2022
Individualising intensive systolic blood pressure reduction in hypertension using computational trial phenomaps and machine learning: a post-hoc analysis of randomised clinical trials
Oikonomou EK, Spatz ES, Suchard MA, Khera R. Individualising intensive systolic blood pressure reduction in hypertension using computational trial phenomaps and machine learning: a post-hoc analysis of randomised clinical trials. The Lancet Digital Health 2022, 4: e796-e805. PMID: 36307193, PMCID: PMC9768739, DOI: 10.1016/s2589-7500(22)00170-4.Peer-Reviewed Original ResearchConceptsSystolic blood pressure controlBlood pressure controlIntensive systolic blood pressure controlType 2 diabetesPressure controlCardiovascular benefitsClinical trialsMajor adverse cardiovascular eventsFirst major adverse cardiovascular eventLarge randomised clinical trialsACCORD-BP trialAdverse cardiovascular eventsRandomised clinical trialsSystolic blood pressureCox regression analysisTreatment effectsHazard ratio estimatesACCORD-BPBP trialCardiovascular eventsBlood pressurePrimary outcomeStandard treatmentBaseline variablesIndex patients
2024
Artificial Intelligence-Enhanced Risk Stratification of Cancer Therapeutics-Related Cardiac Dysfunction Using Electrocardiographic Images.
Oikonomou E, Sangha V, Dhingra L, Aminorroaya A, Coppi A, Krumholz H, Baldassarre L, Khera R. Artificial Intelligence-Enhanced Risk Stratification of Cancer Therapeutics-Related Cardiac Dysfunction Using Electrocardiographic Images. Circulation Cardiovascular Quality And Outcomes 2024 PMID: 39221857, DOI: 10.1161/circoutcomes.124.011504.Peer-Reviewed Original ResearchCancer therapeutics-related cardiac dysfunctionGlobal longitudinal strainLeft ventricular systolic dysfunctionCardiac dysfunctionBreast cancerNon-Hodgkin lymphoma therapyNon-Hodgkin's lymphomaVentricular systolic dysfunctionAssociated with worse global longitudinal strainRisk stratification strategiesHigh-risk groupMonths post-treatmentPost hoc analysisElectrocardiographic (ECGTrastuzumab exposureLymphoma therapySystolic dysfunctionAI-ECGBefore treatmentRisk biomarkersLongitudinal strainLow riskStratification strategiesHigher incidencePositive screenArtificial intelligence-enhanced patient evaluation: bridging art and science
Oikonomou E, Khera R. Artificial intelligence-enhanced patient evaluation: bridging art and science. European Heart Journal 2024, 45: 3204-3218. PMID: 38976371, PMCID: PMC11400875, DOI: 10.1093/eurheartj/ehae415.Peer-Reviewed Reviews, Practice Guidelines, Standards, and Consensus StatementsTransforming Cardiovascular Care With Artificial Intelligence: From Discovery to Practice JACC State-of-the-Art Review
Khera R, Oikonomou E, Nadkarni G, Morley J, Wiens J, Butte A, Topol E. Transforming Cardiovascular Care With Artificial Intelligence: From Discovery to Practice JACC State-of-the-Art Review. Journal Of The American College Of Cardiology 2024, 84: 97-114. PMID: 38925729, DOI: 10.1016/j.jacc.2024.05.003.Peer-Reviewed Reviews, Practice Guidelines, Standards, and Consensus StatementsA Multimodal Video-Based AI Biomarker for Aortic Stenosis Development and Progression
Oikonomou E, Holste G, Yuan N, Coppi A, McNamara R, Haynes N, Vora A, Velazquez E, Li F, Menon V, Kapadia S, Gill T, Nadkarni G, Krumholz H, Wang Z, Ouyang D, Khera R. A Multimodal Video-Based AI Biomarker for Aortic Stenosis Development and Progression. JAMA Cardiology 2024, 9: 534-544. PMID: 38581644, PMCID: PMC10999005, DOI: 10.1001/jamacardio.2024.0595.Peer-Reviewed Original ResearchCardiac magnetic resonanceAortic valve replacementCardiac magnetic resonance imagingAV VmaxSevere ASAortic stenosisCohort studyPeak aortic valve velocityCohort study of patientsAortic valve velocityCohort of patientsTraditional cardiovascular risk factorsAssociated with faster progressionStudy of patientsCedars-Sinai Medical CenterAssociated with AS developmentCardiovascular risk factorsCardiovascular imaging modalitiesIndependent of ageModerate ASEjection fractionEchocardiographic studiesValve replacementRisk stratificationCardiac structureA Multicenter Evaluation of the Impact of Therapies on Deep Learning-Based Electrocardiographic Hypertrophic Cardiomyopathy Markers
