An Intelligent Model for Improving Risk Assessment in Sterilization Units Using Revised FMEA, Fuzzy Inference, k-Nearest Neighbors and Support Vector Machine.

Abstract

The complex environment of the hospital and the critical operations practiced in the medical departments, such as the sterili zation
unit, require implementing risk assessment plans as fundamental support for effective management. The Failure Modes Analysis
and Effects (FMEA) method is one of the popular methods used to perform the risk assessment process. Fuzzy logic and machine
learning techniques provide robust devices that improve the efficiency of several risk assessment methods, such as FMEA. Hence,
this study aims to enhance the efficiency of risk assessment in hospital sterilization units using an intelligent model based on
revised FMEA, an improved FMEA adaptable to the studied system, fuzzy inference system, Support Vector Machine (SVM),
and K-Nearest Neighbors (KNN) techniques. An interesting application of the model in the central sterilization unit of the largest
university hospital is presented. The performance of the proposed model is evaluated at the end to prove its efficiency.