Construction of Cohorts of Similar Patients From Automatic Extraction of Medical Concepts: Phenotype Extraction Study

• Published in: JMIR medical informatics Vol. 10; no. 12; p. e42379
• Main Authors: Gérardin, Christel, Mageau, Arthur, Mékinian, Arsène, Tannier, Xavier, Carrat, Fabrice
• Format: Journal Article
• Language: English
• Published: Canada JMIR Publications 19.12.2022
• Subjects: Algorithms; Annotations; Classification; Codes; Computer Science; Data Structures and Algorithms; Datasets; Electronic health records; Genotype & phenotype; Hospitalization; Lupus; Natural language processing; Original Paper; Patients; Physiology; Rare diseases; Scleroderma; Womens health; France; phenotype; text extraction; natural language processing; MeSH; similar patient cohort; systemic disease; data extraction; NLP; named entity; medical subject heading; automated extraction; algorithm; automatic extraction; Medical subject heading; Named entity; Algorithm; Similar patient cohort; Text extraction; Phenotype; Automatic extraction; Systemic disease; Automated extraction; Natural language processing; Data extraction
• ISSN: 2291-9694; 2291-9694
• DOI: 10.2196/42379

Reliable and interpretable automatic extraction of clinical phenotypes from large electronic medical record databases remains a challenge, especially in a language other than English. We aimed to provide an automated end-to-end extraction of cohorts of similar patients from electronic health records for systemic diseases. 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. 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. Using a method close to clinical reasoning, we built a scalable and interpretable end-to-end algorithm for extracting cohorts of similar patients.