The Internet of Medical Things (IoMT) sector has advanced rapidly in recent years, and security and privacy are essential considerations in the IoMT due to the extensive scope and implementation of IoMT networks. Machine learning (ML) and blockchain (BC) technologies have dramatically improved the functionalities and services of Healthcare 5.0, giving rise to a new domain termed Smart Healthcare. A proactive healthcare system may prevent long-term harm by recognizing issues early. This would improve patients’ quality of life while alleviating their worry and healthcare expenses. The IoMT facilitates several capabilities in information technology, including intelligent and interactive healthcare. Consolidating medical information into a singular repository to train a robust ML model engenders apprehensions around privacy, ownership, and adherence to regulatory standards due to increased concentration. Federated learning (FL) addresses previous challenges using a centralized aggregate server to distribute global learning models. The local participant controls patient data, ensuring data confidentiality and security. Hence, this study proposes the Federated Blockchain-IoT Framework for Sustainable Healthcare Systems (FBCI-SHS) for a secure health monitoring system. Additionally, this paper presents the Intrusion Detection System (IDS) as a tool for healthcare network intrusion detection, allowing doctors to track patients’ vitals using medical sensors and anticipate when they could become sick so they can take preventative steps. The suggested system proves that the method is well-suited for medical monitoring. In contrast, the high prediction accuracy for intrusion detection and the high efficiency in disease detection achieved by the proposed FBI-SHS healthcare 5.0 system. The proposed method achieves data privacy and security by 98.73%, intrusion detection efficiency by 97.16%, disease detection accuracy by 96.425, proactive healthcare management by 98.37%, and interoperability by 96.74%.