Alexander R van Rosendael1, Gabriel Maliakal1, Kranthi K Kolli1, Ashley Beecy1, Subhi J Al'Aref1, Aeshita Dwivedi1, Gurpreet Singh1, Mohit Panday1, Amit Kumar1, Xiaoyue Ma1, Stephan Achenbach2, Mouaz H Al-Mallah3, Daniele Andreini4, Jeroen J Bax5, Daniel S Berman6, Matthew J Budoff7, Filippo Cademartiri8, Tracy Q Callister9, Hyuk-Jae Chang10, Kavitha Chinnaiyan11, Benjamin J W Chow12, Ricardo C Cury13, Augustin DeLago14, Gudrun Feuchtner15, Martin Hadamitzky16, Joerg Hausleiter17, Philipp A Kaufmann18, Yong-Jin Kim19, Jonathon A Leipsic20, Erica Maffei21, Hugo Marques22, Gianluca Pontone4, Gilbert L Raff11, Ronen Rubinshtein23, Leslee J Shaw24, Todd C Villines25, Heidi Gransar26, Yao Lu27, Erica C Jones1, Jessica M Peña1, Fay Y Lin1, James K Min28. 1. Department of Radiology, New York-Presbyterian Hospital and Weill Cornell Medicine, New York, NY, USA. 2. Department of Cardiology, Friedrich-Alexander-University Erlangen-Nuremburg, Germany. 3. King Saud bin Abdulaziz University for Health Sciences, King Abdullah International Medical Research Center, King AbdulAziz Cardiac Center, Ministry of National Guard, Health Affairs, Riyadh, Saudi Arabia. 4. Centro Cardiologico Monzino, IRCCS, Milan, Italy. 5. Department of Cardiology, Leiden University Medical Center, Leiden, The Netherlands. 6. Department of Imaging and Medicine, Cedars Sinai Medical Center, Los Angeles, CA, USA. 7. Department of Medicine, Los Angeles Biomedical Research Institute, Torrance CA, USA. 8. Cardiovascular Imaging Center, SDN IRCCS, Naples, Italy. 9. Tennessee Heart and Vascular Institute, Hendersonville, TN, USA. 10. Division of Cardiology, Severance Cardiovascular Hospital and Severance Biomedical Science Institute, Yonsei University College of Medicine, Yonsei University Health System, Seoul, South Korea. 11. Department of Cardiology, William Beaumont Hospital, Royal Oak, MI, USA. 12. Department of Medicine and Radiology, University of Ottawa, ON, Canada. 13. Department of Radiology, Miami Cardiac and Vascular Institute, Miami, FL, USA. 14. Capitol Cardiology Associates, Albany, NY, USA. 15. Department of Radiology, Medical University of Innsbruck, Innsbruck, Austria. 16. Department of Radiology and Nuclear Medicine, German Heart Center Munich, Munich, Germany. 17. Medizinische Klinik I der Ludwig-Maximilians-UniversitätMünchen, Munich, Germany. 18. Department of Nuclear Medicine, University Hospital, Zurich, Switzerland, University of Zurich, Switzerland. 19. Seoul National University Hospital, Seoul, South Korea. 20. Department of Medicine and Radiology, University of British Columbia, Vancouver, BC, CA, USA. 21. Department of Radiology, Area Vasta 1/ASUR Marche, Urbino, Italy. 22. UNICA, Unit of Cardiovascular Imaging, Hospital da Luz, Lisboa, Portugal. 23. Department of Cardiology at the Lady Davis Carmel Medical Center, The Ruth and Bruce Rappaport School of Medicine, Technion-Israel Institute of Technology, Haifa, Israel. 24. Division of Cardiology, Emory University School of Medicine, Atlanta, GA, USA. 25. Cardiology Service, Walter Reed National Military Center, Bethesda, MD, USA. 26. Department of Imaging, Cedars Sinai Medical Center, Los Angeles, CA, USA. 27. Department of Healthcare Policy and Research, New York-Presbyterian Hospital and the Weill Cornell Medical College, New York, NY, USA. 28. Department of Radiology, New York-Presbyterian Hospital and Weill Cornell Medicine, New York, NY, USA. Electronic address: jkm2001@med.cornell.edu.
Abstract
INTRODUCTION: Machine learning (ML) is a field in computer science that demonstrated to effectively integrate clinical and imaging data for the creation of prognostic scores. The current study investigated whether a ML score, incorporating only the 16 segment coronary tree information derived from coronary computed tomography angiography (CCTA), provides enhanced risk stratification compared with current CCTA based risk scores. METHODS: From the multi-center CONFIRM registry, patients were included with complete CCTA risk score information and ≥3 year follow-up for myocardial infarction and death (primary endpoint). Patients with prior coronary artery disease were excluded. Conventional CCTA risk scores (conventional CCTA approach, segment involvement score, duke prognostic index, segment stenosis score, and the Leaman risk score) and a score created using ML were compared for the area under the receiver operating characteristic curve (AUC). Only 16 segment based coronary stenosis (0%, 1-24%, 25-49%, 50-69%, 70-99% and 100%) and composition (calcified, mixed and non-calcified plaque) were provided to the ML model. A boosted ensemble algorithm (extreme gradient boosting; XGBoost) was used and the entire data was randomly split into a training set (80%) and testing set (20%). First, tuned hyperparameters were used to generate a trained model from the training data set (80% of data). Second, the performance of this trained model was independently tested on the unseen test set (20% of data). RESULTS: In total, 8844 patients (mean age 58.0 ± 11.5 years, 57.7% male) were included. During a mean follow-up time of 4.6 ± 1.5 years, 609 events occurred (6.9%). No CAD was observed in 48.7% (3.5% event), non-obstructive CAD in 31.8% (6.8% event), and obstructive CAD in 19.5% (15.6% event). Discrimination of events as expressed by AUC was significantly better for the ML based approach (0.771) vs the other scores (ranging from 0.685 to 0.701), P < 0.001. Net reclassification improvement analysis showed that the improved risk stratification was the result of down-classification of risk among patients that did not experience events (non-events). CONCLUSION: A risk score created by a ML based algorithm, that utilizes standard 16 coronary segment stenosis and composition information derived from detailed CCTA reading, has greater prognostic accuracy than current CCTA integrated risk scores. These findings indicate that a ML based algorithm can improve the integration of CCTA derived plaque information to improve risk stratification. Published by Elsevier Inc.
