Ensuring patient safety in IoMT: a systematic literature review of behavior-based intrusion detection systems

Abstract

Integrating Internet of Medical Things (IoMT) devices into healthcare has enhanced patient care, enabling real-time data exchange and remote monitoring, yet it also presents substantial security risks. Addressing these risks requires robust Intrusion Detection Systems (IDS). While existing studies target this topic, a systematic literature review focused on the current state and advancements in Behavior-based Intrusion Detection Systems for IoMT environments is necessary. This systematic literature review analyzes 81 studies from the past five years, answering three key research questions: (1) What are the Behavior-based IDS currently used in healthcare? (2) How do the detected attacks impact patient safety? (3) Do these IDS include prevention measures? The findings indicate that nearly 84% of the reviewed studies utilize Artificial Intelligence (AI) techniques for threat detection. However, significant challenges persist, such as the scarcity of IoMT-specific datasets, limited focus on patient safety, and the absence of comprehensive prevention and mitigation strategies. This review highlights the need for more robust, patient-centric security solutions. In particular, developing IoMTspecific datasets and enhancing defensive mechanisms are essential to meet the unique security requirements of IoMT environments.

This publication and other research outcomes are supported by the predoctoral program AGAUR-FI ajuts (2024 FI-1 00643) Joan Oró, and the Chair of Cybersecurity called CARISMATICA which are backed by the Secretariat of Universities and Research of the Department of Research and Universities of the Generalitat of Catalonia, as well as the European Social Plus Fund and the funds from the Recovery, Transformation, and Resilience, financed by the European Union (Next Generation), under the auspices of the INCIBE.

Postprint (author's final draft)