2024
Extracting Systemic Anticancer Therapy and Response Information From Clinical Notes Following the RECIST Definition
Zuo X, Kumar A, Shen S, Li J, Cong G, Jin E, Chen Q, Warner J, Yang P, Xu H. Extracting Systemic Anticancer Therapy and Response Information From Clinical Notes Following the RECIST Definition. JCO Clinical Cancer Informatics 2024, 8: e2300166. PMID: 38885475, DOI: 10.1200/cci.23.00166.Peer-Reviewed Original ResearchConceptsNatural language processingDomain-specific language modelsNatural language processing systemsInformation extraction systemRule-based moduleNarrative clinical textsNLP tasksEntity recognitionText normalizationAssertion classificationLanguage modelInformation extractionClinical textElectronic health recordsLearning-basedClinical notesLanguage processingTest setSystem performanceHealth recordsResponse extractionTime-consumingAnticancer therapyInformationAssessment information
2021
COVID-19 SignSym: a fast adaptation of a general clinical NLP tool to identify and normalize COVID-19 signs and symptoms to OMOP common data model
Wang J, Abu-El-Rub N, Gray J, Pham H, Zhou Y, Manion F, Liu M, Song X, Xu H, Rouhizadeh M, Zhang Y. COVID-19 SignSym: a fast adaptation of a general clinical NLP tool to identify and normalize COVID-19 signs and symptoms to OMOP common data model. Journal Of The American Medical Informatics Association 2021, 28: 1275-1283. PMID: 33674830, PMCID: PMC7989301, DOI: 10.1093/jamia/ocab015.Peer-Reviewed Original ResearchConceptsNatural language processing toolsCommon data modelLanguage processing toolsElectronic health recordsClinical natural language processing toolsData modelDeep learning-based modelProcessing toolsOMOP Common Data ModelPattern-based rulesObservational Medical Outcomes Partnership Common Data ModelLearning-based modelsSpecific information needsUse casesNLP toolsClinical textFree textExtensive evaluationDownloadable packageInformation needsHybrid approachResearch communityHealth recordsData sourcesHigh performanceExtracting postmarketing adverse events from safety reports in the vaccine adverse event reporting system (VAERS) using deep learning
Du J, Xiang Y, Sankaranarayanapillai M, Zhang M, Wang J, Si Y, Pham H, Xu H, Chen Y, Tao C. Extracting postmarketing adverse events from safety reports in the vaccine adverse event reporting system (VAERS) using deep learning. Journal Of The American Medical Informatics Association 2021, 28: 1393-1400. PMID: 33647938, PMCID: PMC8279785, DOI: 10.1093/jamia/ocab014.Peer-Reviewed Original ResearchConceptsDeep learning algorithmsLearning-based methodsVaccine Adverse Event Reporting SystemLearning algorithmArt deep learning algorithmsDeep learning-based methodsConventional machine learning-based methodsMachine learning-based methodsConventional machine learningAdverse Event Reporting SystemGuillain-Barré syndromeLarge modelsAdverse eventsEvent Reporting SystemVAERS reportsDeep learningMachine learningEntity recognitionPeer modelInfluenza vaccine safetyNervous system disordersExact matchVaccine adverse eventsSafety reportsReporting system
2020
Asthma Exacerbation Prediction and Risk Factor Analysis Based on a Time-Sensitive, Attentive Neural Network: Retrospective Cohort Study
Xiang Y, Ji H, Zhou Y, Li F, Du J, Rasmy L, Wu S, Zheng W, Xu H, Zhi D, Zhang Y, Tao C. Asthma Exacerbation Prediction and Risk Factor Analysis Based on a Time-Sensitive, Attentive Neural Network: Retrospective Cohort Study. Journal Of Medical Internet Research 2020, 22: e16981. PMID: 32735224, PMCID: PMC7428917, DOI: 10.2196/16981.Peer-Reviewed Original ResearchConceptsAttentive Neural NetworkAsthma exacerbationsRisk factorsNeural networkAdvanced deep learning modelsClinical variablesDeep learning modelsCerner Health Facts databaseLarge electronic health recordNeural network modelRetrospective cohort studyHealth Facts databasePotential risk factorsRisk factor analysisPersonalized risk factorsElectronic health recordsBaseline methodsLearning modelPersonalized risk scoreProgressive asthmaAsthma symptomsEsophageal refluxAdult patientsCohort studyTime-Sensitive
