Optimal testing policies for diagnosing patients with intermediary probability of disease

•We introduce a shortest path algorithm to derive optimal policies for disease diagnosis.•The algorithm makes use of a Bayesian approach to derive pos-test probabilities given the result.•A dynamic programming algorithm is used to find the optimal sequence of tests up to diagnosis•The algorithm is guaranteed to reach a posterior probability that warrants immediate diagnosis. This paper proposes a stochastic shortest path approach to find an optimal sequence of tests to confirm or discard a disease, for any prescribed optimality criterion. The idea is to select the best sequence in which to apply a series of available tests, with a view at reaching a diagnosis with minimum expenditure of resources. The proposed approach derives an optimal policy whereby the decision maker is provided with a test strategy for each a priori probability of disease, aiming to reach posterior probabilities that warrant either immediate treatment or a not-ill diagnosis.