Dhingra L, Sangha V, Aminorroaya A, Bryde R, Gaballa A, Ali A, Mehra N, Krumholz H, Sen S, Kramer C, Martinez M, Desai M, Oikonomou E, Khera R. A Multicenter Evaluation of the Impact of Therapies on Deep Learning-Based Electrocardiographic Hypertrophic Cardiomyopathy Markers. The American Journal Of Cardiology 2024, 237: 35-40. PMID: 39581517, DOI: 10.1016/j.amjcard.2024.11.028.Peer-Reviewed Original ResearchCleveland Clinic FoundationHypertrophic cardiomyopathyMedian follow-up periodHypertrophic cardiomyopathy therapyMonitoring treatment responseFollow-up periodImpact of therapyAtlantic Health SystemLack of improvementOral alternativePost-SRTMedical therapyTreatment responseMulticenter evaluationInterventricular septumPercutaneous reductionMavacamtenTherapyPatientsClinic FoundationPoint-of-care monitoringECGECG imagesScoresHealth systemExpanding artificial intelligence to understudied populations: congenital heart disease as the next frontier
Oikonomou E, Khera R. Expanding artificial intelligence to understudied populations: congenital heart disease as the next frontier. European Heart Journal 2024, ehae737. PMID: 39523016, DOI: 10.1093/eurheartj/ehae737.Commentaries, Editorials and LettersCardiovascular care with digital twin technology in the era of generative artificial intelligence
Thangaraj P, Benson S, Oikonomou E, Asselbergs F, Khera R. Cardiovascular care with digital twin technology in the era of generative artificial intelligence. European Heart Journal 2024, ehae619. PMID: 39322420, DOI: 10.1093/eurheartj/ehae619.Peer-Reviewed Reviews, Practice Guidelines, Standards, and Consensus StatementsGenerative artificial intelligenceCardiovascular careCardiovascular medicinePersonalized cardiovascular careArtificial intelligenceSimulations of clinical scenariosData modalitiesPrediction of disease riskClinical decision-makingIn silico replicationPersonalized patient careDigital twinClinical scenariosDigital twin technologyMulti-modal dataProcedural planningDiagnostic workflowDisease phenotypePatient careDesigning medical artificial intelligence systems for global use: focus on interoperability, scalability, and accessibility
Oikonomou E, Khera R. Designing medical artificial intelligence systems for global use: focus on interoperability, scalability, and accessibility. Hellenic Journal Of Cardiology 2024 PMID: 39025234, DOI: 10.1016/j.hjc.2024.07.003.Peer-Reviewed Original ResearchArtificial intelligenceMedical artificial intelligence systemsDesigning AI systemsMachine learning systemsArtificial intelligence systemsBenefits of AIIntelligent systemsAI systemsLearning systemEnd-usersData typesAI developmentInteroperabilityTemporal settingAccessScalabilityTreatment of cardiovascular diseasesIntelligenceSystemMachineQuality assuranceInternational cohortCardiovascular diseaseObstaclesEfficient deep learning-based automated diagnosis from echocardiography with contrastive self-supervised learning
Holste G, Oikonomou E, Mortazavi B, Wang Z, Khera R. Efficient deep learning-based automated diagnosis from echocardiography with contrastive self-supervised learning. Communications Medicine 2024, 4: 133. PMID: 38971887, PMCID: PMC11227494, DOI: 10.1038/s43856-024-00538-3.Peer-Reviewed Original ResearchSelf-supervised learningTransfer learningTraining dataEchocardiogram videosPortion of labelled dataStandard transfer learning approachContrastive self-supervised learningSelf-supervised learning approachLearning approachImage recognition tasksState-of-the-artContrastive learning approachFine-tuningTransfer learning approachMedical image diagnosisCardiac disease diagnosisContrastive learningVideo framesLabeled datasetLabeled dataExpert labelsClassification performanceMedical imagesRecognition taskVideoVideo-Based Kinematic Analysis of Movement Quality in a Phase 3 Clinical Trial of Troriluzole in Adults with Spinocerebellar Ataxia: A Post Hoc Analysis
