2008
Validation of an Automated Safety Surveillance System with Prospective, Randomized Trial Data
Matheny M, Morrow D, Ohno-Machado L, Cannon C, Sabatine M, Resnic F. Validation of an Automated Safety Surveillance System with Prospective, Randomized Trial Data. Medical Decision Making 2008, 29: 247-256. PMID: 19015285, PMCID: PMC2743924, DOI: 10.1177/0272989x08327110.Peer-Reviewed Original ResearchMeSH KeywordsBayes TheoremData Interpretation, StatisticalDecision Support TechniquesFibrinolytic AgentsHumansIntracranial HemorrhagesMulticenter Studies as TopicMyocardial InfarctionRandomized Controlled Trials as TopicReproducibility of ResultsRetrospective StudiesSafety ManagementSentinel SurveillanceConceptsIntervention armMortality rateEvent ratesTrial BTrial AMajor bleeding ratesOutcomes Surveillance SystemIntracranial hemorrhage rateCumulative event rateRandomized trial dataEvent-rate analysisSafety surveillance systemSurveillance systemAdverse eventsMulticenter trialHemorrhage rateMonth 14Bleeding rateControl armClinical trialsTrial B.Trial dataTrialsObserved event ratesMonths
2003
No-reflow is an independent predictor of death and myocardial infarction after percutaneous coronary intervention
Resnic F, Wainstein M, Lee M, Behrendt D, Wainstein R, Ohno-Machado L, Kirshenbaum J, Rogers C, Popma J, Piana R. No-reflow is an independent predictor of death and myocardial infarction after percutaneous coronary intervention. American Heart Journal 2003, 145: 42-46. PMID: 12514653, DOI: 10.1067/mhj.2003.36.Peer-Reviewed Original ResearchConceptsPercutaneous coronary interventionPostprocedural myocardial infarctionStrong independent predictorMyocardial infarctionIndependent predictorsSodium nitroprussideInhospital outcomesCoronary interventionClinical outcomesSaphenous vein graft interventionIntracoronary vasodilator therapyVein graft interventionAdministration of verapamilAcute myocardial infarctionRate of deathInhospital mortalityVasodilator therapyCardiogenic shockBaseline demographicsGraft interventionUnstable anginaAdverse eventsConsecutive patientsIntracoronary verapamilInfarction
2001
Vascular closure devices and the risk of vascular complications after percutaneous coronary intervention in patients receiving glycoprotein IIb-IIIa inhibitors
Resnic F, Blake G, Ohno-Machado L, Selwyn A, Popma J, Rogers C. Vascular closure devices and the risk of vascular complications after percutaneous coronary intervention in patients receiving glycoprotein IIb-IIIa inhibitors. The American Journal Of Cardiology 2001, 88: 493-496. PMID: 11524056, DOI: 10.1016/s0002-9149(01)01725-8.Peer-Reviewed Original ResearchMeSH KeywordsAge DistributionAgedAnalysis of VarianceAneurysm, FalseAngioplasty, Balloon, CoronaryAntibodies, MonoclonalAntibodies, Monoclonal, HumanizedArteriovenous FistulaChi-Square DistributionCoronary DiseaseCoronary Vessel AnomaliesCoronary VesselsEquipment SafetyFemaleHematomaHumansIncidenceMaleMiddle AgedMultivariate AnalysisMyocardial InfarctionProbabilityRetrospective StudiesRisk AssessmentRisk FactorsSex DistributionConceptsPercutaneous coronary interventionVascular closure deviceGlycoprotein IIb-IIIa antagonistsVascular complication ratesVascular complicationsClosure deviceCoronary interventionComplication rateLower vascular complication ratesOverall vascular complication rateGlycoprotein IIb-IIIa inhibitorsIIb-IIIa inhibitorsSubgroup of patientsLength of stayHospital stayConsecutive patientsLarge hematomaSurgical repairArteriovenous fistulaPatient populationUnivariate analysisRetrospective analysisComplicationsPatient comfortPatientsSimplified risk score models accurately predict the risk of major in-hospital complications following percutaneous coronary intervention
Resnic F, Ohno-Machado L, Selwyn A, Simon D, Popma J. Simplified risk score models accurately predict the risk of major in-hospital complications following percutaneous coronary intervention. The American Journal Of Cardiology 2001, 88: 5-9. PMID: 11423050, DOI: 10.1016/s0002-9149(01)01576-4.Peer-Reviewed Original ResearchMeSH KeywordsAngioplasty, Balloon, CoronaryCardiopulmonary BypassCoronary DiseaseFemaleHospital MortalityHumansLogistic ModelsMaleMiddle AgedMyocardial InfarctionNeural Networks, ComputerPostoperative ComplicationsPredictive Value of TestsPrognosisProspective StudiesRisk AssessmentRisk FactorsROC CurveConceptsPercutaneous coronary interventionRisk score modelHospital complicationsCoronary interventionScore modelGlycoprotein IIb/IIIa antagonistsIIb/IIIa antagonistsMultiple logistic regression modelBedside risk stratificationCombined end pointUse of stentsMultiple logistic modelLogistic regression modelsBypass surgeryRisk stratificationSingle centerDecreased riskMyocardial infarctionRisk factorsComplicationsInterventional proceduresEnd pointLogistic regressionLogistic modelROC curveUsing patient-reportable clinical history factors to predict myocardial infarction
Wang S, Ohno-Machado L, Fraser H, Kennedy R. Using patient-reportable clinical history factors to predict myocardial infarction. Computers In Biology And Medicine 2001, 31: 1-13. PMID: 11058690, DOI: 10.1016/s0010-4825(00)00022-6.Peer-Reviewed Original ResearchEffects of Case Removal in Prognostic Models
Ohno-Machado L, Vinterbo S. Effects of Case Removal in Prognostic Models. Methods Of Information In Medicine 2001, 40: 32-38. PMID: 11310157, DOI: 10.1055/s-0038-1634461.Peer-Reviewed Original Research
2000
Major complications after angioplasty in patients with chronic renal failure: a comparison of predictive models.
