biostudies-literatureUnknown8(5)Bunnell HT<h4>Objective</h4>To develop a natural language processing (NLP) pipeline for unstructured electronic health record (EHR) data to identify symptoms and functional impacts associated with Long COVID in children.<h4>Materials and methods</h4>We analyzed 48 287 outpatient progress notes from 10 618 pediatric patients from 12 institutions. We evaluated notes obtained 28 to 179 days after a COVID-19 diagnosis or positive test. Two samples were examined: patients with evidence of Long COVID and patients with acute COVID but no evidence of Long COVID based on diagnostic codes. The pipeline identified clinical concepts associated with 21 symptoms and 4 functional impact categories. Subject matter experts (SMEs) screened a sample of 4586 terms from the NLP output to assess pipeline accuracy. PrevalJAMIA openooaf089https://www.ebi.ac.uk/biostudies/studies/S-EPMC12409404biostudies-literatureA natural language processing pipeline for identifying pediatric long COVID symptoms and functional impacts in freeform clinical notes: a RECOVER study.PMC12409404Rivera-Sepulveda ARao SJhaveri RTruong JSills MRMartinez ATDavies SJDChristakis DACowell LGPajor NMCase AForrest CBBailey LCSalamon KSThorpe LRosenman MKelleher KJSchroeder ACummins MRLetts RMorse KEDivers JLorman VWuller SWDavenport MAPatel PBMandel HTaylor BWRutter JLe TRanade DReeder PRECOVER ConsortiumNandagopal JPAStoddard AUtidjian LHuang YGouripeddi RMendonca EADiaz IBunnell HTReedy CKenny RfalseA natural language processing pipeline for identifying pediatric long COVID symptoms and functional impacts in freeform clinical notes: a RECOVER study.<h4>Objective</h4>To develop a natural language processing (NLP) pipeline for unstructured electronic health record (EHR) data to identify symptoms and functional impacts associated with Long COVID in children.<h4>Materials and methods</h4>We analyzed 48 287 outpatient progress notes from 10 618 pediatric patients from 12 institutions. We evaluated notes obtained 28 to 179 days after a COVID-19 diagnosis or positive test. Two samples were examined: patients with evidence of Long COVID and patients with acute COVID but no evidence of Long COVID based on diagnostic codes. The pipeline identified clinical concepts associated with 21 symptoms and 4 functional impact categories. Subject matter experts (SMEs) screened a sample of 4586 terms from the NLP output to assess pipeline accuracy. Preval2025-01-01T00:00:00Z2025 Oct2026-06-03T07:06:12.911Z2026-05-29T03:05:27.548ZS-EPMC124094044091894110.1093/jamiaopen/ooaf089