2024
Natural Language Processing of Clinical Documentation to Assess Functional Status in Patients With Heart Failure
Adejumo P, Thangaraj P, Dhingra L, Aminorroaya A, Zhou X, Brandt C, Xu H, Krumholz H, Khera R. Natural Language Processing of Clinical Documentation to Assess Functional Status in Patients With Heart Failure. JAMA Network Open 2024, 7: e2443925. PMID: 39509128, PMCID: PMC11544492, DOI: 10.1001/jamanetworkopen.2024.43925.Peer-Reviewed Original ResearchConceptsFunctional status assessmentArea under the receiver operating characteristic curveClinical documentationElectronic health record dataHF symptomsOptimal care deliveryHealth record dataAssess functional statusStatus assessmentClinical trial participationProcessing of clinical documentsFunctional status groupCare deliveryOutpatient careMain OutcomesMedical notesTrial participantsNew York Heart AssociationFunctional statusQuality improvementRecord dataHeart failureClinical notesDiagnostic studiesStatus groupsIdentifying incarceration status in the electronic health record using large language models in emergency department settings
Huang T, Socrates V, Gilson A, Safranek C, Chi L, Wang E, Puglisi L, Brandt C, Taylor R, Wang K. Identifying incarceration status in the electronic health record using large language models in emergency department settings. Journal Of Clinical And Translational Science 2024, 8: e53. PMID: 38544748, PMCID: PMC10966832, DOI: 10.1017/cts.2024.496.Peer-Reviewed Original ResearchElectronic health recordsNatural language processingHealth recordsIncarceration statusSignificant social determinant of healthSocial determinants of healthClinic electronic health recordsEHR databasePopulation health initiativesDeterminants of healthMitigate health disparitiesRacial health inequitiesEmergency department settingICD-10 codesHealth inequalitiesNatural language processing modelsHealth disparitiesHealth initiativesDepartment settingEmergency departmentSystem interventionsICD-10Clinical notesStudy populationLanguage model
2023
Identifying suicide documentation in clinical notes through zero‐shot learning
Workman T, Goulet J, Brandt C, Warren A, Eleazer J, Skanderson M, Lindemann L, Blosnich J, O'Leary J, Zeng‐Treitler Q. Identifying suicide documentation in clinical notes through zero‐shot learning. Health Science Reports 2023, 6: e1526. PMID: 37706016, PMCID: PMC10495736, DOI: 10.1002/hsr2.1526.Peer-Reviewed Original ResearchZero-shot learningDeep neural networksTraining dataNeural networkZero-shot learning modelData sparsity issueIdentical training dataTrue positive instancesClinical notesDeep learningDocument contentSparsity issueManual annotationTarget labelsLearning modelSemantic spaceTraining samplesPositive instancesWord featuresTraining casesBaseline modelAuxiliary informationTerms of areaLearningProbability thresholdPatient Dietary Supplements Use: Do Results from Natural Language Processing of Clinical Notes Agree with Survey Data?
Redd D, Workman T, Shao Y, Cheng Y, Tekle S, Garvin J, Brandt C, Zeng-Treitler Q. Patient Dietary Supplements Use: Do Results from Natural Language Processing of Clinical Notes Agree with Survey Data? Medical Sciences 2023, 11: 37. PMID: 37367736, PMCID: PMC10304046, DOI: 10.3390/medsci11020037.Peer-Reviewed Original ResearchConceptsSelf-reported supplement useSupplement useClinical notesStructured medical recordsUnstructured clinical notesPrescription medicationsClinical recordsMedical recordsPhysician guidanceDietary supplementsNatural language processing toolsPatientsNatural language processingFolic acidHealthcare facilitiesLanguage processing toolsSupplementsF1 scoreLanguage processingPotential interactionsNLP performanceProcessing toolsNLP extractionExtra informationMedications
2020
A Prototype Application to Identify LGBT Patients in Clinical Notes
Workman T, Goulet J, Brandt C, Skanderson M, Wang R, Warren A, Eleazer J, Gordon K, Zeng-Treitler Q. A Prototype Application to Identify LGBT Patients in Clinical Notes. 2020, 00: 4270-4275. DOI: 10.1109/bigdata50022.2020.9378109.Peer-Reviewed Original ResearchElectronic health record notesPrototype applicationLGBT patientsRule-based patternLarge data sourcesBinary classification taskRecord notesData scientistsMachine learningClassification taskPositive predictive valueData researchData sourcesTest setClinical relevancePredictive valueHealthcare providersPatientsClinical notesHealth disparitiesLittle workDisproportional burdenApplicationsTaskLearning