L’Italien G, Oikonomou E, Khera R, Potashman M, Beiner M, Maclaine G, Schmahmann J, Perlman S, Coric V. Video-Based Kinematic Analysis of Movement Quality in a Phase 3 Clinical Trial of Troriluzole in Adults with Spinocerebellar Ataxia: A Post Hoc Analysis. Neurology And Therapy 2024, 13: 1287-1301. PMID: 38814532, PMCID: PMC11263303, DOI: 10.1007/s40120-024-00625-6.Peer-Reviewed Original ResearchMovement qualityVideo-based kinematic analysisGait stability measuresTandem walking taskRating of AtaxiaGait qualityGait assessmentGait parametersTandem walkingWalking assessmentsWalking taskSpinocerebellar ataxiaVideo-based assessmentClinical expertiseNatural walkingRandomized participantsGaitHigh riskPost hoc analysisStandardized scalesAdultsWalkingParticipantsHoc analysisPhase 3Development and multinational validation of an algorithmic strategy for high Lp(a) screening
Aminorroaya A, Dhingra L, Oikonomou E, Saadatagah S, Thangaraj P, Vasisht Shankar S, Spatz E, Khera R. Development and multinational validation of an algorithmic strategy for high Lp(a) screening. Nature Cardiovascular Research 2024, 3: 558-566. PMID: 39195936, DOI: 10.1038/s44161-024-00469-1.Peer-Reviewed Original ResearchElectronic health recordsAssociated with premature atherosclerotic cardiovascular diseaseElevated Lp(aHealth recordsUK BiobankPremature atherosclerotic cardiovascular diseaseMachine learning modelsAtherosclerotic cardiovascular diseaseCohort studyReal-world settingsTargeted screeningCardiovascular diseaseLearning modelsNovel targeted therapeuticsAlgorithmic strategiesCohortProbability thresholdScreeningClinical featuresValidation cohortElevated lipoproteinRisk inspectionARICLp(aReal-world evaluation of an algorithmic machine-learning-guided testing approach in stable chest pain: a multinational, multicohort study
Oikonomou E, Aminorroaya A, Dhingra L, Partridge C, Velazquez E, Desai N, Krumholz H, Miller E, Khera R. Real-world evaluation of an algorithmic machine-learning-guided testing approach in stable chest pain: a multinational, multicohort study. European Heart Journal - Digital Health 2024, 5: 303-313. PMID: 38774380, PMCID: PMC11104476, DOI: 10.1093/ehjdh/ztae023.Peer-Reviewed Original ResearchRisk of acute myocardial infarctionAssociated with lower oddsHospital health systemCoronary artery diseaseCardiac testingRisk of adverse outcomesUK BiobankHealth systemProvider-drivenLower oddsAssociated with better outcomesAcute myocardial infarctionBlack raceStable chest painFemale sexReal world evaluationDiabetes historyMulticohort studyFunction testsSuspected coronary artery diseaseYounger ageRisk profileAdverse outcomesMultinational cohortPost hoc analysisLeveraging the Full Potential of Wearable Devices in Cardiomyopathies
Oikonomou E, Khera R. Leveraging the Full Potential of Wearable Devices in Cardiomyopathies. Journal Of Cardiac Failure 2024, 30: 964-966. PMID: 38452997, DOI: 10.1016/j.cardfail.2024.02.011.Commentaries, Editorials and LettersBiometric contrastive learning for data-efficient deep learning from electrocardiographic images
