A novel decision support system for proactive risk management in healthcare based on fuzzy inference, neural network and support vector machine

Abstract

BackgroundThe nature of activities practiced in healthcare organizations makes risk management the most crucial issue for decision-makers, especially in developing countries. New technologies provide effective solutions to support engineers in managing risks. PurposeThis study aims to develop a Decision Support System (DSS) adapted to the healthcare constraints of developing countries that enables the provision of decisions about risk tolerance classes and prioritizations of risk treatment. MethodsFailure Modes and Effects Analysis (FMEA) is a popular method for risk assessment and quality improvement. Fuzzy logic theory is combined with this method to provide a robust tool for risk evaluation. The fuzzy FMEA provides fuzzy Risk Priority Number (RPN) values. The artificial neural network is a powerful algorithm used in this study to classify identified risk tolerances. The risk treatment process is taken into consideration in this study by improving FMEA. A new factor is added to evaluate the feasibility of correcting the intolerable risks, named the control factor, to prioritize these risks and start with the easiest. The new factor is combined with the fuzzy RPN to obtain intolerable risk prioritization. This prioritization is classified using the support vector machine. FindingsResults prove that our DSS is effective according to these reasons: (1) The fuzzy-FMEA surmounts classical FMEA drawbacks. (2) The accuracy of the risk tolerance classification is higher than 98%. (3) The second fuzzy inference system developed (the control factor for intolerable risks with the fuzzy RPN) is useful because of the imprecise situation. (4) The accuracy of the fuzzy-priority results is 74% (mean of testing and training data). ConclusionsDespite the advantages, our DSS also has limitations: There is a need to generalize this support to other healthcare departments rather than one case study (the sterilization unit) in order to confirm its applicability and efficiency in developing countries.