2024
A machine learning framework to adjust for learning effects in medical device safety evaluation
Koola J, Ramesh K, Mao J, Ahn M, Davis S, Govindarajulu U, Perkins A, Westerman D, Ssemaganda H, Speroff T, Ohno-Machado L, Ramsay C, Sedrakyan A, Resnic F, Matheny M. A machine learning framework to adjust for learning effects in medical device safety evaluation. Journal Of The American Medical Informatics Association 2024, ocae273. PMID: 39471493, DOI: 10.1093/jamia/ocae273.Peer-Reviewed Original ResearchMachine learning frameworkSynthetic datasetsLearning frameworkMachine learningCapacity of MLLearning effectFeature correlationDepartment of Veterans AffairsSynthetic dataData generationAbsence of learning effectsTraditional statistical methodsML methodsSuperior performanceDatasetSafety signal detectionSignal detectionDevice signalsVeterans AffairsTime-varying covariatesLearningMachinePhysician experienceLimitations of traditional statistical methodsMedical device post-market surveillance
2023
Simulating complex patient populations with hierarchical learning effects to support methods development for post-market surveillance
Davis S, Ssemaganda H, Koola J, Mao J, Westerman D, Speroff T, Govindarajulu U, Ramsay C, Sedrakyan A, Ohno-Machado L, Resnic F, Matheny M. Simulating complex patient populations with hierarchical learning effects to support methods development for post-market surveillance. BMC Medical Research Methodology 2023, 23: 89. PMID: 37041457, PMCID: PMC10088292, DOI: 10.1186/s12874-023-01913-9.Peer-Reviewed Original ResearchConceptsSynthetic datasetsData characteristicsFeature distributionGround truthMIMIC-III dataReal-world dataData generation processComplex simulation studiesData relationshipsUser definitionSmall datasetsSimulation requirementsCorrelated featuresWorld dataCustomizable optionsReal-world complexitySynthetic patientsNew algorithmDatasetGeneration processLearningAlgorithmData simulation techniquesLearning effectGeneralizable frameworkChapter 7 Data-driven approaches to generating knowledge: Machine learning, artificial intelligence, and predictive modeling
Matheny M, Ohno-Machado L, Davis S, Nemati S. Chapter 7 Data-driven approaches to generating knowledge: Machine learning, artificial intelligence, and predictive modeling. 2023, 217-255. DOI: 10.1016/b978-0-323-91200-6.00031-0.Peer-Reviewed Original Research
2017
Information retrieval for biomedical datasets: the 2016 bioCADDIE dataset retrieval challenge
Roberts K, Gururaj A, Chen X, Pournejati S, Hersh W, Demner-Fushman D, Ohno-Machado L, Cohen T, Xu H. Information retrieval for biomedical datasets: the 2016 bioCADDIE dataset retrieval challenge. Database 2017, 2017: bax068. DOI: 10.1093/database/bax068.Peer-Reviewed Original ResearchBiomedical datasetsRetrieval challengesInformation retrieval techniquesAdvanced query processingBiomedical data repositoriesAdvanced retrieval methodsQuery processingInformation retrievalTest queriesRetrieval systemRank frameworkRetrieval approachRetrieval techniquesData repositoryRetrieval methodTop precisionDatasetQueriesRepositoryChallengesRetrievalTaskLearningSystemCorpus
2016
Secure Multi-pArty Computation Grid LOgistic REgression (SMAC-GLORE)
Shi H, Jiang C, Dai W, Jiang X, Tang Y, Ohno-Machado L, Wang S. Secure Multi-pArty Computation Grid LOgistic REgression (SMAC-GLORE). BMC Medical Informatics And Decision Making 2016, 16: 89. PMID: 27454168, PMCID: PMC4959358, DOI: 10.1186/s12911-016-0316-1.Peer-Reviewed Original ResearchConceptsData sharingPatient privacySecure multi-party computationModel learning phaseMulti-party computationBiomedical data sharingInformation leakageModel learningIntermediary informationInformation exchangeSecondary usePrivacyBig concernPractical solutionLogistic regression frameworkExperimental resultsSharingRegression frameworkFrameworkMultiple institutionsPrevious workComputationLearningBiomedical researchInformation
2013
Detecting inappropriate access to electronic health records using collaborative filtering
Menon A, Jiang X, Kim J, Vaidya J, Ohno-Machado L. Detecting inappropriate access to electronic health records using collaborative filtering. Machine Learning 2013, 95: 87-101. PMID: 24683293, PMCID: PMC3967851, DOI: 10.1007/s10994-013-5376-1.Peer-Reviewed Original ResearchElectronic health recordsCollaborative filteringInappropriate accessHealth recordsSuspicious accessPrivacy policiesAccess patternsMachine learningManual auditingSecurity expertsLatent featuresAccess dataRecord accessHistorical dataSecurityFilteringUnrestricted accessFuture violationsAccessAudit processSVMUsersDatasetLearningAuditingEXpectation Propagation LOgistic REgRession (EXPLORER): Distributed privacy-preserving online model learning
Wang S, Jiang X, Wu Y, Cui L, Cheng S, Ohno-Machado L. EXpectation Propagation LOgistic REgRession (EXPLORER): Distributed privacy-preserving online model learning. Journal Of Biomedical Informatics 2013, 46: 480-496. PMID: 23562651, PMCID: PMC3676314, DOI: 10.1016/j.jbi.2013.03.008.Peer-Reviewed Original ResearchConceptsHigh-level guaranteesOnline model learningSensitive informationModel learningEntire dataOnline learningAbsence of participantsMore flexibilitySame performanceExperimental resultsLearningCommunicationServerInformationGuaranteesModel updatingPosterior distributionServicesClientsUpdatingFrameworkFlexibilityModelPerformance
2011
Smooth isotonic regression: a new method to calibrate predictive models.
Jiang X, Osl M, Kim J, Ohno-Machado L. Smooth isotonic regression: a new method to calibrate predictive models. AMIA Joint Summits On Translational Science Proceedings 2011, 2011: 16-20. PMID: 22211175, PMCID: PMC3248752.Peer-Reviewed Original ResearchBiomedical data setsSupervised learning modelGood generalization abilityMachine learningPredictive modelGeneralization abilityProbabilistic outputsLearning modelData setsIsotonic regression methodNovel methodNon-parametric approachReliability diagramsProbability estimatesRegression methodNew methodLearning