Copyright © 2026 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{183810,
        author = {Akhil Ashwin and Shekhar Nigam},
        title = {A Survey on Deep Learning Approaches for Early Diabetes Detection},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {3},
        pages = {3081-3085},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=183810},
        abstract = {Diabetes mellitus is a chronic metabolic disorder that poses significant health risks if not detected and managed in its early stages. Early diagnosis is crucial to prevent severe complications and improve patient outcomes. With the rise of artificial intelligence in healthcare, deep learning has emerged as a powerful tool for the early detection of diabetes due to its ability to learn complex patterns from large datasets. This survey provides a comprehensive overview of recent deep learning approaches applied to early diabetes detection. We explore various architectures, including Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Autoencoders, and hybrid models, analyzing their performance across diverse datasets and diagnostic scenarios. The paper highlights key methodologies, comparative analyses, strengths, limitations, and potential improvements. Moreover, it discusses challenges such as data quality, interpretability, and real-world applicability. This survey aims to guide future research by identifying promising directions and encouraging the development of more accurate, reliable, and interpretable diagnostic systems.},
        keywords = {Deep Learning, diabetes prediction, early detection, Heart rate variability, ECG, CNN, LSTM},
        month = {October},
        }