"Phenotypes are the measurable biological, behavioral and clinical markers of a condition or disease. The process of deriving research-grade phenotypes from clinical data using computer-executable algorithms is called computational phenotyping(phenotyping for short)”(PMID:27506131)
Computational phenotyping approaches have great potential to aid in diagnosis, prognosis, therapeutic decision-making, and identification of mechanisms or novel biomarkers. Currently, these methods have limited:
Generalizability because they are tailored to specific source vocabularies or hospital systems.
Translational relevance because they primarily rely on clinical data, which requires additional mapping to incorporate, for example, molecular or physiologic data.
Scalability because creating definitions is a time-consuming, iterative process requiring both domain expertise and robust external validation.
Objective: Develop a method(PheKnowVec: Phenotype Knowledge Vectors) for deriving, implementing, and validating computational phenotypes that addresses the aforementioned limitations by:
Mapping standardized clinical terminology concepts to linked open data.
Using embedding methods, which convert large complex heterogeneous data into scalable compressed vectors without semantic information loss.
Phenotypes
We will implement all phenotypes appropriate for use with pediatric and adult populations from the eMERGE network's Phenotype KnowledgeBase(n=9). Additional information on the phenotypes listed below can be found here.
Task Overview
Table of Contents
Timeline
Project Description