Lacson R, Ohno-Machado L. Major complications after angioplasty in patients with chronic renal failure: a comparison of predictive models. AMIA Annual Symposium Proceedings 2000, 457-61. PMID: 11079925, PMCID: PMC2243840.Peer-Reviewed Original ResearchConceptsPercutaneous transluminal coronary angioplastyEnd-stage renal diseaseChronic renal failureMajor complicationsRenal failureCongestive heart failurePatient risk factorsTransluminal coronary angioplastyLogistic regression modelsCoronary angioplastyHeart failureRenal diseasePoor outcomeMyocardial infarctionRisk factorsPrior historyPresence of shockComplicationsLogistic regressionPatientsDiscriminatory abilityDemographic characteristicsAngioplastyRegression modelsStandard logistic regression modelDevelopment and evaluation of models to predict death and myocardial infarction following coronary angioplasty and stenting.
Resnic F, Popma J, Ohno-Machado L. Development and evaluation of models to predict death and myocardial infarction following coronary angioplasty and stenting. AMIA Annual Symposium Proceedings 2000, 690-3. PMID: 11079972, PMCID: PMC2243827.Peer-Reviewed Original ResearchConceptsPercutaneous coronary interventionMyocardial infarctionPost-procedural myocardial infarctionMajor acute complicationsRisk-scoring systemRisk of deathMultivariate logistic regressionRisk score modelRisk-scoring modelLogistic regression modelsAcute complicationsCoronary angioplastyCoronary interventionClinical practiceInfarctionScoring systemInterventional cardiologyLogistic regressionRisk modelClinical implementationRisk deathDeathScore modelReasonable discriminationRegression models
1999
Evaluating variable selection methods for diagnosis of myocardial infarction.
Dreiseitl S, Ohno-Machado L, Vinterbo S. Evaluating variable selection methods for diagnosis of myocardial infarction. AMIA Annual Symposium Proceedings 1999, 246-50. PMID: 10566358, PMCID: PMC2232647.Peer-Reviewed Original ResearchConceptsMachine-learning techniquesBayesian neural networksNeural networkMultilayer perceptronRough setsVariable selection methodsSelection methodInput variablesVariable selectionInfarction dataBackpropagationPerceptronMyocardial infarction dataDifferent subsetsAlgorithmNetworkMethodSetDifferent methodsA genetic algorithm to select variables in logistic regression: example in the domain of myocardial infarction.
Vinterbo S, Ohno-Machado L. A genetic algorithm to select variables in logistic regression: example in the domain of myocardial infarction. AMIA Annual Symposium Proceedings 1999, 984-8. PMID: 10566508, PMCID: PMC2232877.Peer-Reviewed Original ResearchMeSH KeywordsAlgorithmsChest PainEvaluation Studies as TopicGeneticsHumansLogistic ModelsModels, BiologicalMyocardial InfarctionROC CurveConceptsGenetic algorithmNumber of variablesVariable selection methodsGenetic algorithm variable selection methodSelection methodData setsAlgorithmVariable selectionBest variable combinationModel's discriminatory performanceModel simplicityActual useValidation setExternal validation setSetParticular selectionModel
1998
Improving machine learning performance by removing redundant cases in medical data sets.
Ohno-Machado L, Fraser H, Ohrn A. Improving machine learning performance by removing redundant cases in medical data sets. AMIA Annual Symposium Proceedings 1998, 523-7. PMID: 9929274, PMCID: PMC2232167.Peer-Reviewed Original ResearchMeSH KeywordsArea Under CurveArtificial IntelligenceDatabases as TopicHumansMyocardial InfarctionNeural Networks, ComputerRandom AllocationROC Curve