2019
Learning from electronic health records across multiple sites: A communication-efficient and privacy-preserving distributed algorithm
Duan R, Boland M, Liu Z, Liu Y, Chang H, Xu H, Chu H, Schmid C, Forrest C, Holmes J, Schuemie M, Berlin J, Moore J, Chen Y. Learning from electronic health records across multiple sites: A communication-efficient and privacy-preserving distributed algorithm. Journal Of The American Medical Informatics Association 2019, 27: 376-385. PMID: 31816040, PMCID: PMC7025371, DOI: 10.1093/jamia/ocz199.Peer-Reviewed Original ResearchMeSH KeywordsAlgorithmsComputer SimulationConfidentialityData AnalysisDatasets as TopicDrug-Related Side Effects and Adverse ReactionsElectronic Health RecordsFemaleFetal DeathHumansLogistic ModelsOdds RatioPregnancyA 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 ResearchMeSH KeywordsAlgorithmsDeep LearningDrug-Related Side Effects and Adverse ReactionsElectronic Health RecordsHumansInformation Storage and RetrievalMachine LearningNarrationNatural Language ProcessingPharmaceutical PreparationsConceptsDeep 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 corpusMachine
2017
Identification of adverse drug-drug interactions through causal association rule discovery from spontaneous adverse event reports
Cai R, Liu M, Hu Y, Melton B, Matheny M, Xu H, Duan L, Waitman L. Identification of adverse drug-drug interactions through causal association rule discovery from spontaneous adverse event reports. Artificial Intelligence In Medicine 2017, 76: 7-15. PMID: 28363289, PMCID: PMC6438384, DOI: 10.1016/j.artmed.2017.01.004.Peer-Reviewed Original ResearchMeSH KeywordsAdverse Drug Reaction Reporting SystemsBayes TheoremData MiningDrug InteractionsDrug-Related Side Effects and Adverse ReactionsHumansMachine LearningConceptsDrug-drug interactionsTraditional association rule mining methodsAssociation rule mining methodAssociation rule discoveryAssociation rule miningRule mining methodAdverse Event Reporting SystemAdverse drug-drug interactionsAdverse event reportsAdverse eventsData-driven discoveryHigher-order associationsRule miningRule discoveryDrug safety surveillanceMining methodsBayesian networkDrug combinationsChallenging taskCausal associationDrug Administration Adverse Event Reporting SystemDDI identificationAdverse drug reactionsCombination of drugsEvent Reporting SystemLiterature-Based Discovery of Confounding in Observational Clinical Data.
Malec S, Wei P, Xu H, Bernstam E, Myneni S, Cohen T. Literature-Based Discovery of Confounding in Observational Clinical Data. AMIA Annual Symposium Proceedings 2017, 2016: 1920-1929. PMID: 28269951, PMCID: PMC5333204.Peer-Reviewed Original ResearchMeSH KeywordsArea Under CurveBiomedical ResearchConfounding Factors, EpidemiologicDrug-Related Side Effects and Adverse ReactionsElectronic Health RecordsHumansModels, TheoreticalPharmacovigilance
2014
Identifying plausible adverse drug reactions using knowledge extracted from the literature
Shang N, Xu H, Rindflesch T, Cohen T. Identifying plausible adverse drug reactions using knowledge extracted from the literature. Journal Of Biomedical Informatics 2014, 52: 293-310. PMID: 25046831, PMCID: PMC4261011, DOI: 10.1016/j.jbi.2014.07.011.Peer-Reviewed Original ResearchMeSH KeywordsAdverse Drug Reaction Reporting SystemsAlgorithmsBiomedical ResearchData MiningDrug-Related Side Effects and Adverse ReactionsHumansMEDLINENatural Language ProcessingROC CurveSemanticsConceptsPredication-based Semantic IndexingReflective Random IndexingLBD methodsNatural language processing toolsBiomedical literatureDrug-adverse event associationsLanguage processing toolsSemantic indexingElectronic health recordsRandom IndexingHuman reviewVast repositoryDiscovery methodsVolume of knowledgeProcessing toolsEvaluation setHealth recordsData sourcesEvent associationsIndexingDrug-effect relationshipsRepositoryLarge volumesADR associationsReasoning pathwaysLinking Biochemical Pathways and Networks to Adverse Drug Reactions
