Surveillance based dynamic empirical therapy in a health care facility: an artificial intelligence approach

Abstract

We present a solution method to the problem of choosing empirical treatments that minimize the cumulative infected patient-days in the long run in a health care facility. We rely on the stochastic version of a compartmental model to describe the spread of an infecting organism in the health care facility, and the emergence and spread of resistance to two drugs. We assume that the parameters of the model are known. Empirical treatments are chosen at the beginning of each period based on the count of patients with each health status. The same treatment is then administered to all patients, including uninfected patients, during the period and cannot be adjusted until the next period. Our solution method is a variant of the Monte-Carlo tree search algorithm. In our simulations, it allows to reduce the average cumulative infected patient-days over two years by 47.0% compared to the best standard therapy. We explain how our algorithm can be used either to perform online optimization, or to produce data for quantitative analysis.