2012
Grid Binary LOgistic REgression (GLORE): building shared models without sharing data
Wu Y, Jiang X, Kim J, Ohno-Machado L. Grid Binary LOgistic REgression (GLORE): building shared models without sharing data. Journal Of The American Medical Informatics Association 2012, 19: 758-764. PMID: 22511014, PMCID: PMC3422844, DOI: 10.1136/amiajnl-2012-000862.Peer-Reviewed Original ResearchConceptsIntegrity of communicationCentralized data sourcesTraditional LR modelCentral repositoryComputational costData sourcesData setsSame formatPatient dataComputationGenomic dataRare patternRelevant dataLR modelPrediction valueSetRepositoryPartial elementsFormatClassificationCommunicationModelDataPatient setPerform
2011
Using statistical and machine learning to help institutions detect suspicious access to electronic health records
Boxwala A, Kim J, Grillo J, Ohno-Machado L. Using statistical and machine learning to help institutions detect suspicious access to electronic health records. Journal Of The American Medical Informatics Association 2011, 18: 498-505. PMID: 21672912, PMCID: PMC3128412, DOI: 10.1136/amiajnl-2011-000217.Peer-Reviewed Original ResearchConceptsSuspicious accessMachine-learning methodsPrivacy officersMachine learning techniquesVector machine modelAccess logsElectronic health recordsBaseline methodsAccess dataCross-validation setGold standard setSVM modelWhole data setMachine modelBaseline modelOrganizational dataHealth recordsData setsSVMSmooth 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