<p>The adoption of the Internet of Medical Things (IoMT) has revolutionized many aspects of healthcare management by enabling real-time monitoring, personalized treatment, and improved patient outcomes. However, there are numerous challenges that need to be tackled, such as managing the large volume of data generated, the requirement for real-time processing, the integration of various devices and systems, and the need to protect patient privacy and data security. To address these issues, the integration of advanced techniques such as Machine Learning (ML), Metaheuristics, and hybrid approaches that combine both techniques is crucial. While ML have been widely studied in IoMT applications, the potential of Metaheuristics is still largely unaddressed. This paper aims to provide a comprehensive survey of the integration of ML, Metaheuristic algorithms as well as their hybrid combinations in IoMT applications, highlighting the effectiveness of each method in addressing specific tasks, such as resource management, real-time monitoring, and predictive analytics. In addition, this paper compares related studies based on various criteria, such as the techniques used, datasets employed, and the pros and cons of each approach. Finally, the potential issues and challenges associated with using these methods in IoMT applications are discussed.</p>