Partho P Sengupta1, Sirish Shrestha2, Nobuyuki Kagiyama2, Yasmin Hamirani2, Hemant Kulkarni3, Naveena Yanamala2, Rong Bing4, Calvin W L Chin5, Tania A Pawade4, David Messika-Zeitoun6, Lionel Tastet7, Mylène Shen7, David E Newby4, Marie-Annick Clavel7, Phillippe Pibarot8, Marc R Dweck4. 1. West Virginia University Heart and Vascular Institute, Morgantown, West Virginia, USA. Electronic address: partho.sengupta@wvumedicine.org. 2. West Virginia University Heart and Vascular Institute, Morgantown, West Virginia, USA. 3. West Virginia University Heart and Vascular Institute, Morgantown, West Virginia, USA; M&H Research, LLC, San Antonio, Texas, USA. 4. British Heart Foundation Centre for Cardiovascular Science, University of Edinburgh, Edinburgh, United Kingdom. 5. National Heart Centre, Singapore. 6. University of Ottawa Heart Institute, Ottawa, Canada. 7. Department of Medicine, Institut Universitaire de Cardiologie et de Pneumologie de Québec/Québec Heart and Lung Institute, Laval University, Québec, Canada. 8. Department of Medicine, Institut Universitaire de Cardiologie et de Pneumologie de Québec/Québec Heart and Lung Institute, Laval University, Québec, Canada. Electronic address: philippe.pibarot@med.ulaval.ca.
Abstract
OBJECTIVES: The authors explored the development and validation of machine-learning models for augmenting the echocardiographic grading of aortic stenosis (AS) severity. BACKGROUND: In AS, symptoms and adverse events develop secondarily to valvular obstruction and left ventricular decompensation. The current echocardiographic grading of AS severity focuses on the valve and is limited by diagnostic uncertainty. METHODS: Using echocardiography (ECHO) measurements (ECHO cohort, n = 1,052), we performed patient similarity analysis to derive high-severity and low-severity phenogroups of AS. We subsequently developed a supervised machine-learning classifier and validated its performance with independent markers of disease severity obtained using computed tomography (CT) (CT cohort, n = 752) and cardiovascular magnetic resonance (CMR) imaging (CMR cohort, n = 160). The classifier's prognostic value was further validated using clinical outcomes (aortic valve replacement [AVR] and death) observed in the ECHO and CMR cohorts. RESULTS: In 1,964 patients from the 3 multi-institutional cohorts, 1,346 (68%) subjects had either nonsevere or discordant AS severity. Machine learning identified 1,117 (57%) patients as having high-severity and 847 (43%) as having low-severity AS. High-severity patients in CT and CMR cohorts had higher valve calcium scores and left ventricular mass and fibrosis, respectively than the low-severity group. In the ECHO cohort, progression to AVR and progression to death in patients who did not receive AVR was faster in the high-severity group. Compared with the conventional classification of disease severity, machine-learning-based severity classification improved discrimination (integrated discrimination improvement: 0.07; 95% confidence interval: 0.02 to 0.12) and reclassification (net reclassification improvement: 0.17; 95% confidence interval: 0.11 to 0.23) for the outcome of AVR at 5 years. For both ECHO and CMR cohorts, we observed prognostic value of the machine-learning classifications for subgroups with asymptomatic, nonsevere or discordant AS. CONCLUSIONS: Machine learning can integrate ECHO measurements to augment the classification of disease severity in most patients with AS, with major potential to optimize the timing of AVR.
