Integration of generative artificial intelligence and the internet of medical things (IoMT): Systematic literature review for the 2021–2025 period

Abstract

Purpose: This study comprehensively examines the integration of Generative Artificial Intelligence (GenAI) models with Internet of Medical Things (IoMT) systems by systematically reviewing the literature published between 2021 and 2025. Method: Sixteen eligible studies compiled from the PubMed, IEEE Xplore, Springer Nature, ACM Digital Library, and arXiv databases were analyzed using the PRISMA method. Finding: The findings indicate that Generative Adversarial Networks (GANs), Large Language Models (LLMs), Variational Autoencoders (VAE), and Diffusion Models have driven significant transformations in critical IoMT applications such as remote patient monitoring (RPM), clinical decision support systems (CDSS), synthetic medical data generation, anomaly detection, and privacy-preserving federated learning. Conclusion: Regulatory compliance (HIPAA, GDPR), model explainability, the risk of hallucinations, and limited computational capacity on edge devices emerge as key research gaps.