2024
A taxonomy for advancing systematic error analysis in multi-site electronic health record-based clinical concept extraction
Fu S, Wang L, He H, Wen A, Zong N, Kumari A, Liu F, Zhou S, Zhang R, Li C, Wang Y, St Sauver J, Liu H, Sohn S. A taxonomy for advancing systematic error analysis in multi-site electronic health record-based clinical concept extraction. Journal Of The American Medical Informatics Association 2024, 31: 1493-1502. PMID: 38742455, PMCID: PMC11187420, DOI: 10.1093/jamia/ocae101.Peer-Reviewed Original ResearchNatural language processingClinical concept extractionElectronic health recordsConcept extractionClinical natural language processingConcept extraction taskNatural language processing modelsElectronic health record settingsDomain-specific knowledgeError taxonomyHeterogeneity of electronic health recordsReal-world dataAnalysis processExtraction taskOWL formatAnnotated examplesError analysisNLP modelsCommunity feedbackLanguage processingMulti-site settingConduct error analysisError classesError typesError analysis process
2023
Acquisition of a Lexicon for Family History Information: Bidirectional Encoder Representations From Transformers–Assisted Sublanguage Analysis
Wang L, He H, Wen A, Moon S, Fu S, Peterson K, Ai X, Liu S, Kavuluru R, Liu H. Acquisition of a Lexicon for Family History Information: Bidirectional Encoder Representations From Transformers–Assisted Sublanguage Analysis. JMIR Medical Informatics 2023, 11: e48072. PMID: 37368483, PMCID: PMC10337517, DOI: 10.2196/48072.Peer-Reviewed Original ResearchChallenge data setInformation extractionClinical decision support applicationsNatural language processing systemsUnified Medical Language SystemLexical resourcesDecision support applicationsBidirectional Encoder RepresentationsLanguage processing systemConcept unique identifiersData setsTransformer-based methodData analyticsElectronic health recordsF1 scoreClinical notesMedicine Clinical TermsEncoder RepresentationsSupport applicationsUnique identifiersProcessing systemSublanguage analysisHistory informationReasonable performanceSystematized Nomenclature
2022
Recommended practices and ethical considerations for natural language processing‐assisted observational research: A scoping review
Fu S, Wang L, Moon S, Zong N, He H, Pejaver V, Relevo R, Walden A, Haendel M, Chute C, Liu H. Recommended practices and ethical considerations for natural language processing‐assisted observational research: A scoping review. Clinical And Translational Science 2022, 16: 398-411. PMID: 36478394, PMCID: PMC10014687, DOI: 10.1111/cts.13463.Peer-Reviewed Original ResearchConceptsWorld Health OrganizationElectronic health recordsNatural language processingObservational clinical studyReporting guidelinesObservational researchStandardized reporting guidelinesClinical studiesObservational studyClinical informationNLP methodologyClinical researchHealth OrganizationHealth recordsAssessment of Electronic Health Record for Cancer Research and Patient Care Through a Scoping Review of Cancer Natural Language Processing
Wang L, Fu S, Wen A, Ruan X, He H, Liu S, Moon S, Mai M, Riaz I, Wang N, Yang P, Xu H, Warner J, Liu H. Assessment of Electronic Health Record for Cancer Research and Patient Care Through a Scoping Review of Cancer Natural Language Processing. JCO Clinical Cancer Informatics 2022, 6: e2200006. PMID: 35917480, PMCID: PMC9470142, DOI: 10.1200/cci.22.00006.Peer-Reviewed Original ResearchEvaluation of mCODE Coverage in EHR: a Scoping Review of Cancer Natural Language Processing
Wang L, Fu S, Wen A, Ruan X, He H, Liu S, Moon S, Mai M, Riaz I, Wang N, Yang P, Xu H, Warner J, Liu H. Evaluation of mCODE Coverage in EHR: a Scoping Review of Cancer Natural Language Processing. 2022, 00: 517-518. DOI: 10.1109/ichi54592.2022.00094.Peer-Reviewed Original Research
2020
Impact of Diverse Data Sources on Computational Phenotyping
Wang L, Olson J, Bielinski S, St. Sauver J, Fu S, He H, Cicek M, Hathcock M, Cerhan J, Liu H. Impact of Diverse Data Sources on Computational Phenotyping. Frontiers In Genetics 2020, 11: 556. PMID: 32582289, PMCID: PMC7283539, DOI: 10.3389/fgene.2020.00556.Peer-Reviewed Original ResearchDiverse data sourcesElectronic health recordsComputational phenotypingData fragmentationPhenotyping algorithmData sourcesRochester Epidemiology ProjectPositive predictive valueSingle data sourceFalse negative rateRheumatoid arthritisEHR dataMultiple health care systemsHealth recordsMayo dataIncomplete dataType 2 diabetes mellitusAlgorithmPhenotype informationIntegrated sourceHealth care systemScientific discoveryT2DM controlDiabetes mellitusMedical records