2021
Predictive Analytics for Glaucoma Using Data From the All of Us Research Program
Baxter S, Saseendrakumar B, Paul P, Kim J, Bonomi L, Kuo T, Loperena R, Ratsimbazafy F, Boerwinkle E, Cicek M, Clark C, Cohn E, Gebo K, Mayo K, Mockrin S, Schully S, Ramirez A, Ohno-Machado L, Investigators A. Predictive Analytics for Glaucoma Using Data From the All of Us Research Program. American Journal Of Ophthalmology 2021, 227: 74-86. PMID: 33497675, PMCID: PMC8184631, DOI: 10.1016/j.ajo.2021.01.008.Peer-Reviewed Original ResearchConceptsGlaucoma surgeryPrimary open-angle glaucomaOphthalmic researchSingle-center cohortElectronic health record dataMultivariable logistic regressionSingle-center dataOpen-angle glaucomaHealth record dataMean ageClaims dataUs Research ProgramLogistic regressionSurgeryRecord dataOphthalmic imagingCharacteristic curveExternal validationGlaucomaCohortAUCSingle-center model
2020
A tutorial on calibration measurements and calibration models for clinical prediction models
Huang Y, Li W, Macheret F, Gabriel R, Ohno-Machado L. A tutorial on calibration measurements and calibration models for clinical prediction models. Journal Of The American Medical Informatics Association 2020, 27: 621-633. PMID: 32106284, PMCID: PMC7075534, DOI: 10.1093/jamia/ocz228.Peer-Reviewed Reviews, Practice Guidelines, Standards, and Consensus Statements
2019
Machine Learning-Based Predictive Modeling of Surgical Intervention in Glaucoma Using Systemic Data From Electronic Health Records
Baxter S, Marks C, Kuo T, Ohno-Machado L, Weinreb R. Machine Learning-Based Predictive Modeling of Surgical Intervention in Glaucoma Using Systemic Data From Electronic Health Records. American Journal Of Ophthalmology 2019, 208: 30-40. PMID: 31323204, PMCID: PMC6888922, DOI: 10.1016/j.ajo.2019.07.005.Peer-Reviewed Original ResearchConceptsPrimary open-angle glaucomaElectronic health recordsMultivariable logistic regressionSurgical interventionGlaucoma surgeryPOAG patientsSystemic dataHigher mean systolic blood pressureMean systolic blood pressureNon-opioid analgesic medicationsLogistic regressionCertain medication classesEye-specific dataHealth recordsRisk of progressionSystolic blood pressureOpen-angle glaucomaSingle academic institutionAnti-hyperlipidemic medicationsAnalgesic medicationMedication classesProgressive diseaseBlood pressureCalcium blockersOphthalmic medications
2017
A Predictive Model for Extended Postanesthesia Care Unit Length of Stay in Outpatient Surgeries
Gabriel R, Waterman R, Kim J, Ohno-Machado L. A Predictive Model for Extended Postanesthesia Care Unit Length of Stay in Outpatient Surgeries. Anesthesia & Analgesia 2017, 124: 1529-1536. PMID: 28079580, DOI: 10.1213/ane.0000000000001827.Peer-Reviewed Original ResearchMeSH KeywordsAdolescentAdultAge FactorsAgedAged, 80 and overAmbulatory Surgical ProceduresAnesthesiaChildChild, PreschoolCritical CareFemaleForecastingHumansHypertensionInfantInfant, NewbornIntensive Care UnitsLength of StayLogistic ModelsMaleMiddle AgedModels, StatisticalObesity, MorbidPostoperative CareRisk FactorsROC CurveYoung AdultConceptsPACU lengthPostanesthesia care unit lengthPrimary anesthesia typePostanesthesia care unitHosmer-Lemeshow testLogistic regression modelsAnesthesia typeMorbid obesityCare unitHL testOutpatient surgeryOutpatient procedureSingle institutionHigher oddsNonsignificant P valuesStayPatientsSurgical specialtiesROC curveGood calibrationCharacteristic curveExcellent discriminationAUC valuesP-valueBackward elimination
2015
VERTIcal Grid lOgistic regression (VERTIGO)
Li Y, Jiang X, Wang S, Xiong H, Ohno-Machado L. VERTIcal Grid lOgistic regression (VERTIGO). Journal Of The American Medical Informatics Association 2015, 23: 570-579. PMID: 26554428, PMCID: PMC4901373, DOI: 10.1093/jamia/ocv146.Peer-Reviewed Original ResearchConceptsFederated data analysisReal-world medical classification problemsMedical classification problemsLogistic regression algorithmAccurate global modelData setsReal data setsClassification problemExchange of informationLR problemTime complexityComputational complexityExpensive operationRegression algorithmComputational costData analysisAlgorithmDual optimizationTechnical challengesLarge amountComplexityPatient recordsLR modelNovel techniqueHessian matrix
