AI-Driven Cyber Threat Detection in the Healthcare Sector: A Machine Learning Approach

Abstract

The increasing digitization of healthcare systems has led to improved patient care but has also exposed critical infrastructure to growing cybersecurity threats. This study focuses on the development and comparative analysis of various machine learning (ML) models to detect cyber-attacks targeting the healthcare industry. By utilizing publicly available cybersecurity datasets enriched with healthcare-specific attack vectors, we evaluate the performance of models including Decision Trees, Random Forest, Support Vector Machines (SVM), k-Nearest Neighbours (k-NN), and Artificial Neural Networks (ANN). These models are assessed on multiple metrics such as accuracy, precision, recall, F1-score, and false positive rate. Our findings reveal that ensemble methods, particularly Random Forest and gradient-boosted algorithms, achieve superior detection rates while maintaining a low false alarm ratio. The study also highlights the importance of feature selection and data preprocessing in enhancing model performance. The results underscore the potential of ML-based approaches to act as intelligent, real-time defence systems in securing electronic health records and maintaining data integrity within healthcare infrastructures. This work provides a foundational benchmark for future developments in AI-driven cyber defence systems tailored to the healthcare sector.