2019
Cost-aware active learning for named entity recognition in clinical text
Wei Q, Chen Y, Salimi M, Denny J, Mei Q, Lasko T, Chen Q, Wu S, Franklin A, Cohen T, Xu H. Cost-aware active learning for named entity recognition in clinical text. Journal Of The American Medical Informatics Association 2019, 26: 1314-1322. PMID: 31294792, PMCID: PMC6798575, DOI: 10.1093/jamia/ocz102.Peer-Reviewed Original ResearchConceptsAnnotation costUser studyActive learningAL methodsAL algorithmCost-CAUSEReal-world environmentsAnnotation taskAnnotation timeAnnotation accuracyEntity recognitionClinical textAnnotation dataPassive learningInformative examplesCurve scoreMost approachesSimulation areaUsersSyntactic featuresLearningCost measuresAlgorithmCostAnnotationCost-sensitive Active Learning for Phenotyping of Electronic Health Records.
Ji Z, Wei Q, Franklin A, Cohen T, Xu H. Cost-sensitive Active Learning for Phenotyping of Electronic Health Records. AMIA Joint Summits On Translational Science Proceedings 2019, 2019: 829-838. PMID: 31259040, PMCID: PMC6568101.Peer-Reviewed Original ResearchAnnotation timeElectronic health recordsActive learningMachine learning-based methodsCost-sensitive active learningLarge annotated datasetLearning-based methodsHealth recordsUse casesAnnotated datasetUser 1AL algorithmUser 2Phenotyping algorithmAL approachSecondary useAlgorithmBetter performanceActual timeLearningExperimental resultsBreast cancer patientsDatasetModel performancePassive learning
2015
A study of active learning methods for named entity recognition in clinical text
Chen Y, Lasko T, Mei Q, Denny J, Xu H. A study of active learning methods for named entity recognition in clinical text. Journal Of Biomedical Informatics 2015, 58: 11-18. PMID: 26385377, PMCID: PMC4934373, DOI: 10.1016/j.jbi.2015.09.010.Peer-Reviewed Original ResearchConceptsClinical NER tasksMachine learningAnnotation costF-measureEntity recognitionNER taskActive learningLearning methodsI2b2/VA NLP challengeNatural language processing systemsPerformance of MLClinical natural language processing (NLP) systemsSequential labeling tasksSupervised machine learningAL methodsLanguage processing systemDiversity-based methodReal-time settingActive learning methodsNew AL methodsNER corpusDomain expertsUncertainty samplingAnnotation effortClinical text
2013
Applying active learning to high-throughput phenotyping algorithms for electronic health records data
Chen Y, Carroll R, Hinz E, Shah A, Eyler A, Denny J, Xu H. Applying active learning to high-throughput phenotyping algorithms for electronic health records data. Journal Of The American Medical Informatics Association 2013, 20: e253-e259. PMID: 23851443, PMCID: PMC3861916, DOI: 10.1136/amiajnl-2013-001945.Peer-Reviewed Original ResearchConceptsActive learningUnrefined featuresSupervised Machine Learning AlgorithmsRefined featuresPhenotyping algorithmElectronic health record dataMachine Learning AlgorithmsHealth record dataVenous thromboembolismRheumatoid arthritisFeature engineeringDomain expertsDomain knowledgePhenotyping tasksLearning algorithmFeature setsLearning approachColorectal cancerAL approachCurve scorePassive learning approachHigh-throughput phenotyping methodsAlgorithmSmall setRecord data