Manar D Samad1, Gregory J Wehner2, Mohammad R Arbabshirani1, Linyuan Jing1, Andrew J Powell3, Tal Geva3, Christopher M Haggerty1, Brandon K Fornwalt1,4. 1. Department of Imaging Science and Innovation, Center for Health Research, Geisinger Clinic, 100 North Academy Avenue, Danville, 17822-4400 PA, USA. 2. Department of Biomedical Engineering, University of Kentucky, 522 Robotics and Manufacturing Building, Lexington, 40506-0108 KY, USA. 3. Department of Cardiology, Boston Children's Hospital, 300 Longwood Ave, Boston, 02115 MA, USA. 4. Department of Radiology, Geisinger, 100 North Academy Ave, Danville, 17822 PA, USA.
Abstract
Aims: Previous studies using regression analyses have failed to identify which patients with repaired tetralogy of Fallot (rTOF) are at risk for deterioration in ventricular size and function despite using common clinical and cardiac function parameters as well as cardiac mechanics (strain and dyssynchrony). This study used a machine learning pipeline to comprehensively investigate the predictive value of the baseline variables derived from cardiac magnetic resonance (CMR) imaging and provide models for identifying patients at risk for deterioration. Methods and results: Longitudinal deterioration for 153 patients with rTOF was categorized as 'none', 'minor', or 'major' based on changes in ventricular size and ejection fraction between two CMR scans at least 6 months apart (median 2.7 years). Baseline variables were measured at the time of the first CMR. An exhaustive variable search with a support vector machine classifier and five-fold cross-validation was used to predict deterioration and identify the most useful variables. For predicting any deterioration (minor or major) vs. no deterioration, the mean area under the curve (AUC) was 0.82 ± 0.06. For predicting major deterioration vs. minor or no deterioration, the AUC was 0.77 ± 0.07. Baseline left ventricular (LV) ejection fraction, LV circumferential strain, and pulmonary regurgitation were most useful for achieving accurate predictions. Conclusion: For the prediction of deterioration in patients with rTOF, a machine learning pipeline uncovered the utility of baseline variables that was previously lost to regression analyses. The predictive models may be useful for planning early interventions in patients with high risk.
Aims: Previous studies using regression analyses have failed to identify which patients with repaired tetralogy of Fallot (rTOF) are at risk for deterioration in ventricular size and function despite using common clinical and cardiac function parameters as well as cardiac mechanics (strain and dyssynchrony). This study used a machine learning pipeline to comprehensively investigate the predictive value of the baseline variables derived from cardiac magnetic resonance (CMR) imaging and provide models for identifying patients at risk for deterioration. Methods and results: Longitudinal deterioration for 153 patients with rTOF was categorized as 'none', 'minor', or 'major' based on changes in ventricular size and ejection fraction between two CMR scans at least 6 months apart (median 2.7 years). Baseline variables were measured at the time of the first CMR. An exhaustive variable search with a support vector machine classifier and five-fold cross-validation was used to predict deterioration and identify the most useful variables. For predicting any deterioration (minor or major) vs. no deterioration, the mean area under the curve (AUC) was 0.82 ± 0.06. For predicting major deterioration vs. minor or no deterioration, the AUC was 0.77 ± 0.07. Baseline left ventricular (LV) ejection fraction, LV circumferential strain, and pulmonary regurgitation were most useful for achieving accurate predictions. Conclusion: For the prediction of deterioration in patients with rTOF, a machine learning pipeline uncovered the utility of baseline variables that was previously lost to regression analyses. The predictive models may be useful for planning early interventions in patients with high risk.
Authors: Tal Geva; Bryan M Sandweiss; Kimberlee Gauvreau; James E Lock; Andrew J Powell Journal: J Am Coll Cardiol Date: 2004-03-17 Impact factor: 24.094
Authors: A L Knauth; K Gauvreau; A J Powell; M J Landzberg; E P Walsh; J E Lock; P J del Nido; T Geva Journal: Heart Date: 2006-11-29 Impact factor: 5.994
Authors: Sukrit Narula; Khader Shameer; Alaa Mabrouk Salem Omar; Joel T Dudley; Partho P Sengupta Journal: J Am Coll Cardiol Date: 2016-11-29 Impact factor: 24.094
Authors: Jamil A Aboulhosn; Gentian Lluri; Michelle Z Gurvitz; Paul Khairy; François-Pierre Mongeon; Joseph Kay; Anne Marie Valente; Michael G Earing; Alexander R Opotowsky; George Lui; Deborah R Gersony; Stephen Cook; John Child; Jennifer Ting; Gary Webb; Michael Landzberg; Craig S Broberg Journal: Can J Cardiol Date: 2013-01-28 Impact factor: 5.223
Authors: Michael Huntgeburth; Ingo Germund; Lianne M Geerdink; Narayanswami Sreeram; Floris E A Udink Ten Cate Journal: Cardiovasc Diagn Ther Date: 2019-10