@Article{info:doi/10.2196/42379,
author="G{\'e}rardin, Christel
and Mageau, Arthur
and M{\'e}kinian, Ars{\`e}ne
and Tannier, Xavier
and Carrat, Fabrice",
title="Construction of Cohorts of Similar Patients From Automatic Extraction of Medical Concepts: Phenotype Extraction Study",
journal="JMIR Med Inform",
year="2022",
month="Dec",
day="19",
volume="10",
number="12",
pages="e42379",
keywords="natural language processing; similar patient cohort; phenotype; systemic disease; NLP; algorithm; automatic extraction; automated extraction; named entity; MeSH; medical subject heading; data extraction; text extraction",
abstract="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-H{\^o}pitaux 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. ",
issn="2291-9694",
doi="10.2196/42379",
url="https://medinform.jmir.org/2022/12/e42379",
url="https://doi.org/10.2196/42379",
url="http://www.ncbi.nlm.nih.gov/pubmed/36534446"
}