Home
Collaborators:
Informatics Team
Sara Deakyne Davies, Michael G. Kahn, Lawrence E. Hunter
Clinical Team
-
Clinicians
Tellen D. Bennett, Jordan Wyrwa, James A. Feinstein, Blake Martin -
Pharmacists
Katy Trinkley, Jessica Sinclair
Translational Research Team
Adrianne L. Stefanski, Nicole Vasilevsky,
Xingmin Aaron Zhang, Peter N. Robinson
Project Description:
Enriching clinical data from an EHR with other sources of patient data, like social media, environmental, and molecular data, can significantly improve the precision of computational phenotyping. Unfortunately, clinical terminologies, even those standardized to a common data model, are not easily harmonized with non-clinical data. Sources of linked open data, like biomedical ontologies, offer rich representations of a wide variety of natural phenomena and are purposefully designed for integration.
To date, there have been many efforts which have examined the utility of mapping subsets of clinical terminologies to ontologies and some organizations have even developed their own clinical ontologies (e.g. Diabetes Mellitus Diagnosis Ontology, Sickle Cell Disease Ontology, and Artificial Intelligence Rheumatology Consultant System Ontology).
By mapping clinical terminologies to biomedical ontologies it becomes easier to integrate outside sources of biomedical data. More importantly, this mapping makes it possible to derive hypotheses about biologically-actionable mechanism(s) from clinical findings.
UPDATE: Mapping is complete and a manuscript is in progress. All mappings will be publicly available once the manuscript is submitted.
- We recently presented the results of our validation for mapping LOINC lab result to the Human Phenotype Ontology group.
- Vasilevsky N, Zhang A, Yates A et al. LOINC2HPO: Curation of Phenotype Data from the Electronic Health Records using the Human Phenotype Ontology [version 1; not peer reviewed]. F1000Research 2019, 8:383 (slides) (doi: 10.7490/f1000research.1116524.1)
- Vasilevsky N, Zhang A, Gourdine J et al. LOINC2HPO: Curation of Phenotype Data from the Electronic Health Records using the Human Phenotype Ontology [version 1; not peer reviewed]. F1000Research 2019, 8:382 (poster) (doi: 10.7490/f1000research.1116517.1)