2012
Doubly Optimized Calibrated Support Vector Machine (DOC-SVM): An Algorithm for Joint Optimization of Discrimination and Calibration
Jiang X, Menon A, Wang S, Kim J, Ohno-Machado L. Doubly Optimized Calibrated Support Vector Machine (DOC-SVM): An Algorithm for Joint Optimization of Discrimination and Calibration. PLOS ONE 2012, 7: e48823. PMID: 23139819, PMCID: PMC3490990, DOI: 10.1371/journal.pone.0048823.Peer-Reviewed Original ResearchAn improved model for predicting postoperative nausea and vomiting in ambulatory surgery patients using physician-modifiable risk factors
Sarin P, Urman R, Ohno-Machado L. An improved model for predicting postoperative nausea and vomiting in ambulatory surgery patients using physician-modifiable risk factors. Journal Of The American Medical Informatics Association 2012, 19: 995-1002. PMID: 22582204, PMCID: PMC3534465, DOI: 10.1136/amiajnl-2012-000872.Peer-Reviewed Original ResearchConceptsAmbulatory surgery dataExperimental modelNon-modifiable patient characteristicsApfel risk scoreAmbulatory surgery patientsGood calibrationLogistic regression modelsAmbulatory surgery casesPONV prophylaxisPostoperative nauseaFrequent complicationPatient characteristicsSurgery patientsAnesthetic techniqueAmbulatory surgeryPatient riskRisk factorsSurgery casesAnaesthetic practiceRisk scoreAcademic centersSurgery dataPractice improvementNauseaVomitingGrid 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
Improving predictions in imbalanced data using Pairwise Expanded Logistic Regression.
Jiang X, El-Kareh R, Ohno-Machado L. Improving predictions in imbalanced data using Pairwise Expanded Logistic Regression. AMIA Annual Symposium Proceedings 2011, 2011: 625-34. PMID: 22195118, PMCID: PMC3243279.Peer-Reviewed Original Research
2010
Positive predictive value of CT urography in the evaluation of upper tract urothelial cancer.
Sadow C, Wheeler S, Kim J, Ohno-Machado L, Silverman S. Positive predictive value of CT urography in the evaluation of upper tract urothelial cancer. American Journal Of Roentgenology 2010, 195: w337-43. PMID: 20966298, DOI: 10.2214/ajr.09.4147.Peer-Reviewed Original ResearchConceptsUpper tract urothelial cancerPositive predictive valueUrothelial cancerUrine cytologyCT urographyPredictive valueUrographic examinationUrothelial thickeningExact testUpper tract urothelial malignanciesMultivariate logistic regression analysisPositive urine cytologyRecords of patientsSignificant univariate predictorsLogistic regression analysisFisher's exact testT-testStudent's t-testEffect of ageFollowup imagingRetrospective reviewPathologic examinationUrothelial malignancyUnivariate predictorsMimic cancer
2005
The use of receiver operating characteristic curves in biomedical informatics
Lasko T, Bhagwat J, Zou K, Ohno-Machado L. The use of receiver operating characteristic curves in biomedical informatics. Journal Of Biomedical Informatics 2005, 38: 404-415. PMID: 16198999, DOI: 10.1016/j.jbi.2005.02.008.Peer-Reviewed Reviews, Practice Guidelines, Standards, and Consensus StatementsDiscrimination and calibration of mortality risk prediction models in interventional cardiology
