AI-Enhanced Threat Intelligence in Remote Patient Monitoring Systems: A Survey on Recent Advances, Challenges and Future Research Directions

【Author】 Trivedi, Jolly; Tahir, Mohammad; Isoaho, Jouni

【Source】IEEE ACCESS

【影响因子】3.476

【Abstract】Modern healthcare is increasingly relying on Remote Patient Monitoring (RPM) systems, which continuously collect health data and provide the ability to monitor patients in real-time. RPM systems are extremely susceptible to cyber threats due to their growing reliance on interconnected devices and hence need comprehensive security. AI has emerged as a crucial technology for addressing security issues in RPM systems. The objective of this survey is to understand the impact on the security of RPM systems by integrating Artificial Intelligence (AI) with threat intelligence. This survey analyzed 86 research articles from leading databases related to AI models, security of RPM systems, anomaly detection, and architectural solutions, in addition to 24 articles related to existing RPMs. This survey article emphasizes that RPM systems become much more resilient when automated attack mitigation, real-time anomaly detection, and predictive analytics are provided by AI-powered models. To secure the sensitive data in RPM, this survey discusses how AI can be applied to various architectural solutions, including edge computing, cloud integration, blockchain technology, and Federated Learning (FL). Furthermore, the benefits and challenges of deploying AI-driven threat intelligence, cross-platform compatibility, and the need for explainable AI to improve trust in automatically made decisions are presented. Moreover, this review highlights research gaps, including the necessity of comprehensive end-to-end architectures for maintaining security and privacy in RPM systems. It is revealed through this survey that AI-powered threat intelligence enhances RPM security considerably due to its ability of continuous monitoring, adaptive defense mechanisms, and early detection of threats. However, challenges such as the explainability of AI models persist and necessitate continued innovation. The survey paper suggests integrating AI-enhanced threat Detection as a Service (TDaas) that implements FL to transform the existing RPM security system, and ultimately contributes to a secure and reliable threat detection system in healthcare. This review provides a roadmap for future research in the area of AI-driven threat intelligence security for RPM systems and offers insights for developing resilient healthcare infrastructure.

【Keywords】Artificial intelligence; Security; Medical services; Threat assessment; Computer security; Surveys; Cyber threat intelligence; Real-time systems; Federated learning; Privacy; Remote patient monitoring (RPM); telemedicine; human digital twin (HDT); pseudonymization; security; privacy; cloud; artificial intelligence; cyber threat intelligence (CTI); HIPAA; GDPR; machine learning; federated learning; anomaly detection; threat detection; healthcare security; personalized healthcare

【发表时间】2025

【收录时间】2025-07-11

【文献类型】

【主题类别】

--