%0 Journal Article
%@ 2291-9694
%I JMIR Publications
%V 10
%N 12
%P e42379
%T Construction of Cohorts of Similar Patients From Automatic Extraction of Medical Concepts: Phenotype Extraction Study
%A Gérardin,Christel
%A Mageau,Arthur
%A Mékinian,Arsène
%A Tannier,Xavier
%A Carrat,Fabrice
%+ Institute Pierre Louis Epidemiology and Public Health, Institut National de la Santé et de la Recherche Médicale, Sorbonne Université, 27 rue de Chaligny, Paris, 75012, France, 33 678148466, christel.ducroz-gerardin@iplesp.upmc.fr
%K natural language processing
%K similar patient cohort
%K phenotype
%K systemic disease
%K NLP
%K algorithm
%K automatic extraction
%K automated extraction
%K named entity
%K MeSH
%K medical subject heading
%K data extraction
%K text extraction
%D 2022
%7 19.12.2022
%9 Original Paper
%J JMIR Med Inform
%G English
%X Background: Reliable and interpretable automatic extraction of clinical phenotypes from large electronic medical record databases remains a challenge, especially in a language other than English. Objective: We aimed to provide an automated end-to-end extraction of cohorts of similar patients from electronic health records for systemic diseases. Methods: Our multistep algorithm includes a named-entity recognition step, a multilabel classification using medical subject headings ontology, and the computation of patient similarity. A selection of cohorts of similar patients on a priori annotated phenotypes was performed. Six phenotypes were selected for their clinical significance: P1, osteoporosis; P2, nephritis in systemic erythematosus lupus; P3, interstitial lung disease in systemic sclerosis; P4, lung infection; P5, obstetric antiphospholipid syndrome; and P6, Takayasu arteritis. We used a training set of 151 clinical notes and an independent validation set of 256 clinical notes, with annotated phenotypes, both extracted from the Assistance Publique-Hôpitaux de Paris data warehouse. We evaluated the precision of the 3 patients closest to the index patient for each phenotype with precision-at-3 and recall and average precision. Results: For P1-P4, the precision-at-3 ranged from 0.85 (95% CI 0.75-0.95) to 0.99 (95% CI 0.98-1), the recall ranged from 0.53 (95% CI 0.50-0.55) to 0.83 (95% CI 0.81-0.84), and the average precision ranged from 0.58 (95% CI 0.54-0.62) to 0.88 (95% CI 0.85-0.90). P5-P6 phenotypes could not be analyzed due to the limited number of phenotypes. Conclusions: Using a method close to clinical reasoning, we built a scalable and interpretable end-to-end algorithm for extracting cohorts of similar patients. 
%M 36534446
%R 10.2196/42379
%U https://medinform.jmir.org/2022/12/e42379
%U https://doi.org/10.2196/42379
%U http://www.ncbi.nlm.nih.gov/pubmed/36534446