-
Notifications
You must be signed in to change notification settings - Fork 0
Translatability
Problem: Computational phenotype definitions may lack translational relevance because they primarily rely on clinical data requiring additional mapping or data harmonization to incorporate, for example, molecular or physiologic data.
Solution: PhenKnowVec maps standardized clinical terminology concepts (e.g. SNOMED, LOINC, RxNorm, CPT4) to biomedical ontologies (e.g. HPO, DOID, ChEBI), which has been shown to significantly improve the process of integrating and incorporating sources of non-clinical data.
Experiment: For each phenotype, we will examine what information is gained and/or lost when deriving pediatric and adult patient cohorts that are built on standard clinical code sets are mapped to ontology code sets. For all comparisons, the Source Vocabulary - Exact None code set was be used as the gold standard.
The results from these experiments are organized by phenotype and listed below.