2019
Applying a deep learning-based sequence labeling approach to detect attributes of medical concepts in clinical text
Xu J, Li Z, Wei Q, Wu Y, Xiang Y, Lee H, Zhang Y, Wu S, Xu H. Applying a deep learning-based sequence labeling approach to detect attributes of medical concepts in clinical text. BMC Medical Informatics And Decision Making 2019, 19: 236. PMID: 31801529, PMCID: PMC6894107, DOI: 10.1186/s12911-019-0937-2.Peer-Reviewed Original ResearchConceptsSequence labeling approachMedical conceptsEntity recognitionRelation classificationClinical textDetection taskBidirectional long short-term memory networkLong short-term memory networkShort-term memory networkConditional Random FieldsSequence labeling problemTraditional methodsNLP applicationsBi-LSTMNeural architectureLabeling problemLabeling approachMemory networkNovel solutionRandom fieldsHigh accuracyEfficient wayTaskAttributesClassificationDeep learning in clinical natural language processing: a methodical review
Wu S, Roberts K, Datta S, Du J, Ji Z, Si Y, Soni S, Wang Q, Wei Q, Xiang Y, Zhao B, Xu H. Deep learning in clinical natural language processing: a methodical review. Journal Of The American Medical Informatics Association 2019, 27: 457-470. PMID: 31794016, PMCID: PMC7025365, DOI: 10.1093/jamia/ocz200.Peer-Reviewed Original ResearchConceptsNatural language processingClinical natural language processingDeep learningLanguage processingComputing Machinery Digital LibraryInformation extraction tasksMedical informatics communityComputational Linguistics anthologyRecurrent neural networkDigital librariesText classificationElectronic health recordsExtraction taskEntity recognitionWord2vec embeddingsNeural networkRelation extractionNLP communityNLP researchInformatics communitySpecific tasksHealth recordsNLP problemLearningClinical domainsExtracting entities with attributes in clinical text via joint deep learning
Shi X, Yi Y, Xiong Y, Tang B, Chen Q, Wang X, Ji Z, Zhang Y, Xu H. Extracting entities with attributes in clinical text via joint deep learning. Journal Of The American Medical Informatics Association 2019, 26: 1584-1591. PMID: 31550346, PMCID: PMC7647140, DOI: 10.1093/jamia/ocz158.Peer-Reviewed Original ResearchMeSH KeywordsData MiningDatasets as TopicDeep LearningElectronic Health RecordsHumansNatural Language ProcessingConceptsBidirectional long short-term memoryShort-term memoryLong short-term memoryNatural language processingEntity recognitionChinese corpusBest F1English corpusLanguage processingJoint deep learningTaskConditional Random FieldsRelation extractionAttribute recognitionMemorySequential subtasksDeep learning methodsClinical textA study of deep learning approaches for medication and adverse drug event extraction from clinical text
Wei Q, Ji Z, Li Z, Du J, Wang J, Xu J, Xiang Y, Tiryaki F, Wu S, Zhang Y, Tao C, Xu H. A study of deep learning approaches for medication and adverse drug event extraction from clinical text. Journal Of The American Medical Informatics Association 2019, 27: 13-21. PMID: 31135882, PMCID: PMC6913210, DOI: 10.1093/jamia/ocz063.Peer-Reviewed Original ResearchConceptsDeep learning-based approachDeep learning approachLearning-based approachTraditional machineLearning approachNational NLP Clinical ChallengesAdverse drug event extractionOutperform traditional machineDifferent ensemble approachesConditional Random FieldsSequence labeling approachMIMIC-III databaseEvent extractionMedical domainEntity recognitionClassification componentF1 scoreClinical textRelation extractionClinical documentsVector machineEnd evaluationEnsemble approachClinical corpusMachineTime-sensitive clinical concept embeddings learned from large electronic health records