Zheng H, Wang H, Xu H, Wu Y, Zhao Z, Azuaje F. Linking Biochemical Pathways and Networks to Adverse Drug Reactions. IEEE Transactions On NanoBioscience 2014, 13: 131-137. PMID: 24893363, DOI: 10.1109/tnb.2014.2319158.Peer-Reviewed Original ResearchDetermining molecular predictors of adverse drug reactions with causality analysis based on structure learning
Liu M, Cai R, Hu Y, Matheny M, Sun J, Hu J, Xu H. Determining molecular predictors of adverse drug reactions with causality analysis based on structure learning. Journal Of The American Medical Informatics Association 2014, 21: 245-251. PMID: 24334612, PMCID: PMC3932464, DOI: 10.1136/amiajnl-2013-002051.Peer-Reviewed Original ResearchAlgorithmsArtificial IntelligenceBayes TheoremCausalityDatabases, GeneticDrug-Related Side Effects and Adverse ReactionsHumansLogistic ModelsMolecular StructureStatistics, NonparametricSupport Vector Machine
2012
Comparative analysis of pharmacovigilance methods in the detection of adverse drug reactions using electronic medical records
Liu M, Hinz E, Matheny M, Denny J, Schildcrout J, Miller R, Xu H. Comparative analysis of pharmacovigilance methods in the detection of adverse drug reactions using electronic medical records. Journal Of The American Medical Informatics Association 2012, 20: 420-426. PMID: 23161894, PMCID: PMC3628053, DOI: 10.1136/amiajnl-2012-001119.Peer-Reviewed Original ResearchMeSH KeywordsAlgorithmsDrug-Related Side Effects and Adverse ReactionsElectronic Health RecordsHumansPharmacovigilanceProduct Surveillance, PostmarketingConceptsAdverse drug reactionsElectronic medical recordsProportional reporting ratioVanderbilt University Medical CenterSpontaneous reporting systemDrug-event pairsDrug reactionsMedical recordsMedication ordersAbnormal laboratory resultsDrug-exposed groupNew adverse drug reactionsUniversity Medical CenterSpecific drug administrationReference standardLaboratory resultsUnexposed groupGamma Poisson ShrinkerMedical CenterPatient harmDrug AdministrationPharmacovigilance measuresBayesian confidence propagation neural networkEarly detectionReporting ratioOptimizing Drug Outcomes Through Pharmacogenetics: A Case for Preemptive Genotyping
Schildcrout J, Denny J, Bowton E, Gregg W, Pulley J, Basford M, Cowan J, Xu H, Ramirez A, Crawford D, Ritchie M, Peterson J, Masys D, Wilke R, Roden D. Optimizing Drug Outcomes Through Pharmacogenetics: A Case for Preemptive Genotyping. Clinical Pharmacology & Therapeutics 2012, 92: 235-242. PMID: 22739144, PMCID: PMC3785311, DOI: 10.1038/clpt.2012.66.Peer-Reviewed Original ResearchMeSH KeywordsAdultAgedDrug-Related Side Effects and Adverse ReactionsFemaleGenotypeHumansMaleMiddle AgedPatient SafetyPharmacogeneticsPolymorphism, GeneticConceptsVanderbilt University Medical CenterAdverse eventsPreemptive genotypingPotential adverse eventsUniversity Medical CenterHome patientsPharmacogenetic associationsMedical CenterVariant allelesMedicationsDrug outcomesPatient safetyDrug decision makingRelevant genetic variantsRoutine integrationTarget drugsGenetic variantsOutcomesFrequency of opportunitiesGenotypingSafetyPrescribingPatientsCohortPharmacogeneticsLarge-scale prediction of adverse drug reactions using chemical, biological, and phenotypic properties of drugs
Liu M, Wu Y, Chen Y, Sun J, Zhao Z, Chen X, Matheny M, Xu H. Large-scale prediction of adverse drug reactions using chemical, biological, and phenotypic properties of drugs. Journal Of The American Medical Informatics Association 2012, 19: e28-e35. PMID: 22718037, PMCID: PMC3392844, DOI: 10.1136/amiajnl-2011-000699.Peer-Reviewed Original ResearchMeSH KeywordsAlgorithmsArea Under CurveArtificial IntelligenceBayes TheoremDrug-Related Side Effects and Adverse ReactionsHumansLogistic ModelsPharmaceutical PreparationsROC CurveSupport Vector MachineConceptsAdverse drug reactionsPost-marketing phaseDrug reactionsSevere adverse drug reactionsImportant adverse drug reactionsWithdrawal of rofecoxibPotential adverse drug reactionsPost-marketing surveillanceADR predictionPatient morbidityClinical trialsMajor causeLarge-scale studiesDrugsMolecular pathwaysDrug developmentPhenotypic featuresSignificant improvementPhenotypic characteristicsEarly stages