Clinical Note Section Detection Using a Hidden Markov Model of Unified Medical Language System Semantic Types.
Eisman A, Brown K, Chen E, Sarkar I. Clinical Note Section Detection Using a Hidden Markov Model of Unified Medical Language System Semantic Types. AMIA Annual Symposium Proceedings 2022, 2021: 418-427. PMID: 35308919, PMCID: PMC8861726.Peer-Reviewed Original ResearchConceptsNatural language processingUnified Medical Language SystemNatural language processing tasksMedical Language SystemSources of biomedical dataClinical note sectionsUnified Medical Language System semantic typesHidden Markov ModelNLP toolsLanguage processingBiomedical dataSection detectionClinical notesSemantic typesHMMLanguage systemMedical Information Mart for Intensive Care IIIExtracting Angina Symptoms from Clinical Notes Using Pre-Trained Transformer Architectures.
Eisman A, Shah N, Eickhoff C, Zerveas G, Chen E, Wu W, Sarkar I. Extracting Angina Symptoms from Clinical Notes Using Pre-Trained Transformer Architectures. AMIA Annual Symposium Proceedings 2021, 2020: 412-421. PMID: 33936414, PMCID: PMC8075440.Peer-Reviewed Original ResearchConceptsChest painAnginal symptomsPalliation of chest painSubsternal chest painShortness of breathPrimary care physicians' notes.Consecutive patientsCardiac testingCardiac riskAngina symptomsPainCardiovascular managementPhysician notesSymptomsClinical notesIllness sectionTransformer architectureSample size