Title: The Role of Supervised and Unsupervised Machine Learning in Mitigating Cyber Threats to Healthcare Infrastructure in Louisiana
Authors: Chinonso Valentine Nnachetam
Volume: 10
Issue: 6
Pages: 62-67
Publication Date: 2026/06/28
Abstract:
Healthcare today increasingly depends on technologies such as electronic health records, telemedicine platforms, cloud services, and Internet of Medical Things (IokMT) devices. While these tools enhance patient care, they also introduce risks, including ransomware attacks, phishing schemes, insider misuse, and data breaches. This paper explores how both supervised and unsupervised machine learning can help strengthen cybersecurity within Louisiana's healthcare infrastructure. Using a qualitative, document-based approach that draws on cybersecurity records, federal guidelines, and recent peer-reviewed studies, the analysis finds that supervised learning is effective for detecting known threats like phishing and malware, whereas unsupervised learning excels at spotting unusual behaviours and previously unseen attacks. However, machine learning alone is not enough. Successful implementation requires human oversight, strong data governance, workforce training, and modernized infrastructure. The study proposes a hybrid approach that integrates supervised threat detection, unsupervised anomaly monitoring, analyst review, and continuous feedback loops.