OBJECTIVES: The authors explored the development and validation of machine-learning models for augmenting the echocardiographic grading of aortic stenosis (AS) severity. BACKGROUND: In AS, symptoms and adverse events develop secondarily to valvular obstruction and left ventricular decompensation. The current echocardiographic grading of AS severity focuses on the valve and is limited by diagnostic uncertainty. METHODS: Using echocardiography (ECHO) measurements (ECHO cohort, n = 1,052), we performed patient similarity analysis to derive high-severity and low-severity phenogroups of AS. We subsequently developed a supervised machine-learning classifier and validated its performance with independent markers of disease severity obtained using computed tomography (CT) (CT cohort, n = 752) and cardiovascular magnetic resonance (CMR) imaging (CMR cohort, n = 160). The classifier's prognostic value was further validated using clinical outcomes (aortic valve replacement [AVR] and death) observed in the ECHO and CMR cohorts. RESULTS: In 1,964 patients from the 3 multi-institutional cohorts, 1,346 (68%) subjects had either nonsevere or discordant AS severity. Machine learning identified 1,117 (57%) patients as having high-severity and 847 (43%) as having low-severity AS. High-severity patients in CT and CMR cohorts had higher valve calcium scores and left ventricular mass and fibrosis, respectively than the low-severity group. In the ECHO cohort, progression to AVR and progression to death in patients who did not receive AVR was faster in the high-severity group. Compared with the conventional classification of disease severity, machine-learning-based severity classification improved discrimination (integrated discrimination improvement: 0.07; 95% confidence interval: 0.02 to 0.12) and reclassification (net reclassification improvement: 0.17; 95% confidence interval: 0.11 to 0.23) for the outcome of AVR at 5 years. For both ECHO and CMR cohorts, we observed prognostic value of the machine-learning classifications for subgroups with asymptomatic, nonsevere or discordant AS. CONCLUSIONS: Machine learning can integrate ECHO measurements to augment the classification of disease severity in most patients with AS, with major potential to optimize the timing of AVR.
Authors: Romain Capoulade; Florent Le Ven; Marie-Annick Clavel; Jean G Dumesnil; Abdellaziz Dahou; Christophe Thébault; Marie Arsenault; Kim O'Connor; Élisabeth Bédard; Jonathan Beaudoin; Mario Sénéchal; Mathieu Bernier; Philippe Pibarot Journal: Heart Date: 2016-04-05 Impact factor: 5.994
Authors: Helmut Baumgartner; Judy Hung; Javier Bermejo; John B Chambers; Thor Edvardsen; Steven Goldstein; Patrizio Lancellotti; Melissa LeFevre; Fletcher Miller; Catherine M Otto Journal: J Am Soc Echocardiogr Date: 2017-04 Impact factor: 5.251
Authors: Tania Pawade; Marie-Annick Clavel; Christophe Tribouilloy; Julien Dreyfus; Tiffany Mathieu; Lionel Tastet; Cedric Renard; Mesut Gun; William Steven Arthur Jenkins; Laurent Macron; Jacob W Sechrist; Joan M Lacomis; Virginia Nguyen; Laura Galian Gay; Hug Cuéllar Calabria; Ioannis Ntalas; Timothy Robert Graham Cartlidge; Bernard Prendergast; Ronak Rajani; Arturo Evangelista; João L Cavalcante; David E Newby; Philippe Pibarot; David Messika Zeitoun; Marc R Dweck Journal: Circ Cardiovasc Imaging Date: 2018-03 Impact factor: 7.792
Authors: Calvin W L Chin; Russell J Everett; Jacek Kwiecinski; Alex T Vesey; Emily Yeung; Gavin Esson; William Jenkins; Maria Koo; Saeed Mirsadraee; Audrey C White; Alan G Japp; Sanjay K Prasad; Scott Semple; David E Newby; Marc R Dweck Journal: JACC Cardiovasc Imaging Date: 2016-12-21
Authors: Philippe Généreux; Philippe Pibarot; Björn Redfors; Michael J Mack; Raj R Makkar; Wael A Jaber; Lars G Svensson; Samir Kapadia; E Murat Tuzcu; Vinod H Thourani; Vasilis Babaliaros; Howard C Herrmann; Wilson Y Szeto; David J Cohen; Brian R Lindman; Thomas McAndrew; Maria C Alu; Pamela S Douglas; Rebecca T Hahn; Susheel K Kodali; Craig R Smith; D Craig Miller; John G Webb; Martin B Leon Journal: Eur Heart J Date: 2017-12-01 Impact factor: 29.983
Authors: Brian R Lindman; Devraj Sukul; Marc R Dweck; Mahesh V Madhavan; Benoit J Arsenault; Megan Coylewright; W David Merryman; David E Newby; John Lewis; Frank E Harrell; Michael J Mack; Martin B Leon; Catherine M Otto; Philippe Pibarot Journal: J Am Coll Cardiol Date: 2021-12-07 Impact factor: 24.094