<p>Patient care and healthcare operations have been significantly improved by the use of Internet of Things (IoT) technology in medical applications. Understanding the Internet of Medical Things (IoMT) enables healthcare professionals to use remote diagnostics and real-time patient monitoring to provide treatment and save many lives. However, security and privacy have been issues since IoMT devices are vulnerable to hackers. IoMT devices don’t have enough memory or processing power to set up security features. One of the primary issues with the current system is the leaking of personal and private information (IoMT). Considering the aforementioned, this study suggests an advanced intrusion detection technology (AIDT) to guarantee safe data exchange amongst IoMT devices. The model uses a probabilistic neural network (PNN) to classify whether intrusions are present or not, and particle swarm optimization (PSO) for feature extraction. By employing the integrated patient sensing and network traffic datasets, our research achieves a superior accuracy rate of 96.4% in network intrusion detection compared to the competing algorithms. Furthermore, we incorporated a comprehensive analysis of the implementation of different classification algorithms in IoMT network intrusion detection, further supporting the claim that the proposed framework performs marginally better than alternative models. </p>