Xiang Y, Xu J, Si Y, Li Z, Rasmy L, Zhou Y, Tiryaki F, Li F, Zhang Y, Wu Y, Jiang X, Zheng W, Zhi D, Tao C, Xu H. Time-sensitive clinical concept embeddings learned from large electronic health records. BMC Medical Informatics And Decision Making 2019, 19: 58. PMID: 30961579, PMCID: PMC6454598, DOI: 10.1186/s12911-019-0766-3.Peer-Reviewed Original ResearchMeSH KeywordsAlgorithmsDatabases, FactualDeep LearningElectronic Health RecordsHumansInformation Storage and RetrievalTime FactorsConceptsConcept similarity measurePositive pointwise mutual informationConcept embeddingsSimilarity measurePredictive modeling tasksLarge electronic health recordTime-sensitive informationPointwise mutual informationImportant research areaDeep learningElectronic health recordsMedical domainLarge electronic health record databaseWord2vec embeddingsTemporal dependenciesLearning methodsFastText algorithmModeling tasksResultsOur experimentsExtrinsic evaluationIntrinsic evaluationMutual informationHealth recordsDistributional representationsEmbeddingParsing clinical text using the state-of-the-art deep learning based parsers: a systematic comparison
Zhang Y, Tiryaki F, Jiang M, Xu H. Parsing clinical text using the state-of-the-art deep learning based parsers: a systematic comparison. BMC Medical Informatics And Decision Making 2019, 19: 77. PMID: 30943955, PMCID: PMC6448179, DOI: 10.1186/s12911-019-0783-2.Peer-Reviewed Original ResearchIntegrating shortest dependency path and sentence sequence into a deep learning framework for relation extraction in clinical text
Li Z, Yang Z, Shen C, Xu J, Zhang Y, Xu H. Integrating shortest dependency path and sentence sequence into a deep learning framework for relation extraction in clinical text. BMC Medical Informatics And Decision Making 2019, 19: 22. PMID: 30700301, PMCID: PMC6354333, DOI: 10.1186/s12911-019-0736-9.Peer-Reviewed Original ResearchMeSH KeywordsDeep LearningElectronic Health RecordsHumansMedical Informatics ApplicationsNatural Language ProcessingConceptsShortest dependency pathConvolutional neural networkNeural network architectureNatural language processingSentence sequenceRelation extractionClinical relation extractionTarget entityNetwork architectureClinical textNeural networkRepresentation moduleDependency pathsDeep learning-based approachNew neural network architectureBidirectional long short-term memory networkLong short-term memory networkDeep learning frameworkDeep neural networksShort-term memory networkLearning-based approachNovel neural approachRelation extraction datasetBi-LSTM networkSyntactic features
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 ResearchMeSH KeywordsDeep LearningHumansNatural Language ProcessingNeural Networks, ComputerUnified Medical Language SystemConceptsRecurrent 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 representationExtraction of BI-RADS findings from breast ultrasound reports in Chinese using deep learning approaches
