Abstract

The swift digital evolution of healthcare systems has greatly enhanced patient assistance while also presenting significant cybersecurity issues. The rising adoption of Electronic Health Records (EHRs), cloud technology, and Internet of Medical Things (IoMT) devices has increased the vulnerability to cyber threats. This paper suggests a cybersecurity framework based on Machine Learning (ML) to protect healthcare data by identifying and stopping cyberattacks in real time. The proposed solution incorporates feature selection, anomaly detection, and classification methods to improve detection precision. Experimental findings show better performance regarding accuracy, precision, recall, and false positive rates in comparison to conventional techniques. The research emphasizes the necessity for intelligent and adaptive security solutions to protect sensitive patient information.