A probabilistic approach to improved antibiotic therapy

PTA is a decision-theoretic expert system that aims to assist clinicians in diagnosing and treating patients with pneumonia in the intensive care unit. Its underlying probabilistic network model includes knowledge for diagnosing pneumonia on the basis of the likelihood of tracheobronchial-tree colonisation by pathogens, and symptoms and signs actually present in the patient. Optimal antibiotic therapy is selected by balancing the expected efficacy of treatment, which is related to the likelihood of pathogen-specific pneumonias, against costs and side effects of treatment. In this article, the model underlying the system and results of a preliminary evaluation are described.