<p>The integration of Internet of Things (IoT) technologies into the healthcare sector has revolutionized patient care by enabling real-time monitoring, automated data collection, and efficient communication across medical devices, collectively referred to as the Internet of Medical Things (IoMT). While these advancements improve healthcare delivery, they also introduce significant security and privacy concerns due to the sensitive nature of medical data and the distributed architecture of IoMT systems. This paper presents a Blockchain-Enabled IoT Healthcare System that addresses these challenges by incorporating a dual-layered security approach. The proposed framework combines the immutability, transparency, and decentralized control of blockchain technology with an intelligent Intrusion Detection System (IDS). At the core of the IDS is a hybrid machine learning model that integrates an Enhanced Artificial Bee Colony (E-ABC) algorithm with a Deep Belief Network (DBN). The E-ABC algorithm is utilized to optimize the DBN by fine-tuning its hyperparameters and effectively initializing weights, thereby improving its detection accuracy, and reducing training time. This hybrid approach enhances the IDS’s ability to identify anomalies and detect intrusions with high precision in IoMT environments. Extensive experiments conducted on benchmark IoMT intrusion datasets demonstrate that the proposed ABC-DBN model outperforms existing techniques in terms of detection rate, accuracy, precision, and false positive rate. The results validate the model’s effectiveness and potential for real-world deployment. This study contributes to the development of secure and intelligent healthcare infrastructures by presenting a scalable solution that ensures data integrity, confidentiality, and timely threat detection.</p>