Summary
This paper describes PheKB, a web-based platform designed to streamline the creation, validation, and sharing of electronic phenotype algorithms derived from electronic health record data across multiple institutions. As of mid-2015, the repository contained 30 finalised algorithms and 62 under development, with median PPVs remaining consistent between originating sites and secondary implementation sites (case PPV 96–97.5%, control PPV 100%), demonstrating that algorithms developed at one institution are generally transportable to others. This infrastructure addresses a critical bottleneck in precision medicine research by enabling reproducible, research-grade phenotyping at scale.
UK applicability
Whilst developed primarily within United States health systems, the PheKB platform's approach to phenotype algorithm development and validation could inform similar efforts within the UK's National Health Service and linked research databases (e.g. UK Biobank). However, direct applicability would require adaptation to UK coding systems (SNOMED-CT, Read codes) and data governance frameworks.
Key measures
Positive predictive value (PPV) for cases and controls at authoring institutions versus secondary implementation sites; algorithm component frequency (ICD codes, medications, natural language processing); number of phenotype algorithms and unique views
Outcomes reported
The study assessed the development, sharing, and validation of electronic phenotype algorithms within PheKB, measuring their transportability across multiple health care systems. Performance metrics included positive predictive values (PPVs) for case and control identification at authoring and implementation sites.
Topic tags
Dig deeper with Pulse AI.
Pulse AI has read the whole catalogue. Ask about this record, its theme, or how the findings apply to UK farming and policy — every answer cites the underlying studies.