A Proposed Framework to Determine the Reliability and Spare Parts Replacement for Medical Devices

Abstract

The lack of malfunction of medical equipment has the potential to significantly impact the medical industry and pose a threat to the well-being of billions of individuals globally. Subsequently, maintenance services are executed to ascertain that the equipment is functioning following the standards set by the manufacturer and upheld at the desired level of quality. Downtime resulting from equipment breakdowns can significantly impact the operational efficiency of equipment, leading to decreased output, heightened operating expenses, and disruptions in customer services. The main objective of this conceptual framework is to explore on the spare parts replacement and their impact on the maintenance function of the health system. The proposed approach uses the Failure Mode and Effects Analysis (FMEA) method to identify potential failures effectively. It will describe how obtained scores are used to set up guidelines for appropriate spare parts replacement for improved maintenance strategies.  To forecast the demand for spare parts for medical devices, this paper proposes a semi-supervised learning algorithm to solve the problem. Through the use of data-driven insights and predictive analytics, machine learning algorithms can enhance decision-making processes about the timing and selection of spare parts replacement.