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 surveillanceSecure Federated Learning Integrated Statistical Modeling for Healthcare Data
Jiang X, Kim J, Kuo T, Ohno-Machado L. Secure Federated Learning Integrated Statistical Modeling for Healthcare Data. 2024, 313-324. DOI: 10.1201/9781003185284-24.Peer-Reviewed Original ResearchA primer for quantum computing and its applications to healthcare and biomedical research
Durant T, Knight E, Nelson B, Dudgeon S, Lee S, Walliman D, Young H, Ohno-Machado L, Schulz W. A primer for quantum computing and its applications to healthcare and biomedical research. Journal Of The American Medical Informatics Association 2024, 31: 1774-1784. PMID: 38934288, PMCID: PMC11258415, DOI: 10.1093/jamia/ocae149.Peer-Reviewed Reviews, Practice Guidelines, Standards, and Consensus StatementsBiomedical blockchain with practical implementations and quantitative evaluations: a systematic review
Lacson R, Yu Y, Kuo T, Ohno-Machado L. Biomedical blockchain with practical implementations and quantitative evaluations: a systematic review. Journal Of The American Medical Informatics Association 2024, 31: 1423-1435. PMID: 38726710, PMCID: PMC11105130, DOI: 10.1093/jamia/ocae084.Peer-Reviewed Original ResearchConceptsElectronic health recordsSystematic reviewData sharingMedical data sharingSpeed metricsPreferred Reporting ItemsCertificate storageDecentralized InternetNetwork permissionsBlockchain platformBlockchain applicationsEvaluation metricsBiomedical domainBlockchainBiomedical data managementHealth recordsData managementData storageReporting ItemsHealth sectorQuantitative metricsMedical facilitiesMetricsTrial managementClinical trial management
2023
JAMIA at 30: looking back and forward
Stead W, Miller R, Ohno-Machado L, Bakken S. JAMIA at 30: looking back and forward. Journal Of The American Medical Informatics Association 2023, 31: 1-9. PMID: 38134400, PMCID: PMC10746314, DOI: 10.1093/jamia/ocad215.Peer-Reviewed Original ResearchGuiding Principles to Address the Impact of Algorithm Bias on Racial and Ethnic Disparities in Health and Health Care
Chin M, Afsar-Manesh N, Bierman A, Chang C, Colón-Rodríguez C, Dullabh P, Duran D, Fair M, Hernandez-Boussard T, Hightower M, Jain A, Jordan W, Konya S, Moore R, Moore T, Rodriguez R, Shaheen G, Snyder L, Srinivasan M, Umscheid C, Ohno-Machado L. Guiding Principles to Address the Impact of Algorithm Bias on Racial and Ethnic Disparities in Health and Health Care. JAMA Network Open 2023, 6: e2345050. PMID: 38100101, PMCID: PMC11181958, DOI: 10.1001/jamanetworkopen.2023.45050.Peer-Reviewed Original ResearchSevere aortic stenosis detection by deep learning applied to echocardiography
Holste G, Oikonomou E, Mortazavi B, Coppi A, Faridi K, Miller E, Forrest J, McNamara R, Ohno-Machado L, Yuan N, Gupta A, Ouyang D, Krumholz H, Wang Z, Khera R. Severe aortic stenosis detection by deep learning applied to echocardiography. European Heart Journal 2023, 44: 4592-4604. PMID: 37611002, PMCID: PMC11004929, DOI: 10.1093/eurheartj/ehad456.Peer-Reviewed Original ResearchExamining sociodemographic correlates of opioid use, misuse, and use disorders in the All of Us Research Program.
