PhenoFit: A Framework for Determining Computable Phenotyping Algorithm Fitness for Purpose and Reuse

Background: Computational phenotyping from electronic health records (EHRs) is essential forclinical research, decision support, and quality/population health assessment, but theproliferation of algorithms for the same conditions makes it difficult to identify which algorithm ismost appropriate for reuse.Objective: To develop a framework for assessing phenotyping algorithm fitness for purpose andreuse.Fitness for Purpose: Phenotyping algorithms are fit for purpose when they identify theintended population with performance characteristics appropriate for the intended application.Fitness for Reuse: Phenotyping algorithms are fit for reuse when the algorithm isimplementable and generalizable - that is, it identifies the same intended population with similarperformance characteristics when applied to a new setting.Conclusions: The PhenoFit framework provides a structured approach to evaluate and adaptphenotyping algorithms for new contexts increasing efficiency and consistency of identifyingpatient populations from EHRs.