Machine Learning-Based Automated Threat Detection Network Security in Healthcare

This paper presents an automated threat detection for healthcare networks using machine learning models. It addresses the increased cybersecurity needs arising from integrating IoT devices and cloud services in healthcare. The approach involves data collection from IoT devices, preprocessing, and training models on historical attack data. It evaluates machine learning algorithms such as SVM, Naive Bayes, and Random Forest for their effectiveness in detecting threats, deploying them in real-time monitoring systems, and assessing their performance based on accuracy, precision, and recall. The results show that these models significantly improve threat detection and mitigation in healthcare networks, particularly in identifying anomalous behaviors that could lead to breaches. However, challenges such as limited real attack data and high false positive rates for some algorithms indicate the need for continuous model training and more advanced techniques. The proposed framework offers promise but requires ongoing innovation to keep pace with evolving cyber threats.