TY  - JOUR
A1  - De Freitas, Jessica K.
A1  - Johnson, Kipp W.
A1  - Golden, Eddye
A1  - Nadkarni, Girish N.
A1  - Dudley, Joel T.
A1  - Böttinger, Erwin
A1  - Glicksberg, Benjamin S.
A1  - Miotto, Riccardo
T1  - Phe2vec
T2  - Patterns
N2  - Robust phenotyping of patients from electronic health records (EHRs) at scale is a challenge in clinical informatics. Here, we introduce Phe2vec, an automated framework for disease phenotyping from EHRs based on unsupervised learning and assess its effectiveness against standard rule-based algorithms from Phenotype KnowledgeBase (PheKB). Phe2vec is based on pre-computing embeddings of medical concepts and patients' clinical history. Disease phenotypes are then derived from a seed concept and its neighbors in the embedding space. Patients are linked to a disease if their embedded representation is close to the disease phenotype. Comparing Phe2vec and PheKB cohorts head-to-head using chart review, Phe2vec performed on par or better in nine out of ten diseases. Differently from other approaches, it can scale to any condition and was validated against widely adopted expert-based standards. Phe2vec aims to optimize clinical informatics research by augmenting current frameworks to characterize patients by condition and derive reliable disease cohorts.
Y1  - 2021
UR  - https://publishup.uni-potsdam.de/frontdoor/index/index/docId/60419
SN  - 2666-3899
VL  - 2
IS  - 9
PB  - Elsevier
CY  - Amsterdam
ER  -