Journal of Engineering Research and Reports

This study investigates the application of artificial intelligence (AI) and machine learning (ML) in predictive cybersecurity risk modeling within the healthcare sector. Given the increasing digitization of healthcare systems and the corresponding rise in cyber threats, it is crucial to develop proactive measures to safeguard sensitive patient data. To achieve this, the study employs quantitative methods and publicly available datasets to analyze risk patterns and evaluate the effectiveness of AI-driven models. Specifically, the research utilizes the Verizon Data Breach Investigations Report to examine threat prevalence, the CIC-IDS 2017 dataset to assess a Random Forest classifier, the Stanford AI Index Report to identify implementation challenges, and IBM’s Cost of a Data Breach Report to quantify AI's operational impact. The Random Forest model demonstrated high performance, achieving an accuracy of 92.7%, precision of 89.9%, recall of 90.5%, and an F1-score of 90.2%. Healthcare organizations leveraging AI experienced a significant 26% reduction in data breach costs and resolved incidents 36% faster compared to non-AI adopters. Key challenges identified include internal threats, regulatory compliance issues, and workforce skill gaps. To address these challenges, the study recommends targeted workforce training, strategic compliance alignment, the adoption of behavioral threat detection techniques, and the establishment of federated learning partnerships to enhance healthcare cybersecurity resilience.