Yeh H, Peltz-Rauchman C, Johnson C, Pawloski P, Chesla D, Waring S, Stevens A, Epstein M, Joseph C, Miller-Matero L, Gui H, Tang A, Boerwinkle E, Cicek M, Clark C, Cohn E, Gebo K, Loperena R, Mayo K, Mockrin S, Ohno-Machado L, Schully S, Ramirez A, Qian J, Ahmedani B. Examining sociodemographic correlates of opioid use, misuse, and use disorders in the All of Us Research Program. PLOS ONE 2023, 18: e0290416. PMID: 37594966, PMCID: PMC10437856, DOI: 10.1371/journal.pone.0290416.Peer-Reviewed Original ResearchConceptsOpioid use disorderOpioid usePrescription opioidsElectronic health recordsReduced oddsDiagnosis of OUDSociodemographic characteristicsPrevalence of OUDNonmedical useLifetime opioid useEHR dataNon-Hispanic white participantsImportant clinical informationNon-medical useLifetime prevalenceStreet opioidsHigher oddsOpioidsClinical informationUse disordersUs Research ProgramSociodemographic correlatesLogistic regressionPrevalenceHealth recordsFamily and personal history of cancer in the All of Us research program for precision medicine
Bruce L, Paul P, Kim K, Kim J, Keegan T, Hiatt R, Ohno-Machado L, Investigators O. Family and personal history of cancer in the All of Us research program for precision medicine. PLOS ONE 2023, 18: e0288496. PMID: 37459328, PMCID: PMC10351738, DOI: 10.1371/journal.pone.0288496.Peer-Reviewed Original ResearchPatient and researcher stakeholder preferences for use of electronic health record data: a qualitative study to guide the design and development of a platform to honor patient preferences.
Morse B, Kim K, Xu Z, Matsumoto C, Schilling L, Ohno-Machado L, Mak S, Keller M. Patient and researcher stakeholder preferences for use of electronic health record data: a qualitative study to guide the design and development of a platform to honor patient preferences. Journal Of The American Medical Informatics Association 2023, 30: 1137-1149. PMID: 37141581, PMCID: PMC10198527, DOI: 10.1093/jamia/ocad058.Peer-Reviewed Original ResearchCommon and rare variants associated with cardiometabolic traits across 98,622 whole-genome sequences in the All of Us research program
Wang X, Ryu J, Kim J, Ramirez A, Mayo K, Condon H, Vaitinadin N, Ohno-Machado L, Talavera G, Ellinor P, Lubitz S, Choi S. Common and rare variants associated with cardiometabolic traits across 98,622 whole-genome sequences in the All of Us research program. Journal Of Human Genetics 2023, 68: 565-570. PMID: 37072623, PMCID: PMC10524735, DOI: 10.1038/s10038-023-01147-z.Peer-Reviewed Original ResearchConceptsDiverse human populationsGenomic dataGene-based burden testsWhole genome sequencesRare variant analysisHuman populationQuantitative traitsBurden testsRare lossLociComplex diseasesGenetic associationVariant analysisFunction variantsCardiometabolic traitsRare variantsTraitsBiomedical researchGIGYF1VariantsNPR2ACANSequencePopulationLDLRSimulating 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 frameworkBlockchain-enabled immutable, distributed, and highly available clinical research activity logging system for federated COVID-19 data analysis from multiple institutions
