Phenoflow: A Microservice Architecture for Portable Workflow-based Phenotype Definitions
Chapman, M.; Rasmussen, L. V.; Pacheco, J. A.; Curcin, V.
Show abstract
Phenotyping is an effective way to identify cohorts of patients with particular characteristics within a population. In order to enhance the portability of a phenotype definition across institutions, it is often defined abstractly, with implementers expected to realise the phenotype computationally before executing it against a dataset. However, unclear definitions, with little information about how best to implement the definition in practice, hinder this process. To address this issue, we propose a new multi-layer, workflow-based model for defining phenotypes, and a novel authoring architecture, Phenoflow, that supports the development of these structured definitions and their realisation as computable phenotypes. To evaluate our model, we determine its impact on the portability of both code-based (COVID-19) and logic-based (diabetes) definitions, in the context of key datasets, including 26,406 patients at North-western University. Our approach is shown to ensure the portability of phenotype definitions and thus contributes to the transparency of resulting studies.
Matching journals
The top 6 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Evaluating Semantic Similarity Methods for Comparison of Text-derived Phenotype Profiles 94%
- Towards semantic interoperability: finding and repairing hidden contradictions in biomedical ontologies 93%
- Ontology-based expansion of virtual gene panels to improve diagnostic efficiency for rare genetic diseases 93%
Similar papers in this journal
- MMFP-Tableau: Enabling Precision Mitochondrial Medicine through Integration, Visualization, and Analytics of Clinical and Research Health System Electronic Data 95%
- A Simple Electronic Medical Record System Designed for Research 94%
- Development of a COVID-19 Application Ontology for the ACT Network 93%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.