Miao S, Xu T, Wu Y, Xie H, Wang J, Jing S, Zhang Y, Zhang X, Yang Y, Zhang X, Shan T, Wang L, Xu H, Wang S, Liu Y. Extraction of BI-RADS findings from breast ultrasound reports in Chinese using deep learning approaches. International Journal Of Medical Informatics 2018, 119: 17-21. PMID: 30342682, DOI: 10.1016/j.ijmedinf.2018.08.009.Peer-Reviewed Original ResearchConceptsLearning-based methodsBreast ultrasound reportsElectronic health record systemsTraditional machine learning-based methodsDeep learning-based approachDeep learning-based methodsNatural language processing methodsMachine learning-based methodsDeep learning technologyConditional random field algorithmDeep learning approachLanguage processing methodsLearning-based approachUltrasound reportsBreast cancer researchRule-based methodHealth record systemsBreast radiology reportsLearning technologyNLP approachLearning approachField algorithmDetailed clinical informationWide adoptionRecord systemPredict effective drug combination by deep belief network and ontology fingerprints
Chen G, Tsoi A, Xu H, Zheng W. Predict effective drug combination by deep belief network and ontology fingerprints. Journal Of Biomedical Informatics 2018, 85: 149-154. PMID: 30081101, DOI: 10.1016/j.jbi.2018.07.024.Peer-Reviewed Original ResearchExtracting psychiatric stressors for suicide from social media using deep learning
Du J, Zhang Y, Luo J, Jia Y, Wei Q, Tao C, Xu H. Extracting psychiatric stressors for suicide from social media using deep learning. BMC Medical Informatics And Decision Making 2018, 18: 43. PMID: 30066665, PMCID: PMC6069295, DOI: 10.1186/s12911-018-0632-8.Peer-Reviewed Original ResearchMeSH KeywordsAlgorithmsDeep LearningHumansNeural Networks, ComputerSocial MediaStress, PsychologicalSuicide PreventionConceptsConvolutional neural networkRecurrent neural networkDeep learningConditional Random FieldsSupport vector machineSuicide-related tweetsClinical textNeural networkPsychiatric stressorsExtra TreesBinary classifierTransfer learning strategiesEntity recognition taskSocial mediaExact matchTraditional machineAnnotation costLearning strategiesRecognition problemSharing flowInexact matchVector machineTwitter dataRecognition taskTwitterA study of generalizability of recurrent neural network-based predictive models for heart failure onset risk using a large and heterogeneous EHR data set
Rasmy L, Wu Y, Wang N, Geng X, Zheng W, Wang F, Wu H, Xu H, Zhi D. A study of generalizability of recurrent neural network-based predictive models for heart failure onset risk using a large and heterogeneous EHR data set. Journal Of Biomedical Informatics 2018, 84: 11-16. PMID: 29908902, PMCID: PMC6076336, DOI: 10.1016/j.jbi.2018.06.011.Peer-Reviewed Original ResearchConceptsRecurrent neural networkOnset riskCapability of RNNCerner Health FactsHeterogeneous EHR dataHeart failure patientsData setsElectronic health record dataDeep learning modelsDifferent patient populationsNeural network-based predictive modelDifferent patient groupsHealth record dataEHR data setsPredictive modelingSmall data setsFailure patientsPatient groupPatient populationReduction of AUCNeural networkRNN modelRETAIN modelHealth FactsHospitalClinical Named Entity Recognition Using Deep Learning Models.
Wu Y, Jiang M, Xu J, Zhi D, Xu H. Clinical Named Entity Recognition Using Deep Learning Models. AMIA Annual Symposium Proceedings 2018, 2017: 1812-1819. PMID: 29854252, PMCID: PMC5977567.Peer-Reviewed Original ResearchMeSH KeywordsDatasets as TopicDeep LearningMedical RecordsNatural Language ProcessingNeural Networks, ComputerConceptsClinical Named Entity RecognitionNamed Entity RecognitionDeep learning modelsConvolutional neural networkClinical NER systemRecurrent neural networkNeural networkLearning modelEntity recognitionRNN modelNER systemDeep neural network architecturePopular deep learning architecturesNatural language processing tasksUnsupervised learning featuresConditional random field modelAutomatic feature learningDeep learning architectureClinical NER tasksDeep neural networksNeural network architectureClinical concept extractionLanguage processing tasksFeature learningLearning architecture