Kuo T, Pham A, Edelson M, Kim J, Chan J, Gupta Y, Ohno-Machado L, Anderson D, Balacha C, Bath T, Baxter S, Becker-Pennrich A, Bell D, Bernstam E, Ngan C, Day M, Doctor J, DuVall S, El-Kareh R, Florian R, Follett R, Geisler B, Ghigi A, Gottlieb A, Hinske L, Hu Z, Ir D, Jiang X, Kim K, Kim J, Knight T, Koola J, Kuo T, Lee N, Mansmann U, Matheny M, Meeker D, Mou Z, Neumann L, Nguyen N, Nick A, Ohno-Machado L, Park E, Paul P, Pletcher M, Post K, Rieder C, Scherer C, Schilling L, Soares A, SooHoo S, Soysal E, Steven C, Tep B, Toy B, Wang B, Wu Z, Xu H, Yong C, Zheng K, Zhou Y, Zucker R. Blockchain-enabled immutable, distributed, and highly available clinical research activity logging system for federated COVID-19 data analysis from multiple institutions. Journal Of The American Medical Informatics Association 2023, 30: 1167-1178. PMID: 36916740, PMCID: PMC10198529, DOI: 10.1093/jamia/ocad049.Peer-Reviewed Original ResearchConceptsFederated data analysisUser activity logsSmart contract deploymentRun-time efficiencyData analysis systemData analysis activitiesActivity logsData discoveryQuerying timeBlockchain systemBlockchain technologyNetwork transactionsCOVID-19 data analysisMultiple institutionsLow deploymentBlockchainGitHub repositoryMultiple nodesLarge networksQueriesAnalysis activitiesHigh availabilityLanguage codeBaseline solutionData analysisA hierarchical strategy to minimize privacy risk when linking “De-identified” data in biomedical research consortia
Ohno-Machado L, Jiang X, Kuo T, Tao S, Chen L, Ram P, Zhang G, Xu H. A hierarchical strategy to minimize privacy risk when linking “De-identified” data in biomedical research consortia. Journal Of Biomedical Informatics 2023, 139: 104322. PMID: 36806328, PMCID: PMC10975485, DOI: 10.1016/j.jbi.2023.104322.Peer-Reviewed Original ResearchConceptsPrivacy of individualsAppropriate privacy protectionData-driven modelsPrivacy protectionPrivacy risksData Coordination CenterData hubData repositoryHierarchical strategyPrivacyBiomedical discoveryData setsRecord linkageData Coordinating CenterRepositoryComplex strategiesCoordination centerTechnologyTechniqueDataPartiesSetHierarchyChapter 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
2022
Evaluation of available risk scores to predict multiple cardiovascular complications for patients with type 2 diabetes mellitus using electronic health records
Ho J, Staimez L, Narayan K, Ohno-Machado L, Simpson R, Hertzberg V. Evaluation of available risk scores to predict multiple cardiovascular complications for patients with type 2 diabetes mellitus using electronic health records. Computer Methods And Programs In Biomedicine Update 2022, 3: 100087. PMID: 37332899, PMCID: PMC10274317, DOI: 10.1016/j.cmpbup.2022.100087.Peer-Reviewed Original ResearchType 2 diabetes mellitusCardiovascular risk modelsElectronic health recordsDiabetes mellitusCardiovascular risk prediction modelsHealth recordsElectronic health record dataAvailable risk scoresMultiple cardiovascular complicationsType 2 diabetesHosmer-Lemeshow goodnessHealth record dataHosmer-Lemeshow statisticRisk prediction modelCardiovascular complicationsCardiovascular outcomesCardiovascular endpointsC-statisticRisk modelRisk scoreType 2PatientsSecondary analysisImpact of raceRecord dataAchieving a Representative Sample of Asian Americans in Biomedical Research Through Community-Based Approaches: Comparing Demographic Data in the All of Us Research Program With the American Community Survey
Randal F, Lozano P, Qi S, Maene C, Shah S, Mo Y, Ratsimbazafy F, Boerwinkle E, Cicek M, Clark C, Cohn E, Gebo K, Loperena R, Mayo K, Mockrin S, Ohno-Machado L, Schully S, Ramirez A, Aschebrook-Kilfoy B, Ahsan H, Lam H, Kim K. Achieving a Representative Sample of Asian Americans in Biomedical Research Through Community-Based Approaches: Comparing Demographic Data in the All of Us Research Program With the American Community Survey. Journal Of Transcultural Nursing 2022, 34: 59-67. PMID: 36398985, DOI: 10.1177/10436596221130796.Peer-Reviewed Original ResearchInvestigation of hypertension and type 2 diabetes as risk factors for dementia in the All of Us cohort
