2022
Discovering novel drug-supplement interactions using SuppKG generated from the biomedical literature
Schutte D, Vasilakes J, Bompelli A, Zhou Y, Fiszman M, Xu H, Kilicoglu H, Bishop J, Adam T, Zhang R. Discovering novel drug-supplement interactions using SuppKG generated from the biomedical literature. Journal Of Biomedical Informatics 2022, 131: 104120. PMID: 35709900, PMCID: PMC9335448, DOI: 10.1016/j.jbi.2022.104120.Peer-Reviewed Original ResearchConceptsUnified Medical Language SystemComprehensive knowledge graphDomain terminologyKnowledge graphSemantic relationsNatural language processing technologyLanguage processing technologyNLP toolsDownstream tasksF1 scoreSemantic relationshipsDiscovery patternsPubMed abstractsLimited coverageBiomedical literatureProcessing technologyLanguage systemSemRepDietary supplement informationManual reviewNovel methodologyGraphNodesDomainTask
2018
Combine Factual Medical Knowledge and Distributed Word Representation to Improve Clinical Named Entity Recognition.
Wu Y, Yang X, Bian J, Guo Y, Xu H, Hogan W. Combine Factual Medical Knowledge and Distributed Word Representation to Improve Clinical Named Entity Recognition. AMIA Annual Symposium Proceedings 2018, 2018: 1110-1117. PMID: 30815153, PMCID: PMC6371322.Peer-Reviewed Original ResearchConceptsRecurrent neural networkWord embeddingsOne-hot vectorsWord representationsLow-frequency wordsOnly word embeddingsClinical Named Entity RecognitionClinical NER tasksWord embedding methodsConditional Random FieldsStatistical language modelNamed Entity RecognitionUnlabeled corpusLanguage modelLanguage systemNER taskDecent representationFactual medical knowledgeImportant wordsDeep learning modelsEntity recognitionClinical corpusNamed Entity Recognition SystemArt performanceFeature representation
2007
A study of abbreviations in clinical notes.
Xu H, Stetson P, Friedman C. A study of abbreviations in clinical notes. AMIA Annual Symposium Proceedings 2007, 2007: 821-5. PMID: 18693951, PMCID: PMC2655910.Peer-Reviewed Original ResearchConceptsUnified Medical Language SystemNatural language processing systemsLanguage processing systemNarrative clinical notesDetection methodClinical notesDifferent knowledge sourcesSense inventoryDomain expertsNLP systemsCorrect sensesDecision supportText corporaKnowledge sourcesError detectionProcessing systemBiomedical literatureStudy of abbreviationsLanguage systemPatient informationAmbiguity rateBetter detection methodsDatabaseAnnotationAbbreviationsUsing contextual and lexical features to restructure and validate the classification of biomedical concepts
Fan J, Xu H, Friedman C. Using contextual and lexical features to restructure and validate the classification of biomedical concepts. BMC Bioinformatics 2007, 8: 264. PMID: 17650333, PMCID: PMC2014782, DOI: 10.1186/1471-2105-8-264.Peer-Reviewed Original ResearchConceptsUnified Medical Language SystemString-based approachesMean reciprocal rankReciprocal rankNatural language processingError rateContextual featuresLexical featuresIntegration of dataLow error rateReasoning systemAutomatic approachComplementary classifiersLanguage processingClassification approachBiomedical terminologiesClassification errorOntological conceptsBiomedical conceptsOntological termsSyntactic approachLanguage systemClassifierSyntactic featuresOntology