Restoring the patient therapeutic history from prescription data to enable computerized guideline-based decision support in primary care

Abstract

The application of a guideline-based therapeutic strategy in the context of a chronic disease requires a clear picture, at the appropriate level of abstraction, of a patient's particular therapeutic history. However, like most clinical data, information on past treatments is often incompletely specified. We propose temporal abstraction mechanisms based on a simple and heuristic treatment of temporal indeterminacy of period bounds. Applied to prescription data, continuity and simultaneousness of treatments have to be characterized. Even if limited, our method restores the therapeutic history of a patient, with episodes of mono-, bi-, and tritherapies in order to adequately position her within the guideline therapeutic strategy.