The Internet of Medical Things (IoMT) has transformed healthcare by connecting medical devices to enable real-time monitoring in smart hospitals, enhancing patient care and operational efficiency. However, the increased connectivity of IoMT devices has also introduced significant vulnerabilities, including unauthorized access, data breaches, and ransomware attacks. These risks not only compromise patient privacy but also pose challenges to hospital operations, potentially endangering lives. This study aims to address IoMT cybersecurity challenges by employing machine learning (ML) techniques to detect and mitigate cyber threats effectively. Using a publicly available network traffic dataset labeled with various attack types—such as Distributed Denial of Service (DDoS), spoofing, and data exfiltration—this research evaluates the performance of two classification algorithms: Support Vector Machine (SVM) and Random Forest (RF). 

The methodology includes data cleaning, normalization, and feature selection to prepare the dataset. The data will be divided into training and testing subsets to evaluate the models’ ability to generalize to unseen scenarios. Key performance metrics such as accuracy, precision, recall, F1-score, and confusion matrix will be used to compare the effectiveness of the SVM and RF classifiers in identifying cyberattacks. By focusing on SVM and RF, this study provides insights into the suitability of these algorithms for IoMT cybersecurity applications. The findings are expected to contribute to the development of robust intrusion detection systems, enhancing the security and reliability of IoMT devices in smart hospital environments.