A nonparametric approach for optimal reliability allocation in health services

Purpose - Reliability evaluation of healthcare services has been a challenging task for both operations managers and system engineers working in the respective field. The purpose of this paper is to develop a data envelopment analysis-based reliability allocation model. Design/methodology/approach - A two-phase optimization scheme for the reliability evaluation and allocation of homogeneous system entities, namely, hospitals, operating in a healthcare network is proposed. First, reliability evaluation is performed nonparametrically through the frontier estimation technique data envelopment analysis by considering several failure modes and failure free discharged patients as the inputs and output of the service system. Subsequently, optimal reliability allocation that maximizes the overall network reliability subject to a budget constraint is carried out by utilizing weights of the inputs and output calculated on the Pareto optimal frontier, which is constructed from the most reliable hospitals operating in the network. Findings - The popular performance assessment methodology DEA is found to be an invaluable reliability assessment and allocation tool, where optimal weights of the associated envelopment model, under certain budget restrictions, are used to maximize overall network reliability. Originality/value - An empirical illustration of the proposed model is presented on a set of hospital network data from Turkey. Modeling implications can be carried out on similar service operations where identification of the critical performance indicator costs is possible.