Julie K Shade1,2, Rheeda L Ali1, Dante Basile1,2, Dan Popescu1,3, Tauseef Akhtar4, Joseph E Marine4, David D Spragg4, Hugh Calkins1,4, Natalia A Trayanova1,2,5. 1. Alliance for Cardiovascular Diagnostic and Treatment Innovation (J.K.S., R.L.A., D.B., D.P., H.C., N.A.T.), Johns Hopkins University, Baltimore, MD. 2. Department of Biomedical Engineering (J.K.S., D.B., N.A.T.), Johns Hopkins University, Baltimore, MD. 3. Department of Applied Math and Statistics (D.P.), Johns Hopkins University, Baltimore, MD. 4. Division of Cardiology, Department of Medicine (T.A., J.E.M., D.D.S., H.C.), Johns Hopkins University School of Medicine, Baltimore, MD. 5. Department of Medicine (N.A.T.), Johns Hopkins University School of Medicine, Baltimore, MD.
Abstract
BACKGROUND: Pulmonary vein isolation (PVI) is an effective treatment strategy for patients with atrial fibrillation (AF), but many experience AF recurrence and require repeat ablation procedures. The goal of this study was to develop and evaluate a methodology that combines machine learning (ML) and personalized computational modeling to predict, before PVI, which patients are most likely to experience AF recurrence after PVI. METHODS: This single-center retrospective proof-of-concept study included 32 patients with documented paroxysmal AF who underwent PVI and had preprocedural late gadolinium enhanced magnetic resonance imaging. For each patient, a personalized computational model of the left atrium simulated AF induction via rapid pacing. Features were derived from pre-PVI late gadolinium enhanced magnetic resonance images and from results of simulations of AF induction. The most predictive features were used as input to a quadratic discriminant analysis ML classifier, which was trained, optimized, and evaluated with 10-fold nested cross-validation to predict the probability of AF recurrence post-PVI. RESULTS: In our cohort, the ML classifier predicted probability of AF recurrence with an average validation sensitivity and specificity of 82% and 89%, respectively, and a validation area under the curve of 0.82. Dissecting the relative contributions of simulations of AF induction and raw images to the predictive capability of the ML classifier, we found that when only features from simulations of AF induction were used to train the ML classifier, its performance remained similar (validation area under the curve, 0.81). However, when only features extracted from raw images were used for training, the validation area under the curve significantly decreased (0.47). CONCLUSIONS: ML and personalized computational modeling can be used together to accurately predict, using only pre-PVI late gadolinium enhanced magnetic resonance imaging scans as input, whether a patient is likely to experience AF recurrence following PVI, even when the patient cohort is small.
BACKGROUND: Pulmonary vein isolation (PVI) is an effective treatment strategy for patients with atrial fibrillation (AF), but many experience AF recurrence and require repeat ablation procedures. The goal of this study was to develop and evaluate a methodology that combines machine learning (ML) and personalized computational modeling to predict, before PVI, which patients are most likely to experience AF recurrence after PVI. METHODS: This single-center retrospective proof-of-concept study included 32 patients with documented paroxysmal AF who underwent PVI and had preprocedural late gadolinium enhanced magnetic resonance imaging. For each patient, a personalized computational model of the left atrium simulated AF induction via rapid pacing. Features were derived from pre-PVI late gadolinium enhanced magnetic resonance images and from results of simulations of AF induction. The most predictive features were used as input to a quadratic discriminant analysis ML classifier, which was trained, optimized, and evaluated with 10-fold nested cross-validation to predict the probability of AF recurrence post-PVI. RESULTS: In our cohort, the ML classifier predicted probability of AF recurrence with an average validation sensitivity and specificity of 82% and 89%, respectively, and a validation area under the curve of 0.82. Dissecting the relative contributions of simulations of AF induction and raw images to the predictive capability of the ML classifier, we found that when only features from simulations of AF induction were used to train the ML classifier, its performance remained similar (validation area under the curve, 0.81). However, when only features extracted from raw images were used for training, the validation area under the curve significantly decreased (0.47). CONCLUSIONS: ML and personalized computational modeling can be used together to accurately predict, using only pre-PVI late gadolinium enhanced magnetic resonance imaging scans as input, whether a patient is likely to experience AF recurrence following PVI, even when the patient cohort is small.
Authors: Sohail Zahid; Hubert Cochet; Patrick M Boyle; Erica L Schwarz; Kaitlyn N Whyte; Edward J Vigmond; Rémi Dubois; Mélèze Hocini; Michel Haïssaguerre; Pierre Jaïs; Natalia A Trayanova Journal: Cardiovasc Res Date: 2016-04-07 Impact factor: 10.787
Authors: Jan Budzianowski; Jarosław Hiczkiewicz; Paweł Burchardt; Konrad Pieszko; Janusz Rzeźniczak; Paweł Budzianowski; Katarzyna Korybalska Journal: Heart Vessels Date: 2018-08-23 Impact factor: 2.037
Authors: Ryan P O'Hara; Edem Binka; Adityo Prakosa; Stefan L Zimmerman; Mark J Cartoski; M Roselle Abraham; Dai-Yin Lu; Patrick M Boyle; Natalia A Trayanova Journal: Elife Date: 2022-01-25 Impact factor: 8.140
Authors: Caroline H Roney; Charles Sillett; John Whitaker; Jose Alonso Solis Lemus; Iain Sim; Irum Kotadia; Mark O'Neill; Steven E Williams; Steven A Niederer Journal: Eur Heart J Cardiovasc Imaging Date: 2021-12-18 Impact factor: 6.875
Authors: Sofia Monaci; Karli Gillette; Esther Puyol-Antón; Ronak Rajani; Gernot Plank; Andrew King; Martin Bishop Journal: Front Physiol Date: 2021-07-01 Impact factor: 4.566
Authors: Jordi Heijman; Henry Sutanto; Harry J G M Crijns; Stanley Nattel; Natalia A Trayanova Journal: Cardiovasc Res Date: 2021-06-16 Impact factor: 10.787