AI Article Synopsis
- Phenotyping algorithms are key for clinical research using observational data, with manual algorithms like those from the eMERGE Network being the gold standard but labor-intensive to create.
- The authors propose a new framework that leverages the structure of eMERGE phenotype concept sets to streamline the development of novel phenotype definitions.
- By analyzing pairwise relationships in a concept graph and training models to predict connections, the framework helps identify candidate phenotype sets, which can then be used to construct new definitions efficiently.
Article Abstract
Phenotyping algorithms are essential tools for conducting clinical research on observational data. Manually devel- oped phenotyping algorithms, such as those curated within the eMERGE (electronic Medical Records and Genomics) Network, represent the gold standard but are time consuming to create. In this work, we propose a framework for learning from the structure of eMERGE phenotype concept sets to assist construction of novel phenotype definitions. We use eMERGE phenotypes as a source of reference concept sets and engineer rich features characterizing the con- cept pairs within each set. We treat these pairwise relationships as edges in a concept graph, train models to perform edge prediction, and identify candidate phenotype concept sets as highly connected subgraphs. Candidate concept sets may then be interrogated and composed to construct novel phenotype definitions.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8075469 | PMC |
Publication Analysis
Top Keywords
Similar Publications
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!