Matheny M, Ohno-Machado L, Resnic F. Discrimination and calibration of mortality risk prediction models in interventional cardiology. Journal Of Biomedical Informatics 2005, 38: 367-375. PMID: 16198996, DOI: 10.1016/j.jbi.2005.02.007.Peer-Reviewed Original ResearchMeSH KeywordsAngioplasty, Balloon, CoronaryCalibrationCardiologyComorbidityDecision Support Systems, ClinicalDiagnosis, Computer-AssistedDiscriminant AnalysisExpert SystemsHumansIncidenceOutcome Assessment, Health CarePostoperative ComplicationsPrognosisRetrospective StudiesRisk AssessmentRisk FactorsROC CurveSurvival AnalysisSurvival RateUnited StatesConceptsLocal risk modelAcute myocardial infarctionHosmer-Lemeshow goodnessRisk prediction modelRisk factorsCardiology-National Cardiovascular Data RegistryConsecutive percutaneous coronary interventionsMortality risk prediction modelPercutaneous coronary interventionMultivariate risk factorsCertain risk factorsROC curveAccurate risk predictionIndividual casesGood discriminationCardiogenic shockHospital mortalityCoronary interventionUnstable anginaArtery interventionPatient populationMyocardial infarctionRisk modelElective proceduresWomen's HospitalA global goodness-of-fit test for receiver operating characteristic curve analysis via the bootstrap method
Zou K, Resnic F, Talos I, Goldberg-Zimring D, Bhagwat J, Haker S, Kikinis R, Jolesz F, Ohno-Machado L. A global goodness-of-fit test for receiver operating characteristic curve analysis via the bootstrap method. Journal Of Biomedical Informatics 2005, 38: 395-403. PMID: 16198998, DOI: 10.1016/j.jbi.2005.02.004.Peer-Reviewed Original ResearchAdolescentAdultAlgorithmsAngioplasty, Balloon, CoronaryBrain NeoplasmsCalibrationData Interpretation, StatisticalDecision Support Systems, ClinicalDiagnosis, Computer-AssistedDiscriminant AnalysisExpert SystemsFemaleHumansIncidenceMaleMiddle AgedOutcome Assessment, Health CarePrognosisRisk AssessmentRisk FactorsROC CurveSurvival AnalysisSurvival RateUnited StatesCombining Classifiers Using Their Receiver Operating Characteristics and Maximum Likelihood Estimation
Haker S, Wells W, Warfield S, Talos I, Bhagwat J, Goldberg-Zimring D, Mian A, Ohno-Machado L, Zou K. Combining Classifiers Using Their Receiver Operating Characteristics and Maximum Likelihood Estimation. Lecture Notes In Computer Science 2005, 8: 506-514. PMID: 16685884, PMCID: PMC3681096, DOI: 10.1007/11566465_63.Peer-Reviewed Original Research
2004
Diagnostic accuracy of chest X-rays acquired using a digital camera for low-cost teleradiology
Szot A, Jacobson F, Munn S, Jazayeri D, Nardell E, Harrison D, Drosten R, Ohno-Machado L, Smeaton L, Fraser H. Diagnostic accuracy of chest X-rays acquired using a digital camera for low-cost teleradiology. International Journal Of Medical Informatics 2004, 73: 65-73. PMID: 15036080, DOI: 10.1016/j.ijmedinf.2003.10.002.Peer-Reviewed Original Research
2001
Simplified 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 curveEffects of data anonymization by cell suppression on descriptive statistics and predictive modeling performance.
Ohno-Machado L, Vinterbo S, Dreiseitl S. Effects of data anonymization by cell suppression on descriptive statistics and predictive modeling performance. AMIA Annual Symposium Proceedings 2001, 503-7. PMID: 11825239, PMCID: PMC2243599.Peer-Reviewed Original Research
2000
Comparing Three-class Diagnostic Tests by Three-way ROC Analysis
Dreiseitl S, Ohno-Machado L, Binder M. Comparing Three-class Diagnostic Tests by Three-way ROC Analysis. Medical Decision Making 2000, 20: 323-331. PMID: 10929855, DOI: 10.1177/0272989x0002000309.Peer-Reviewed Original ResearchBuilding knowledge in a complex preterm birth problem domain.
Goodwin L, Maher S, Ohno-Machado L, Iannacchione M, Crockett P, Dreiseitl S, Vinterbo S, Hammond W. Building knowledge in a complex preterm birth problem domain. AMIA Annual Symposium Proceedings 2000, 305-9. PMID: 11079894, PMCID: PMC2243761.Peer-Reviewed Original Research
1999
A 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 ResearchConceptsGenetic algorithmNumber of variablesVariable selection methodsGenetic algorithm variable selection methodSelection methodData setsAlgorithmVariable selectionBest variable combinationModel's discriminatory performanceModel simplicityActual useValidation setExternal validation setSetParticular selectionModel