Enhancing Healthcare Data Security in the Cloud: Integrating ML-Based Intrusion Detection Systems

Technology integration, but particularly the merging of health care data systems (HCDS) with Cloud Computing, becomes crucial for the proper data management in developing healthcare system. The integration yields notable benefits including improved patient care, simplified administrative procedures and informed decision-making within healthcare organizations. Cloud computing also has scalability, flexibility and cost-effectiveness, so it becomes the best alternative for keeping and analyzing the big amounts of healthcare data. Nevertheless, the shift in paradigm leads to data security and privacy issues, which require strong security controls for sensitive health data. This research paper concerns optimizing HCDS using Cloud Computing to provide data management, accessibility, and scalability in the Healthcare industry. It studies the utilization of Technology, specifically Cloud Computing, in improving Health Care administration systems, reducing paperwork, and creating a centralized platform for efficient health care organization administration. The focus area is concerned with the security issues raised by keeping healthcare data on the cloud, which covers the creation and implementation of such as encryption, access controls and intrusion detection. The research utilizes the latest technologies such as AI and ML to enhance healthcare data on the cloud security. The NSL-KDD benchmark dataset is used to maturely apply and analyse ML models such as RF, SVM, and LR. The results show the models' capacity to distinguish Denial of Service, Probe, Remote and Local, and User to Root attacks. Compared to other ML models, in particular Random Forest is a leading one in performance in all attack types.