Sangha V, Khunte A, Holste G, Mortazavi B, Wang Z, Oikonomou E, Khera R. Biometric contrastive learning for data-efficient deep learning from electrocardiographic images. Journal Of The American Medical Informatics Association 2024, 31: 855-865. PMID: 38269618, PMCID: PMC10990541, DOI: 10.1093/jamia/ocae002.Peer-Reviewed Original ResearchLabeled training dataContrastive learningECG imagesLabeled dataTraining dataDeep learningProportions of labeled dataArtificial intelligenceSelf-supervised contrastive learningTraditional supervised learningConvolutional neural networkHeld-out test setSupervised learningPretraining strategyBiometric signatureImageNet initializationPretraining approachNeural networkImageNetAI modelsImage objectsTest setLearningDetect atrial fibrillationEquivalent performance
2023
An explainable machine learning-based phenomapping strategy for adaptive predictive enrichment in randomized clinical trials
Oikonomou E, Thangaraj P, Bhatt D, Ross J, Young L, Krumholz H, Suchard M, Khera R. An explainable machine learning-based phenomapping strategy for adaptive predictive enrichment in randomized clinical trials. Npj Digital Medicine 2023, 6: 217. PMID: 38001154, PMCID: PMC10673945, DOI: 10.1038/s41746-023-00963-z.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 ResearchDetection of left ventricular systolic dysfunction from single-lead electrocardiography adapted for portable and wearable devices
Khunte A, Sangha V, Oikonomou E, Dhingra L, Aminorroaya A, Mortazavi B, Coppi A, Brandt C, Krumholz H, Khera R. Detection of left ventricular systolic dysfunction from single-lead electrocardiography adapted for portable and wearable devices. Npj Digital Medicine 2023, 6: 124. PMID: 37433874, PMCID: PMC10336107, DOI: 10.1038/s41746-023-00869-w.Peer-Reviewed Original ResearchArtificial intelligenceRandom Gaussian noiseNoisy electrocardiogramGaussian noiseElectrocardiogram (ECGWearable devicesSingle-lead electrocardiogramPortable devicesSNRWearableNoiseDevice noiseRepositoryAI-based screeningIntelligenceDetectionDevicesNoise sourcesVentricular systolic dysfunctionModelElectrocardiogramSingle-lead electrocardiographyTrainingPredicting aortic stenosis progression using a video-based deep learning model of aortic stenosis built for single-view two-dimensional echocardiography
Oikonomou E, Holste G, Mcnamara R, Velazquez E, Nadkarni G, Ouyang D, Krumholz H, Wang Z, Khera R. Predicting aortic stenosis progression using a video-based deep learning model of aortic stenosis built for single-view two-dimensional echocardiography. European Heart Journal 2023, 44: ehad655.040. DOI: 10.1093/eurheartj/ehad655.040.Peer-Reviewed Original ResearchLeft ventricular ejection fractionSevere aortic stenosisAortic stenosisAS progressionAV VmaxTransthoracic echocardiographyYale New Haven Health SystemBaseline left ventricular ejection fractionAortic stenosis progressionModerate aortic stenosisRetrospective cohort studyVentricular ejection fractionTwo-dimensional echocardiographyMean rateModerate ASAS severityCohort studyEjection fractionPatient sexStenosis progressionTTE studiesEligible participantsSerial monitoringSpecialized centersTimely diagnosis
2021
A phenomapping-derived tool to personalize the selection of anatomical vs. functional testing in evaluating chest pain (ASSIST)
Oikonomou EK, Van Dijk D, Parise H, Suchard MA, de Lemos J, Antoniades C, Velazquez EJ, Miller EJ, Khera R. A phenomapping-derived tool to personalize the selection of anatomical vs. functional testing in evaluating chest pain (ASSIST). European Heart Journal 2021, 42: 2536-2548. PMID: 33881513, PMCID: PMC8488385, DOI: 10.1093/eurheartj/ehab223.Peer-Reviewed Original ResearchConceptsStable chest painChest painPrimary endpointMajor adverse cardiovascular eventsNon-fatal myocardial infarctionAdverse cardiovascular eventsStudy's primary endpointCoronary artery diseaseClinical trial populationsCox regression modelParticipant-level dataSCOT-HEARTCardiovascular eventsCause mortalityHazard ratioPatients 5Artery diseaseFunctional testingPROMISE trialTrial populationMyocardial infarctionLower incidenceStudy populationPainCollected variables