The Internet of Medical Things has emerged as a transformative technology in healthcare, facilitating remote monitoring and management of medical devices. However, despite these benefits, there is a need for more vigilance in ensuring electromagnetic compatibility within the Internet of Medical Things networks. It is quite essential to prevent electromagnetic interference as it could compromise device efficacy and consequently patient safety. This study aims to enhance real-time detection and prediction of electromagnetic radiations on the Internet of Medical Things networks by leveraging the predictive capabilities of the Kalman filter. An experiment was conducted over 30 days to evaluate the performance of the algorithm in optimizing electromagnetic compatibility management thus mitigating electromagnetic interference events. The algorithm was implemented and validated with 2500 samples of radiation emissions, with coordinates of the device’s location. The results indicated that the implementation of Kalman filter algorithms could reduce sensor noise by up to 88% of accuracy. This research contributes to advancing electromagnetic compatibility monitoring techniques on the Internet of Medical Things networks, offering valuable implications for the design and implementation of resilient healthcare systems.