In the age of computing, there is a vast assortment of medical equipment and software available. Software and medical equipment that can be online connected to healthcare Information Technology (IT) systems are referred to as Internet of Medical Things (IoMT). This research study elaborates healthcare connectivity and its security issues to the different dimension of IoMT. During the pandemic situation in 2020-21 Covid, importance of virtualization and its dependencies have got the momentum. The security challenge of IoMT needs to be addressed. The research analysis is evaluating the impact of security factors in IoMT. By systematically evaluating research studies based on the keywords IoMT, security of IoMT, and security in healthcare sector, security attributes and factors were discovered from the different digital library. This evaluation uses soft computing and Artificial Intelligence (AI) techniques, quantitatively elaborates the factors of IoMT and their impact based on security. The results provide guidance for the development of IoMT with security attributes that can help to ensure the security of the device and software based applications on networks or in the cloud. To assess the importance of the criteria and the ranking of the alternatives, the AI technique of Analytic Hierarchy Process (AHP) and Technique for Order of Preferences by Similarity to Ideal Solution (TOPSIS) were applied. The hybrid Fuzzy AHP, Fuzzy TOPSIS techniques are utilizing the concept of decision making in security of IoMT. The items were evaluated using a multi rules choice investigation with several standards. In this research study, eight factors and ten alternatives of IoMT were selected to determine their impact on security. The creating new funding, operating and business model factor of IoMT got the top weight and successfully navigating regulatory change got the least. The AI research on IoMT security determination helps the developer, medical practitioner, and medical device operator to consider the impact of security in IoMT. 

The increasing use of healthcare devices and their communication networks has raised concerns about the security of patient information and the potential for cyber-attacks. In this study, we propose a machine learning approach for classifying security vulnerabilities in healthcare device communication networks by using the Machine Learing (ML) Technique. We collected a dataset of healthcare device vulnerabilities and used feature selection and engineering techniques to extract the most relevant features for the classification task. We trained several machine learning algorithms, Snort algorithm, and support vector machines (SVM) and evaluated their performance using various evaluation metrics. The results showed that the SVM and Snort algorithms had an accuracy of 94%, a precision of 95%, a recall of 93%, and an F1-score of 94%. Our approach can help identify and prioritize security vulnerabilities in healthcare device communication networks, which can lead to better security practices and patient safety.