2024
Clinical phenotypes among patients with normal cardiac perfusion using unsupervised learning: a retrospective observational study
Miller R, Bednarski B, Pieszko K, Kwiecinski J, Williams M, Shanbhag A, Liang J, Huang C, Sharir T, Hauser M, Dorbala S, Di Carli M, Fish M, Ruddy T, Bateman T, Einstein A, Kaufmann P, Miller E, Sinusas A, Acampa W, Han D, Dey D, Berman D, Slomka P. Clinical phenotypes among patients with normal cardiac perfusion using unsupervised learning: a retrospective observational study. EBioMedicine 2024, 99: 104930. PMID: 38168587, PMCID: PMC10794922, DOI: 10.1016/j.ebiom.2023.104930.Peer-Reviewed Original ResearchMyocardial infarctionMyocardial perfusion imagingBlood InstituteNational HeartPharmacologic stressExternal testing cohortNormal imaging resultsRetrospective observational studyCoronary artery diseasePrevious myocardial infarctionRisk of deathNormal perfusion scanBritish Heart FoundationNational InstituteCluster 4 patientsDistinct phenotypesCardiovascular riskArtery diseaseRisk stratificationPerfusion scanNormal perfusionImaging featuresNormal scansMPI patientsHeart Foundation
2023
CORONARY ARTERY CALCIFICATIONS ARE A BETTER PREDICTOR OF CARDIOVASCULAR OUTCOMES THAN ISCHEMIC ECG CHANGES IN PATIENTS WITH NORMAL PERFUSION ON EXERCISE SPECT
Shi T, Kokkinidis D, Agarwal R, Liu Y, Sinusas A, Miller E, Feher A. CORONARY ARTERY CALCIFICATIONS ARE A BETTER PREDICTOR OF CARDIOVASCULAR OUTCOMES THAN ISCHEMIC ECG CHANGES IN PATIENTS WITH NORMAL PERFUSION ON EXERCISE SPECT. Journal Of The American College Of Cardiology 2023, 81: 1498. DOI: 10.1016/s0735-1097(23)01942-3.Peer-Reviewed Original Research
2022
Direct Risk Assessment From Myocardial Perfusion Imaging Using Explainable Deep Learning
Singh A, Miller RJH, Otaki Y, Kavanagh P, Hauser MT, Tzolos E, Kwiecinski J, Van Kriekinge S, Wei CC, Sharir T, Einstein AJ, Fish MB, Ruddy TD, Kaufmann PA, Sinusas AJ, Miller EJ, Bateman TM, Dorbala S, Di Carli M, Liang JX, Huang C, Han D, Dey D, Berman DS, Slomka PJ. Direct Risk Assessment From Myocardial Perfusion Imaging Using Explainable Deep Learning. JACC Cardiovascular Imaging 2022, 16: 209-220. PMID: 36274041, PMCID: PMC10980287, DOI: 10.1016/j.jcmg.2022.07.017.Peer-Reviewed Original ResearchConceptsMyocardial perfusion imagingTotal perfusion deficitNonfatal myocardial infarctionMyocardial infarctionPerfusion imagingTomography myocardial perfusion imagingIschemic total perfusion deficitStress total perfusion deficitTesting groupReceiver-operating characteristic curvePatient-level riskPrediction of deathSingle photon emissionLogistic regression modelsCause mortalityPrimary outcomeHighest quartileRisk stratificationAbnormal perfusionNormal perfusionPerfusion deficitsAdverse event predictionPrognostic accuracyHigh riskMyocardial perfusionUnsupervised machine learning improves risk stratification of patients with visual normal SPECT myocardial perfusion imaging assessments
Bednarski B, Williams M, Pieszko K, Miller R, Huang C, Kwiecinski J, Sharir T, Di Carli M, Fish M, Ruddy T, Hasuer T, Miller E, Acampa W, Berman D, Slomka P. Unsupervised machine learning improves risk stratification of patients with visual normal SPECT myocardial perfusion imaging assessments. European Heart Journal 2022, 43: ehac544.300. DOI: 10.1093/eurheartj/ehac544.300.Peer-Reviewed Original ResearchMajor adverse cardiac eventsPeak systolic blood pressureSystolic blood pressureHigh-risk clustersRisk stratificationMyocardial perfusion imagingNormal perfusionHazard ratioBlood pressureCox proportional hazards analysisHigher left ventricular massHigher body mass indexTomography myocardial perfusion imagingNormal clinical assessmentRisk-stratified subgroupsAdverse cardiac eventsPrevalence of diabetesProportional hazards analysisBetter risk stratificationCoronary artery diseaseImproved risk stratificationManagement of patientsKaplan-Meier curvesBody mass indexLeft ventricular mass