Engineering & Technology (ICCET 2022), vol. 2022, pp. 92-95, 2022, February.
• V Krishnapraseeda, M S Geetha Devasena, V Venkatesh and A Kousalya, “Predictive Analytics on Diabetes Data using Machine Learning Techniques”, 7th International Conference on Advanced Computing and Communication Systems (ICACCS), pp. 458-463, IEEE 2021.
• Valasapalli Mounika, Devi Sree Neeli, Gorla Suma Sree, Parimi Mourya and Modala Aravind Babu, “Prediction of Type-2 Diabetes using Machine Learning Algorithms”, International Conference on Artificial Intelligence and Smart Systems (ICAIS), pp. 167-173, IEEE 2021.
• I. K. Mujawar, B.T. Jadhav, V.B. Waghmare and R.Y. Patil, “Development of Diabetes Diagnosis System with Artificial Neural Network and Open Source Environment”, International Conference on Emerging Smart Computing and Informatics (ESCI), pp. 778-784, IEEE 2021.
• Cecilia Saint-Pierre;Florencia Prieto;Valeria Herskovic;Marcos Sepúlveda, “Team Collaboration Networks and Multidisciplinarity in Diabetes Care: Implications for Patient Outcomes”, IEEE Journal of Biomedical and Health Informatics, Vol. 14(1), pp. 319-329, 2020.
• Bin Liu, Ying Li, Soumya Ghosh, Zhaonan Sun, Kenney Ng and Jianying Hu, “Complication Risk Profiling in Diabetes Care: A Bayesian Multi-Task and Feature Relationship Learning Approach”, IEEE Transactions on Knowledge and Data Engineering, Vol. 32(7), pp. no. 1276-1289, 2020.
• Klompas M., Eggleston E., McVetta J., Lazarus R., Li L. and Platt R., “Automated Detection and Classification of Type 1 versus Type 2 Diabetes using Electronic Health Record Data” Diabetes Care, Vol.36(4), Pp. 914-921, 2013.
• Ramanathan T.T. and Sharma D., “An SVM-Fuzzy Expert System Design For Diabetes Risk Classification” International Journal of Computer Science and Information Technologies, 6(3), Pp. 2221-2226, 2015.
• Karan O., Bayraktar C., Gümüşkaya H. and Karlık B., “Diagnosing Diabetes using Neural Networks on Small Mobile Devices”, Expert Systems with Applications, 39(1), Pp. 54-60, 2012.
• Rajesh K. and Sangeetha V., “Application of Data Mining Methods and Techniques for Diabetes Diagnosis”, International Journal of Engineering and Innovative Technology (IJEIT), Vol. 2(3), 2012.
• Acharya U.R., Ng E.Y.K., Tan J.H., Sree S.V. and Ng K.H., “An Integrated Index for the Identification of Diabetic Retinopathy Stages using Texture Parameters”, Journal of Medical Systems, Vol.36(3), Pp. 2011-2020, 2012.
• Gujral S., “Early Diabetes Detection using Machine Learning: A Review”, International Journal for Innovative Research in Science & Technology, Volume 3, Issue 10, 2017.