INTRODUCTION: Machine learning (ML) is a field in computer science that demonstrated to effectively integrate clinical and imaging data for the creation of prognostic scores. The current study investigated whether a ML score, incorporating only the 16 segment coronary tree information derived from coronary computed tomography angiography (CCTA), provides enhanced risk stratification compared with current CCTA based risk scores. METHODS: From the multi-center CONFIRM registry, patients were included with complete CCTA risk score information and ≥3 year follow-up for myocardial infarction and death (primary endpoint). Patients with prior coronary artery disease were excluded. Conventional CCTA risk scores (conventional CCTA approach, segment involvement score, duke prognostic index, segment stenosis score, and the Leaman risk score) and a score created using ML were compared for the area under the receiver operating characteristic curve (AUC). Only 16 segment based coronary stenosis (0%, 1-24%, 25-49%, 50-69%, 70-99% and 100%) and composition (calcified, mixed and non-calcified plaque) were provided to the ML model. A boosted ensemble algorithm (extreme gradient boosting; XGBoost) was used and the entire data was randomly split into a training set (80%) and testing set (20%). First, tuned hyperparameters were used to generate a trained model from the training data set (80% of data). Second, the performance of this trained model was independently tested on the unseen test set (20% of data). RESULTS: In total, 8844 patients (mean age 58.0 ± 11.5 years, 57.7% male) were included. During a mean follow-up time of 4.6 ± 1.5 years, 609 events occurred (6.9%). No CAD was observed in 48.7% (3.5% event), non-obstructive CAD in 31.8% (6.8% event), and obstructive CAD in 19.5% (15.6% event). Discrimination of events as expressed by AUC was significantly better for the ML based approach (0.771) vs the other scores (ranging from 0.685 to 0.701), P < 0.001. Net reclassification improvement analysis showed that the improved risk stratification was the result of down-classification of risk among patients that did not experience events (non-events). CONCLUSION: A risk score created by a ML based algorithm, that utilizes standard 16 coronary segment stenosis and composition information derived from detailed CCTA reading, has greater prognostic accuracy than current CCTA integrated risk scores. These findings indicate that a ML based algorithm can improve the integration of CCTA derived plaque information to improve risk stratification. Published by Elsevier Inc.
Authors: Frederic Commandeur; Piotr J Slomka; Markus Goeller; Xi Chen; Sebastien Cadet; Aryabod Razipour; Priscilla McElhinney; Heidi Gransar; Stephanie Cantu; Robert J H Miller; Alan Rozanski; Stephan Achenbach; Balaji K Tamarappoo; Daniel S Berman; Damini Dey Journal: Cardiovasc Res Date: 2020-12-01 Impact factor: 10.787
Authors: Subhi J Al'Aref; Gabriel Maliakal; Gurpreet Singh; Alexander R van Rosendael; Xiaoyue Ma; Zhuoran Xu; Omar Al Hussein Alawamlh; Benjamin Lee; Mohit Pandey; Stephan Achenbach; Mouaz H Al-Mallah; Daniele Andreini; Jeroen J Bax; Daniel S Berman; Matthew J Budoff; Filippo Cademartiri; Tracy Q Callister; Hyuk-Jae Chang; Kavitha Chinnaiyan; Benjamin J W Chow; Ricardo C Cury; Augustin DeLago; Gudrun Feuchtner; Martin Hadamitzky; Joerg Hausleiter; Philipp A Kaufmann; Yong-Jin Kim; Jonathon A Leipsic; Erica Maffei; Hugo Marques; Pedro de Araújo Gonçalves; Gianluca Pontone; Gilbert L Raff; Ronen Rubinshtein; Todd C Villines; Heidi Gransar; Yao Lu; Erica C Jones; Jessica M Peña; Fay Y Lin; James K Min; Leslee J Shaw Journal: Eur Heart J Date: 2020-01-14 Impact factor: 29.983
Authors: Andrew Lin; Márton Kolossváry; Jeremy Yuvaraj; Sebastien Cadet; Priscilla A McElhinney; Cathy Jiang; Nitesh Nerlekar; Stephen J Nicholls; Piotr J Slomka; Pál Maurovich-Horvat; Dennis T L Wong; Damini Dey Journal: JACC Cardiovasc Imaging Date: 2020-08-26
Authors: Eric Munger; Harry Choi; Amit K Dey; Youssef A Elnabawi; Jacob W Groenendyk; Justin Rodante; Andrew Keel; Milena Aksentijevich; Aarthi S Reddy; Noor Khalil; Jenis Argueta-Amaya; Martin P Playford; Julie Erb-Alvarez; Xin Tian; Colin Wu; Johann E Gudjonsson; Lam C Tsoi; Mohsin Saleet Jafri; Veit Sandfort; Marcus Y Chen; Sanjiv J Shah; David A Bluemke; Benjamin Lockshin; Ahmed Hasan; Joel M Gelfand; Nehal N Mehta Journal: J Am Acad Dermatol Date: 2019-10-31 Impact factor: 11.527