Machine Learning Framework to Identify Individuals at Risk of Rapid Progression of Coronary Atherosclerosis: From the PARADIGM Registry

• Type of Material: Article
• Authors: Donghee Han, Yonsei University; Kranthi K. Kolli, New York Presbyterian Hospital; Subhi J. Al'Aref, New York Presbyterian Hospital; Lohendran Baskaran, New York Presbyterian Hospital; Alexander R. van Rosendael, New York Presbyterian Hospital; Heidi Gransar, Cedars Sinai Medical Center; Daniele Andreini, IRCCS; Matthew J. Budoff, Los Angeles Biomedical Research Institute; Filippo Cademartiri, SDN IRCCS; Kavitha Chinnaiyan, William Beaumont Hospital; Jung Hyun Choi, Pusan National University; Gianluca Conte, IRCCS; Hugo Marques, Hospital da Luz; Pedro de Araujo Goncalves, Hospital da Luz; Ilan Gottlieb, Casa Saude Sao Jose; Martin Hadamitzky, German Heart Center Munich; Jonathon A. Leipsic, University of British Columbia; Erica Maffei, Area Vasta 1 ASUR Urbino; Gianluca Pontone, IRCCS; Gilbert L. Raff, William Beaumont Hospital; Sangshoon Shin, Ewha Womans University; Yong-Jin Kim, Seoul National University; Byoung kwon Lee, Yonsei University; Eun Ju Chun, Seoul National University; Ji Min Sung, Yonsei University; Sang-Eun Lee, Yonsei University; Renu Virmani, CVPath Institute; Habib Samady, Emory University; Peter Stone, Harvard Medical School; Jagat Narula, Icahn School of Medicine at Mount Sinai; Daniel S. Berman, Cedars Sinai Medical Center; Jeroen J. Bax, Leiden University; Leslee Shaw, Emory University; Fay Y. Lin, New York Presbyterian Hospital; James K. Min, New York Presbyterian Hospital; Hyuk Jae Chang, Yonsei University
• Language: English
• Date: 2020-03-03
• Publisher: Wiley
• Publication Version: Final Published Version
• Copyright Statement: © 2020 The Authors. Published on behalf of the American Heart Association, Inc., by Wiley.
• License: Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International
• Final Published Version (URL): http://dx.doi.org/10.1161/JAHA.119.013958
• Title of Journal or Parent Work: Journal of the American Heart Association
• Volume: 9
• Issue: 5
• Start Page: e013958
• End Page: e013958
• Grant/Funding Information: This work was also supported by Institute for Information & communications Technology Promotion (IITP) grant funded by the Korea government (MSIT) (2017‐0‐00255, Autonomous digital companion framework and application).; This work was supported by the Leading Foreign Research Institute Recruitment Program through the National Research Foundation (NRF) of Korea funded by the Ministry of Science and ICT (MSIT) (Grant No. 2012027176) and the Technology Innovation Program (10075266, Data Center for Korean Cardiovascular Imaging Reference) funded by the Ministry of Trade, Industry & Energy (MOTIE, Korea).
• Keywords: Regression; coronary computed tomography angiography; Quantification; Computed tomography; Guidelines; risk prediction; Cardiovascular System & Cardiology; plaque progression; Prediction; Life Sciences & Biomedicine; Plaque; Science & Technology; Artery disease; Cardiac & Cardiovascular Systems; coronary artery disease; Lesions; Cardiovascular risk; Performance; machine learning
• Research Categories: Health Sciences, Pathology; Health Sciences, Health Care Management; Health Sciences, Radiology

Abstract

Background Rapid coronary plaque progression (RPP) is associated with incident cardiovascular events. To date, no method exists for the identification of individuals at risk of RPP at a single point in time. This study integrated coronary computed tomography angiography–determined qualitative and quantitative plaque features within a machine learning (ML) framework to determine its performance for predicting RPP. Methods and Results Qualitative and quantitative coronary computed tomography angiography plaque characterization was performed in 1083 patients who underwent serial coronary computed tomography angiography from the PARADIGM (Progression of Atherosclerotic Plaque Determined by Computed Tomographic Angiography Imaging) registry. RPP was defined as an annual progression of percentage atheroma volume ≥1.0%. We employed the following ML models: model 1, clinical variables; model 2, model 1 plus qualitative plaque features; model 3, model 2 plus quantitative plaque features. ML models were compared with the atherosclerotic cardiovascular disease risk score, Duke coronary artery disease score, and a logistic regression statistical model. 224 patients (21%) were identified as RPP. Feature selection in ML identifies that quantitative computed tomography variables were higher‐ranking features, followed by qualitative computed tomography variables and clinical/laboratory variables. ML model 3 exhibited the highest discriminatory performance to identify individuals who would experience RPP when compared with atherosclerotic cardiovascular disease risk score, the other ML models, and the statistical model (area under the receiver operating characteristic curve in ML model 3, 0.83 [95% CI 0.78–0.89], versus atherosclerotic cardiovascular disease risk score, 0.60 [0.52–0.67]; Duke coronary artery disease score, 0.74 [0.68–0.79]; ML model 1, 0.62 [0.55–0.69]; ML model 2, 0.73 [0.67–0.80]; all P<0.001; statistical model, 0.81 [0.75–0.87], P=0.128). Conclusions Based on a ML framework, quantitative atherosclerosis characterization has been shown to be the most important feature when compared with clinical, laboratory, and qualitative measures in identifying patients at risk of RPP.