Author + information
- Received December 18, 2019
- Revision received July 15, 2020
- Accepted July 16, 2020
- Published online September 7, 2020.
- Partho P. Sengupta, MD, DMa,∗ (, )
- Sirish Shrestha, MSca,
- Béatrice Berthon, PhDb,
- Emmanuel Messas, MDc,
- Erwan Donal, MDd,
- Geoffrey H. Tison, MD, MPHe,
- James K. Min, MDf,
- Jan D’hooge, PhDg,
- Jens-Uwe Voigt, MDh,i,
- Joel Dudley, PhDj,k,
- Johan W. Verjans, MD, PhDl,m,
- Khader Shameer, PhDj,k,
- Kipp Johnson, PhDj,k,
- Lasse Lovstakken, PhDm,
- Mahdi Tabassian, PhDg,
- Marco Piccirilli, PhDa,
- Mathieu Pernot, PhDb,
- Naveena Yanamala, MS, PhDa,
- Nicolas Duchateau, PhDn,
- Nobuyuki Kagiyama, MD, PhDa,
- Olivier Bernard, PhDn,
- Piotr Slomka, PhDo,
- Rahul Deo, MD, PhDe and
- Rima Arnaout, MDe
- aWest Virginia University Heart and Vascular Institute, Division of Cardiology, Morgantown, West Virginia
- bPhysique pour la Médecine Paris, Inserm U1273, CNRS FRE 2031, ESPCI Paris, PSL Research University, Paris, France
- cUniversité Paris Descartes, Sorbonne Paris Cité, Paris, France
- dDépartement de Cardiologie et Maladies Vasculaires, Service de Cardiologie et maladies vasculaires, CHU Rennes, Rennes, France
- eDivision of Cardiology, Department of Medicine, University of California San Francisco, San Francisco, California
- fCleerly, Inc., New York, New York
- gLaboratory on Cardiovascular Imaging and Dynamics, Department of Cardiovascular Sciences, KU Leuven, Leuven, Belgium
- hDepartment of Cardiovascular Science, KU Leuven, Leuven, Belgium
- iDepartment of Cardiovascular Diseases, University Hospitals Leuven, Belgium
- jDepartment of Genetics and Genomic Sciences and Institute for Genomics and Multiscale Biology, Icahn School of Medicine at Mount Sinai, New York, New York
- kInstitute for Next Generation Healthcare, Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, New York
- lAustralian Institute for Machine Learning, University of Adelaide, North Terrace, Adelaide, South Australia, Australia
- mDepartment of Circulation and Medical Imaging, Faculty of Medicine and Health Sciences, Norwegian University of Science and Technology, Trondheim, Norway
- nCREATIS, CNRS UMR 5220, INSERM U1206, Université Lyon 1, INSA-LYON, France
- oDepartment of Imaging and Medicine, Cedars-Sinai Medical Center, Los Angeles, California
- ↵∗Address for correspondence:
Dr. Partho P. Sengupta, Heart and Vascular Institute, West Virginia University, 1 Medical Center Drive, Morgantown, West Virginia 26506-8059.
• Algorithm complexity and flexibility of ML techniques can result in inconsistencies in model reporting and interpretations.
• The PRIME checklist provides 7 items to be reported for reducing algorithmic errors and biases.
• The checklist aims to standardize reporting on model design, data, selection, assessment, evaluation, replicability, and limitations.
• As artificial intelligence and ML technologies continue to grow, the checklist will need periodic updates.
Machine learning (ML) has been increasingly used within cardiology, particularly in the domain of cardiovascular imaging. Due to the inherent complexity and flexibility of ML algorithms, inconsistencies in the model performance and interpretation may occur. Several review articles have been recently published that introduce the fundamental principles and clinical application of ML for cardiologists. This paper builds on these introductory principles and outlines a more comprehensive list of crucial responsibilities that need to be completed when developing ML models. This paper aims to serve as a scientific foundation to aid investigators, data scientists, authors, editors, and reviewers involved in machine learning research with the intent of uniform reporting of ML investigations. An independent multidisciplinary panel of ML experts, clinicians, and statisticians worked together to review the theoretical rationale underlying 7 sets of requirements that may reduce algorithmic errors and biases. Finally, the paper summarizes a list of reporting items as an itemized checklist that highlights steps for ensuring correct application of ML models and the consistent reporting of model specifications and results. It is expected that the rapid pace of research and development and the increased availability of real-world evidence may require periodic updates to the checklist.
- artificial intelligence
- cardiovascular imaging
- digital health
- machine learning
- reporting guidelines
- reproducible research
The views expressed in this paper do not reflect the views of the American College of Cardiology or the Journal of American College of Cardiology family. Dr. Dudley has salary support from Tempus Labs. Dr. Johnson has salary support from Tempus Labs; and has an equity interest in Tempus Labs and in Oova, Inc. Dr. Lovstakken is a consultant for GE Vingmed Ultrasound AS. Dr. Min has employment and salary support from Clearly Inc.; and serves as advisor for Arienta. Dr. Slomka has received a grant from Siemens Medical Systems; and has received royalties from Cedars-Sinai. Dr. Yanamala is member of Think2Innovate LLC. Dr. Sengupta is a consultant for Heartsciences, Ultromics, and Kencor Health; and holds equity interests in Ultromics, Kencor Health, and Heartsciences. All other authors have reported that they have no relationships relevant to the contents of this paper to disclose. Jagat Narula, MD, was Guest Editor on this paper.
The authors attest they are in compliance with human studies committees and animal welfare regulations of the authors’ institutions and Food and Drug Administration guidelines, including patient consent where appropriate. For more information, visit the JACC: Cardiovascular Imaging author instructions page.
- Received December 18, 2019.
- Revision received July 15, 2020.
- Accepted July 16, 2020.
- 2020 American College of Cardiology Foundation
This article requires a subscription or purchase to view the full text. If you are a subscriber or member, click Login or the Subscribe link (top menu above) to access this article.