{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"submitter":["Liu S"],"funding":["National Center for Advancing Translational Sciences","Bill & Melinda Gates Foundation","Bill & Melinda Gates Foundation","NCATS NIH HHS","NLM NIH HHS","National Institutes of Health","NIH HHS"],"pagination":["2036-2040"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC10654844"],"repository":["biostudies-literature"],"omics_type":["Unknown"],"volume":["30(12)"],"pubmed_abstract":["Despite recent methodology advancements in clinical natural language processing (NLP), the adoption of clinical NLP models within the translational research community remains hindered by process heterogeneity and human factor variations. Concurrently, these factors also dramatically increase the difficulty in developing NLP models in multi-site settings, which is necessary for algorithm robustness and generalizability. Here, we reported on our experience developing an NLP solution for Coronavirus Disease 2019 (COVID-19) signs and symptom extraction in an open NLP framework from a subset of sites participating in the National COVID Cohort (N3C). We then empirically highlight the benefits of multi-site data for both symbolic and statistical methods, as well as highlight the need for federate"],"journal":["Journal of the American Medical Informatics Association : JAMIA"],"pubmed_title":["An open natural language processing (NLP) framework for EHR-based clinical research: a case demonstration using the National COVID Cohort Collaborative (N3C)."],"pmcid":["PMC10654844"],"funding_grant_id":["U01 TR002062","U24 TR002306","R01 LM013240","UM1 TR004400"],"pubmed_authors":["Fuentes R","Liu H","Fu S","Liu M","Hong SS","Liu S","Schaffter T","Williams A","Zhang R","Chute CG","Miller R","Wang L","Osborne JD","Szolovits P","Kavuluru R","Duong T","Wen A","Schutte D","He H","Rouhizadeh M","Xu H","He Y","Haendel MA","Abu-El-Rub N","Harris D","Pfaff E","Topaloglu U","Saltz JH"],"additional_accession":[]},"is_claimable":false,"name":"An open natural language processing (NLP) framework for EHR-based clinical research: a case demonstration using the National COVID Cohort Collaborative (N3C).","description":"Despite recent methodology advancements in clinical natural language processing (NLP), the adoption of clinical NLP models within the translational research community remains hindered by process heterogeneity and human factor variations. Concurrently, these factors also dramatically increase the difficulty in developing NLP models in multi-site settings, which is necessary for algorithm robustness and generalizability. Here, we reported on our experience developing an NLP solution for Coronavirus Disease 2019 (COVID-19) signs and symptom extraction in an open NLP framework from a subset of sites participating in the National COVID Cohort (N3C). We then empirically highlight the benefits of multi-site data for both symbolic and statistical methods, as well as highlight the need for federate","dates":{"release":"2023-01-01T00:00:00Z","publication":"2023 Nov","modification":"2025-04-21T23:52:41.01Z","creation":"2025-04-05T19:22:15.287Z"},"accession":"S-EPMC10654844","cross_references":{"pubmed":["37555837"],"doi":["10.1093/jamia/ocad134"]}}