AI-Driven Decision Support Framework for Preventing Medical Equipment Failure and Enhancing Patient Safety: A New Perspective

Sara Awni Alkhatib,1,2 Rateb Katmah,1 Doua Kosaji,1 Syed Usama Bin Afzal,3 Muhammad Hamza Tariq,1 Mecit Can Emre Simsekler,4 Samer Ellahham5 1Department of Biomedical Engineering and Biotechnology, Khalifa University of Science & Technology, Abu Dhabi, United Arab Emirates; 2Center for Catalysis and Separation (CeCaS), Khalifa University of Science & Technology, Abu Dhabi, United Arab Emirates; 3Department of Electrical and Computer Engineering, Khalifa University of Science & Technology, Abu Dhabi, United Arab Emirates; 4Department of Management Science & Engineering, Khalifa University of Science & Technology, Abu Dhabi, United Arab Emirates; 5Heart and Vascular Institute, Cleveland Clinic Abu Dhabi, Abu Dhabi, United Arab EmiratesCorrespondence: Mecit Can Emre Simsekler, Email [email protected]: Medical equipment failures pose serious risks to patient safety and healthcare system efficiency. Although AI-based predictive maintenance (PdM) has shown promise in other industries, its application in healthcare remains fragmented and insufficiently aligned with human-centered principles. This perspective paper proposes a novel AI-driven decision support framework that integrates systems thinking and prioritizes human-centered design. By leveraging real-time sensor data and historical maintenance records, the framework proactively predicts equipment failures and reduces downtime. It incorporates insights from key stakeholders, including biomedical engineers, technicians, patients, and administrators, to ensure human-centered and ethically responsible implementation. The paper also addresses major challenges such as data integration, human factors, and organizational readiness, offering practical strategies for sustainable adoption. This work contributes to the evolving role of AI in healthcare by emphasizing empathy, stakeholder collaboration, and safety, ultimately promoting more reliable medical devices and improved patient outcomes.Keywords: artificial intelligence, equipment failure analysis, maintenance, predictive, patient safety, human factors, clinical decision support systems