Anish N Bhuva1,2, Thomas A Treibel1,2, Antonio De Marvao3, Carlo Biffi3,4, Timothy J W Dawes3,5, Georgia Doumou3, Wenjia Bai4, Kush Patel1,2, Redha Boubertakh2, Daniel Rueckert4, Declan P O'Regan3, Alun D Hughes1, James C Moon1,2, Charlotte H Manisty1,2. 1. Institute for Cardiovascular Science, University College London, Chenies Mews, London WC1E6HX, UK. 2. Department of Cardiovascular Imaging, Barts Heart Centre, Barts Health NHS Trust, King George V Building, West Smithfield, London EC1A 7BE, UK. 3. MRC London Institute of Medical Sciences, Imperial College London, Hammersmith Hospital Campus, Du Cane Road, London W120NN, UK. 4. Department of Computing, Imperial College London, South Kensington Campus, 180 Queen's Gate, London SW72RH, UK. 5. National Heart and Lung Institute, Imperial College London, Du Cane Road, London W120NN, UK.
Abstract
AIMS: Left ventricular hypertrophy (LVH) in aortic stenosis (AS) varies widely before and after aortic valve replacement (AVR), and deeper phenotyping beyond traditional global measures may improve risk stratification. We hypothesized that machine learning derived 3D LV models may provide a more sensitive assessment of remodelling and sex-related differences in AS than conventional measurements. METHODS AND RESULTS: One hundred and sixteen patients with severe, symptomatic AS (54% male, 70 ± 10 years) underwent cardiovascular magnetic resonance pre-AVR and 1 year post-AVR. Computational analysis produced co-registered 3D models of wall thickness, which were compared with 40 propensity-matched healthy controls. Preoperative regional wall thickness and post-operative percentage wall thickness regression were analysed, stratified by sex. AS hypertrophy and regression post-AVR was non-uniform-greatest in the septum with more pronounced changes in males than females (wall thickness regression: -13 ± 3.6 vs. -6 ± 1.9%, respectively, P < 0.05). Even patients without LVH (16% with normal indexed LV mass, 79% female) had greater septal and inferior wall thickness compared with controls (8.8 ± 1.6 vs. 6.6 ± 1.2 mm, P < 0.05), which regressed post-AVR. These differences were not detectable by global measures of remodelling. Changes to clinical parameters post-AVR were also greater in males: N-terminal pro-brain natriuretic peptide (NT-proBNP) [-37 (interquartile range -88 to -2) vs. -1 (-24 to 11) ng/L, P = 0.008], and systolic blood pressure (12.9 ± 23 vs. 2.1 ± 17 mmHg, P = 0.009), with changes in NT-proBNP correlating with percentage LV mass regression in males only (ß 0.32, P = 0.02). CONCLUSION: In patients with severe AS, including those without overt LVH, LV remodelling is most plastic in the septum, and greater in males, both pre-AVR and post-AVR. Three-dimensional machine learning is more sensitive than conventional analysis to these changes, potentially enhancing risk stratification. CLINICAL TRIAL REGISTRATION: Regression of myocardial fibrosis after aortic valve replacement (RELIEF-AS); NCT02174471. https://clinicaltrials.gov/ct2/show/NCT02174471. Published on behalf of the European Society of Cardiology. All rights reserved.
AIMS: Left ventricular hypertrophy (LVH) in aortic stenosis (AS) varies widely before and after aortic valve replacement (AVR), and deeper phenotyping beyond traditional global measures may improve risk stratification. We hypothesized that machine learning derived 3D LV models may provide a more sensitive assessment of remodelling and sex-related differences in AS than conventional measurements. METHODS AND RESULTS: One hundred and sixteen patients with severe, symptomatic AS (54% male, 70 ± 10 years) underwent cardiovascular magnetic resonance pre-AVR and 1 year post-AVR. Computational analysis produced co-registered 3D models of wall thickness, which were compared with 40 propensity-matched healthy controls. Preoperative regional wall thickness and post-operative percentage wall thickness regression were analysed, stratified by sex. AS hypertrophy and regression post-AVR was non-uniform-greatest in the septum with more pronounced changes in males than females (wall thickness regression: -13 ± 3.6 vs. -6 ± 1.9%, respectively, P < 0.05). Even patients without LVH (16% with normal indexed LV mass, 79% female) had greater septal and inferior wall thickness compared with controls (8.8 ± 1.6 vs. 6.6 ± 1.2 mm, P < 0.05), which regressed post-AVR. These differences were not detectable by global measures of remodelling. Changes to clinical parameters post-AVR were also greater in males: N-terminal pro-brain natriuretic peptide (NT-proBNP) [-37 (interquartile range -88 to -2) vs. -1 (-24 to 11) ng/L, P = 0.008], and systolic blood pressure (12.9 ± 23 vs. 2.1 ± 17 mmHg, P = 0.009), with changes in NT-proBNP correlating with percentage LV mass regression in males only (ß 0.32, P = 0.02). CONCLUSION: In patients with severe AS, including those without overt LVH, LV remodelling is most plastic in the septum, and greater in males, both pre-AVR and post-AVR. Three-dimensional machine learning is more sensitive than conventional analysis to these changes, potentially enhancing risk stratification. CLINICAL TRIAL REGISTRATION: Regression of myocardial fibrosis after aortic valve replacement (RELIEF-AS); NCT02174471. https://clinicaltrials.gov/ct2/show/NCT02174471. Published on behalf of the European Society of Cardiology. All rights reserved.
