Multimodal Predictive Analytics for Early Disease Detection Using Wearable IoMT and Artificial Intelligence

Abstract

The convergence of wearable technology, Internet of Medical Things (IoMT), and artificial intelligence represents a paradigm shift in healthcare delivery from reactive treatment toward continuous, data-driven early disease detection. This review synthesizes recent evidence demonstrating how AI-powered wearable devices enable physiological monitoring and disease identification across cardiovascular, metabolic, neurological, and respiratory conditions with diagnostic accuracies exceeding 95% [1,2]. We examine architectural frameworks integrating edge computing and deep learning models, including convolutional neural networks and transformers. While substantial progress has been achieved, persistent challenges remain, including energy constraints, data interoperability, algorithmic bias, and privacy concerns under HIPAA and GDPR regulations. Emerging solutions through federated learning, explainable AI, and 6G connectivity offer pathways toward fully integrated wearable systems. This review provides evidence-based insights for advancing personalized, preventive healthcare through intelligent wearable technologies.