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{187277,
        author = {Jayshree Nilesh Balinge and Priyanka Pramod Mahalle and Juhi Kisan Chavan},
        title = {Advanced IoT-Enabled Early Disease Detection System Using Multi-Modal Sensor Fusion and Deep Learning: A Comprehensive Approach for Parkinson's Disease and Diabetes},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {6},
        pages = {5688-5693},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=187277},
        abstract = {This paper presents an advanced IoT-enabled framework for early detection of Parkinson's disease and diabetes using multi-modal sensor fusion and state-of-the-art deep learning architectures. We propose a hybrid CNN-LSTM-Attention model integrated with Transformer-based temporal processing and Graph Neural Networks for enhanced feature extraction from heterogeneous sensor data. Our system achieves 97.8% accuracy for Parkinson's disease detection and 95.6% for diabetes prediction, surpassing existing approaches by 5-8%. The framework incorporates edge AI processing, explainable AI components, and federated learning for privacy-preserving distributed training. Extensive validation across 2,500+ patients demonstrate the system's robustness, with early detection capability 8-12 months before clinical diagnosis. We also present a comprehensive comparison with existing methodologies and provide insights into deployment considerations for real-world clinical settings.},
        keywords = {IoT sensors, deep learning, Parkinson's disease, diabetes detection, multi-modal fusion, edge computing, explainable AI, wearable devices},
        month = {November},
        }