Nagar S, Pemu P, Qian J, Boerwinkle E, Cicek M, Clark C, Cohn E, Gebo K, Loperena R, Mayo K, Mockrin S, Ohno-Machado L, Ramirez A, Schully S, Able A, Green A, Zuchner S, Jordan I, Meller R. Investigation of hypertension and type 2 diabetes as risk factors for dementia in the All of Us cohort. Scientific Reports 2022, 12: 19797. PMID: 36396674, PMCID: PMC9672061, DOI: 10.1038/s41598-022-23353-z.Peer-Reviewed Original ResearchConceptsAssociation of hypertensionPrevalence of dementiaType 2 diabetesRisk factorsUS populationRace/ethnicityHigh prevalenceLarge observational cohort studyMultivariable logistic regression modelRisk factor modificationObservational cohort studyT2D risk factorsInvestigation of hypertensionAssociation of T2DOdds of dementiaRace/ethnicity groupsAssociation of sexCross-sectional analysisLogistic regression modelsWorld Health OrganizationElectronic health recordsConcurrent hypertensionModifiable comorbiditiesCohort studyFinal cohortComparative Safety and Effectiveness of Biologic Therapy for Crohn’s Disease: A CA-IBD Cohort Study
Singh S, Kim J, Luo J, Paul P, Rudrapatna V, Park S, Zheng K, Syal G, Ha C, Fleshner P, McGovern D, Sauk J, Limketkai B, Dulai P, Boland B, Eisenstein S, Ramamoorthy S, Melmed G, Mahadevan U, Sandborn W, Ohno-Machado L. Comparative Safety and Effectiveness of Biologic Therapy for Crohn’s Disease: A CA-IBD Cohort Study. Clinical Gastroenterology And Hepatology 2022, 21: 2359-2369.e5. PMID: 36343846, DOI: 10.1016/j.cgh.2022.10.029.Peer-Reviewed Original ResearchConceptsTNF-α antagonistsRisk of hospitalizationUstekinumab-treated patientsCrohn's diseaseSerious infectionsLower riskMulticenter cohortInflammatory bowel disease-related surgeryTumor necrosis factor α antagonistsNecrosis factor α antagonistsDisease-related surgeryHigher comorbidity burdenVedolizumab-treated patientsNew biologic agentsPropensity-score matchingComorbidity burdenCause hospitalizationAdult patientsBiologic therapyCohort studyPrior hospitalizationBiologic agentsΑ antagonistsBiologic classesComparative safetyConcordance of SARS-CoV-2 Antibody Results during a Period of Low Prevalence
Miller C, Althoff K, Schlueter D, Anton-Culver H, Chen Q, Garbett S, Ratsimbazafy F, Thomsen I, Karlson E, Cicek M, Pinto L, Malin B, Ohno-Machado L, Williams C, Goldstein D, Kouame A, Ramirez A, Gebo K, Schully S. Concordance of SARS-CoV-2 Antibody Results during a Period of Low Prevalence. MSphere 2022, 7: e00257-22. PMID: 36173112, PMCID: PMC9599436, DOI: 10.1128/msphere.00257-22.Peer-Reviewed Original ResearchConceptsSARS-CoV-2 antibody concentrationsLow prevalenceVaccine availabilitySARS-CoV-2 enzyme-linked immunosorbent assayFalse positivityLow SARS-CoV-2 prevalenceSARS-CoV-2 IgG assaysSARS-CoV-2 IgG testSARS-CoV-2 IgG antibodiesSevere acute respiratory syndrome coronavirus 2Coronavirus disease 2019 prevalenceAcute respiratory syndrome coronavirus 2Antibody concentrationsSARS-CoV-2 testDifferent antigensRespiratory syndrome coronavirus 2SARS-CoV-2 prevalenceSyndrome coronavirus 2SARS-CoV-2 pandemicConcordant positive resultsConcordant negative resultsEnzyme-linked immunosorbent assayPositive resultsFuture pandemic preparednessConcordance of results