Clinical phenotypes among patients with normal cardiac perfusion using unsupervised learning: a retrospective observational studyResearch in context
Robert J.H. Miller,
Bryan P. Bednarski,
Konrad Pieszko,
Jacek Kwiecinski,
Michelle C. Williams,
Aakash Shanbhag,
Joanna X. Liang,
Cathleen Huang,
Tali Sharir,
M. Timothy Hauser,
Sharmila Dorbala,
Marcelo F. Di Carli,
Mathews B. Fish,
Terrence D. Ruddy,
Timothy M. Bateman,
Andrew J. Einstein,
Philipp A. Kaufmann,
Edward J. Miller,
Albert J. Sinusas,
Wanda Acampa,
Donghee Han,
Damini Dey,
Daniel S. Berman,
Piotr J. Slomka
Affiliations
Robert J.H. Miller
Departments of Medicine (Division of Artificial Intelligence in Medicine), Biomedical Sciences, and Imaging, Cedars-Sinai Medical Center, Los Angeles, CA, USA; Department of Cardiac Sciences, University of Calgary and Libin Cardiovascular Institute, Calgary, AB, Canada
Bryan P. Bednarski
Departments of Medicine (Division of Artificial Intelligence in Medicine), Biomedical Sciences, and Imaging, Cedars-Sinai Medical Center, Los Angeles, CA, USA
Konrad Pieszko
Departments of Medicine (Division of Artificial Intelligence in Medicine), Biomedical Sciences, and Imaging, Cedars-Sinai Medical Center, Los Angeles, CA, USA
Jacek Kwiecinski
Departments of Medicine (Division of Artificial Intelligence in Medicine), Biomedical Sciences, and Imaging, Cedars-Sinai Medical Center, Los Angeles, CA, USA; Department of Interventional Cardiology and Angiology, Institute of Cardiology, Warsaw, Poland
Michelle C. Williams
Departments of Medicine (Division of Artificial Intelligence in Medicine), Biomedical Sciences, and Imaging, Cedars-Sinai Medical Center, Los Angeles, CA, USA; British Heart Foundation Centre for Cardiovascular Science, University of Edinburgh, Edinburgh, United Kingdom
Aakash Shanbhag
Departments of Medicine (Division of Artificial Intelligence in Medicine), Biomedical Sciences, and Imaging, Cedars-Sinai Medical Center, Los Angeles, CA, USA; Signal and Image Processing Institute, Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California, Los Angeles, CA, USA
Joanna X. Liang
Departments of Medicine (Division of Artificial Intelligence in Medicine), Biomedical Sciences, and Imaging, Cedars-Sinai Medical Center, Los Angeles, CA, USA
Cathleen Huang
Departments of Medicine (Division of Artificial Intelligence in Medicine), Biomedical Sciences, and Imaging, Cedars-Sinai Medical Center, Los Angeles, CA, USA
Tali Sharir
Department of Nuclear Cardiology, Assuta Medical Centers, Tel Aviv, Israel; Israel and Ben Gurion University of the Negev, Beer Sheba, Israel
M. Timothy Hauser
Department of Nuclear Cardiology, Oklahoma Heart Hospital, Oklahoma City, OK, USA
Sharmila Dorbala
Division of Nuclear Medicine and Molecular Imaging, Department of Radiology, Brigham and Women's Hospital, Boston, MA, USA
Marcelo F. Di Carli
Division of Nuclear Medicine and Molecular Imaging, Department of Radiology, Brigham and Women's Hospital, Boston, MA, USA
Mathews B. Fish
Oregon Heart and Vascular Institute, Sacred Heart Medical Center, Springfield, OR, USA
Terrence D. Ruddy
Division of Cardiology, University of Ottawa Heart Institute, Ottawa, ON, Canada
Timothy M. Bateman
Cardiovascular Imaging Technologies LLC, Kansas City, MO, USA
Andrew J. Einstein
Division of Cardiology, Department of Medicine and Department of Radiology, Columbia University Irving Medical Center and New York-Presbyterian Hospital, New York, NY, USA
Philipp A. Kaufmann
Department of Nuclear Medicine, Cardiac Imaging, University Hospital Zurich, Zurich, Switzerland
Edward J. Miller
Section of Cardiovascular Medicine, Department of Internal Medicine, Yale University School of Medicine, New Haven, CT, USA
Albert J. Sinusas
Section of Cardiovascular Medicine, Department of Internal Medicine, Yale University School of Medicine, New Haven, CT, USA
Wanda Acampa
Department of Advanced Biomedical Sciences, University of Naples ''Federico II'', Naples, Italy
Donghee Han
Departments of Medicine (Division of Artificial Intelligence in Medicine), Biomedical Sciences, and Imaging, Cedars-Sinai Medical Center, Los Angeles, CA, USA
Damini Dey
Departments of Medicine (Division of Artificial Intelligence in Medicine), Biomedical Sciences, and Imaging, Cedars-Sinai Medical Center, Los Angeles, CA, USA
Daniel S. Berman
Departments of Medicine (Division of Artificial Intelligence in Medicine), Biomedical Sciences, and Imaging, Cedars-Sinai Medical Center, Los Angeles, CA, USA
Piotr J. Slomka
Departments of Medicine (Division of Artificial Intelligence in Medicine), Biomedical Sciences, and Imaging, Cedars-Sinai Medical Center, Los Angeles, CA, USA; Corresponding author. Cedars-Sinai Medical Center, 8700 Beverly Boulevard, Ste. Metro 203, Los Angeles, 90048, CA, USA.
Summary: Background: Myocardial perfusion imaging (MPI) is one of the most common cardiac scans and is used for diagnosis of coronary artery disease and assessment of cardiovascular risk. However, the large majority of MPI patients have normal results. We evaluated whether unsupervised machine learning could identify unique phenotypes among patients with normal scans and whether those phenotypes were associated with risk of death or myocardial infarction. Methods: Patients from a large international multicenter MPI registry (10 sites) with normal perfusion by expert visual interpretation were included in this cohort analysis. The training population included 9849 patients, and external testing population 12,528 patients. Unsupervised cluster analysis was performed, with separate training and external testing cohorts, to identify clusters, with four distinct phenotypes. We evaluated the clinical and imaging features of clusters and their associations with death or myocardial infarction. Findings: Patients in Clusters 1 and 2 almost exclusively underwent exercise stress, while patients in Clusters 3 and 4 mostly required pharmacologic stress. In external testing, the risk for Cluster 4 patients (20.2% of population, unadjusted hazard ratio [HR] 6.17, 95% confidence interval [CI] 4.64–8.20) was higher than the risk associated with pharmacologic stress (HR 3.03, 95% CI 2.53–3.63), or previous myocardial infarction (HR 1.82, 95% CI 1.40–2.36). Interpretation: Unsupervised learning identified four distinct phenotypes of patients with normal perfusion scans, with a significant proportion of patients at very high risk of myocardial infarction or death. Our results suggest a potential role for patient phenotyping to improve risk stratification of patients with normal imaging results. Funding: This work was supported by the National Heart, Lung, and Blood Institute at the National Institutes of Health [R35HL161195 to PS]. The REFINE SPECT database was supported by the National Heart, Lung, and Blood Institute at the National Institutes of Health [R01HL089765 to PS]. MCW was supported by the British Heart Foundation [FS/ICRF/20/26002].
