Soumik, Md Shadman and al mamun, kh said and Hossain, Mohammad Sazzad and Omim, Shahamat and Akter, Farzana and Al Mamun, Abdullah and SARKAR, MRINMOY and Toushi, Deb Kanna Roy (2025) LEVERAGING ARTIFICIAL INTELLIGENCE AND PREDICTIVE DATA ANALYTICS TO ENHANCE CYBERSECURITY AND SAFEGUARD PATIENT PRIVACY IN U.S. ELECTRONIC HEALTH RECORDS. International Journal of Communication Networks and Information Security (IJCNIS),, 17 (8). pp. 181-202. ISSN 2073-607X

Text 8661-Article Text-19541-1-10-20251126.pdf Download (708kB)

Abstract

Electronification of healthcare has transformed the way patients are treated, however, at the same time, it enlarged the uniform of cyber vulnerabilities in U.S. Electronic Health Records (EHRs). Patient privacy and security have become a national priority as healthcare institutions increasingly start to depend on cloud-based systems and interconnected data systems. This study will discuss the potential to use Artificial Intelligence (AI) and Predictive Data Analytics as a strategic tool to increase the level of cybersecurity resilience and safeguard patient confidentiality in EHR systems. The paper examines modern models, such as AI-based intrusion detection, anomaly prediction and predictive risk modeling, and discusses the way these solutions change the current healthcare data protection paradigm into the proactive paradigm. Based on new literature, regulatory implications, and practice usages, the paper provides a theoretical framework of encompassing AI capabilities and predictive analytics pipelines to strengthen EHR ecosystems. The results indicate that predictive systems with AI substantially enhance early security anomaly detection, respond to incidents automatically, and compliance with the U.S. data privacy regulations including the HIPAA and the HITECH Act. The study has concluded that though AI is a source of ethical and technical challenges, it can be combined with predictive analytics to create a sustainable basis for intelligent and privacy-conscious health data security. Suggestions include the creation of explainable AI systems and ongoing model control to make sure there is transparency, accountability, and ethical integrity to the protection of patient data.

Item Type:	Article
Uncontrolled Keywords:	Artificial Intelligence, Predictive Data Analytics, Cybersecurity, Electronic Health Records, Patient Privacy
Subjects:	A General Works > AI Indexes (General)
Depositing User:	admin eprints
Date Deposited:	13 Oct 2026 01:44
Last Modified:	13 Oct 2026 01:44
URI:	http://eprints.umsida.ac.id/id/eprint/17202

Actions (login required)

View Item