Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{188991,
        author = {Muthushree MC and Yogesh K and Ganya R and Likith Reddy CS and Dr B Vani},
        title = {EarlyDiabNet: A Machine Learning Framework for Early Diabetes Prediction},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {7},
        pages = {4272-4283},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=188991},
        abstract = {Diabetes is one of the most common chronic diseases affecting millions of people worldwide. Early prediction of diabetes risk plays a crucial role in preventing complications and improving patient health outcomes. This study focuses on developing a diabetes risk prediction model using machine learning techniques. Various health parameters such as Age, Body Mass Index (BMI), Blood Pressure, Glucose Insulin concentration are analyzed to identify patterns associated with diabetes. The system is trained on a consolidated dataset Proximal Intestinal mucosal ablation (PIMA), Sylhet and leverages a Sophisticated Ensemble Model combining three high-performance algorithms that is Random Forest, XGBoost (Extreme Gradient Boosting Machine) and Light Gradient Boosting Machine (LightGBM) with a dedicated PyTorch Multilayer Perceptron (MLP) deep learning component. The MLP is enhanced with advanced techniques, including an Attention Mechanism and a Hybrid Loss Function to specifically improve prediction on hard-to-detect and high-risk cases. The results demonstrate that machine learning can effectively predict the likelihood of diabetes, enabling timely medical intervention and promoting data-driven healthcare decision.},
        keywords = {Smote (Synthetic Minority Over-sampling Technique) Attention Mechanism, Imbalanced Data handling, Precision, Recall, F1 Score, AUC Metrics.},
        month = {December},
        }