Authors: Giovanni Cioffi; Pompilio Faggiano; Enrico Vizzardi; Luigi Tarantini; Dana Cramariuc; Eva Gerdts; Giovanni de Simone Journal: Heart Date: 2010-08-18 Impact factor: 5.994
Authors: O F Bueno; L J De Windt; K M Tymitz; S A Witt; T R Kimball; R Klevitsky; T E Hewett; S P Jones; D J Lefer; C F Peng; R N Kitsis; J D Molkentin Journal: EMBO J Date: 2000-12-01 Impact factor: 11.598
Authors: Georges E Haddad; Lori J Saunders; Seth D Crosby; Maria Carles; Federica del Monte; Kindra King; Michael R Bristow; Francis G Spinale; Thomas E Macgillivray; Marc J Semigran; G William Dec; Steven A Williams; Roger J Hajjar; Judith K Gwathmey Journal: Physiol Genomics Date: 2008-02-26 Impact factor: 3.107
Authors: George Petrov; Elke Dworatzek; Tabea Marie Schulze; Michael Dandel; Georgios Kararigas; Shokufeh Mahmoodzadeh; Christoph Knosalla; Roland Hetzer; Vera Regitz-Zagrosek Journal: JACC Cardiovasc Imaging Date: 2014-10-08
Authors: Wenjia Bai; Wenzhe Shi; Antonio de Marvao; Timothy J W Dawes; Declan P O'Regan; Stuart A Cook; Daniel Rueckert Journal: Med Image Anal Date: 2015-09-01 Impact factor: 8.545
Authors: Antonio de Marvao; Timothy J W Dawes; Wenzhe Shi; Christopher Minas; Niall G Keenan; Tamara Diamond; Giuliana Durighel; Giovanni Montana; Daniel Rueckert; Stuart A Cook; Declan P O'Regan Journal: J Cardiovasc Magn Reson Date: 2014-02-03 Impact factor: 5.364
Authors: Anvesha Singh; Daniel C S Chan; John P Greenwood; Dana K Dawson; Piotr Sonecki; Kai Hogrefe; Damian J Kelly; Vijay Dhakshinamurthy; Chim C Lang; Jeffery P Khoo; David Sprigings; Richard P Steeds; Ruiqi Zhang; Ian Ford; Michael Jerosch-Herold; Jing Yang; Zhuyin Li; Leong L Ng; Gerry P McCann Journal: JACC Cardiovasc Imaging Date: 2017-12-13
Authors: Andreas Schuster; Torben Lange; Sören J Backhaus; Carolin Strohmeyer; Patricia C Boom; Jonas Matz; Johannes T Kowallick; Joachim Lotz; Michael Steinmetz; Shelby Kutty; Boris Bigalke; Matthias Gutberlet; Suzanne de Waha-Thiele; Steffen Desch; Gerd Hasenfuß; Holger Thiele; Thomas Stiermaier; Ingo Eitel Journal: J Am Heart Assoc Date: 2020-09-02 Impact factor: 5.501
Authors: Antonio de Marvao; Kathryn A McGurk; Sean L Zheng; Marjola Thanaj; Wenjia Bai; Jinming Duan; Carlo Biffi; Francesco Mazzarotto; Ben Statton; Timothy J W Dawes; Nicolò Savioli; Brian P Halliday; Xiao Xu; Rachel J Buchan; A John Baksi; Marina Quinlan; Paweł Tokarczuk; Upasana Tayal; Catherine Francis; Nicola Whiffin; Pantazis I Theotokis; Xiaolei Zhang; Mikyung Jang; Alaine Berry; Antonis Pantazis; Paul J R Barton; Daniel Rueckert; Sanjay K Prasad; Roddy Walsh; Carolyn Y Ho; Stuart A Cook; James S Ware; Declan P O'Regan Journal: J Am Coll Cardiol Date: 2021-09-14 Impact factor: 24.094