Dataset Information

Deep Learning Classification of Unipolar Electrograms in Human Atrial Fibrillation: Application in Focal Source Mapping.

ABSTRACT: Focal sources are potential targets for atrial fibrillation (AF) catheter ablation, but they can be time-consuming and challenging to identify when unipolar electrograms (EGM) are numerous and complex. Our aim was to apply deep learning (DL) to raw unipolar EGMs in order to automate putative focal sources detection. We included 78 patients from the Focal Source and Trigger (FaST) randomized controlled trial that evaluated the efficacy of adjunctive FaST ablation compared to pulmonary vein isolation alone in reducing AF recurrence. FaST sites were identified based on manual classification of sustained periodic unipolar QS EGMs over 5-s. All periodic unipolar EGMs were divided into training (n = 10,004) and testing cohorts (n = 3,180). DL was developed using residual convolutional neural network to discriminate between FaST and non-FaST. A gradient-based method was applied to interpret the DL model. DL classified FaST with a receiver operator characteristic area under curve of 0.904 ± 0.010 (cross-validation) and 0.923 ± 0.003 (testing). At a prespecified sensitivity of 90%, the specificity and accuracy were 81.9 and 82.5%, respectively, in detecting FaST. DL had similar performance (sensitivity 78%, specificity 89%) to that of FaST re-classification by cardiologists (sensitivity 78%, specificity 79%). The gradient-based interpretation demonstrated accurate tracking of unipolar QS complexes by select DL convolutional layers. In conclusion, our novel DL model trained on raw unipolar EGMs allowed automated and accurate classification of FaST sites. Performance was similar to FaST re-classification by cardiologists. Future application of DL to classify FaST may improve the efficiency of real-time focal source detection for targeted AF ablation therapy.

SUBMITTER: Liao S

PROVIDER: S-EPMC8360838 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Background: Presence of left atrial low voltage substrate in bipolar voltage mapping is associated with increased arrhythmia recurrences following pulmonary vein isolation for atrial fibrillation (AF). Besides local myocardial fibrosis, bipolar voltage amplitudes may be influenced by inter-electrode spacing and bipole-to-wavefront-angle. It is unclear to what extent these impact low voltage areas (LVA) in the clinical setting. Alternatively, unipolar electrogram voltage is not affected by these factors but requires advanced filtering. Objectives: To assess the relationship between bipolar and unipolar voltage mapping in sinus rhythm (SR) and AF and identify if the electrogram recording mode affects the quantification and localization of LVA. Methods: Patients (n = 28, 66±7 years, 46% male, 82% persistent AF, 32% redo-procedures) underwent high-density (>1,200 sites, 20 ± 10 sites/cm2, using a 20-pole 2-6-2 mm-spaced Lasso) voltage mapping in SR and AF. Bipolar LVA were defined using four different thresholds described in literature: <0.5 and <1 mV in SR, <0.35 and <0.5 mV in AF. The optimal unipolar voltage threshold resulting in the highest agreement in both unipolar and bipolar mapping modes was determined. The impact of the inter-electrode distance (2 vs. 6 mm) on the correlation was assessed. Regional analysis was performed using an 11-segment left atrial model. Results: Patients had relevant bipolar LVA (23 ± 23 cm2 at <0.5 mV in SR and 42 ± 26 cm2 at <0.5 mV in AF). 90 ± 5% (in SR) and 85 ± 5% (AF) of mapped sites were concordantly classified as high or low voltage in both mapping modes. Discordant mapping sites located to the border zone of LVA. Bipolar voltage mapping using 2 vs. 6 mm inter-electrode distances increased the portion of matched mapping points by 4%. The unipolar thresholds (y) which resulted in a high spatial concordance can be calculated from the bipolar threshold (x) using following linear equations: y = 1.06x + 0.26mV (r = 0.994) for SR and y = 1.22x + 0.12mV (r = 0.998) for AF. Conclusion: Bipolar and unipolar voltage maps are highly correlated, in SR and AF. While bipole orientation and inter-electrode spacing are theoretical confounders, their impact is unlikely to be of clinical importance for localization of LVA, when mapping is performed at high density with a 20-polar Lasso catheter.

Project description:BACKGROUND:Electrogram-guided ablation procedures have been proposed as an alternative strategy consisting of either mapping and ablating focal sources or targeting complex fractionated electrograms in atrial fibrillation (AF). However, the incomplete understanding of the mechanism of AF makes difficult the decision of detecting the target sites. To date, feature extraction from electrograms is carried out mostly based on the time-domain morphology analysis and non-linear features. However, their combination has been reported to achieve better performance. Besides, most of the inferring approaches applied for identifying the levels of fractionation are supervised, which lack of an objective description of fractionation. This aspect complicates their application on EGM-guided ablation procedures. METHODS:This work proposes a semi-supervised clustering method of four levels of fractionation. In particular, we make use of the spectral clustering that groups a set of widely used features extracted from atrial electrograms. We also introduce a new atrial-deflection-based feature to quantify the fractionated activity. Further, based on the sequential forward selection, we find the optimal subset that provides the highest performance in terms of the cluster validation. The method is tested on external validation of a labeled database. The generalization ability of the proposed training approach is tested to aid semi-supervised learning on unlabeled dataset associated with anatomical information recorded from three patients. RESULTS:A joint set of four extracted features, based on two time-domain morphology analysis and two non-linear dynamics, are selected. To discriminate between four considered levels of fractionation, validation on a labeled database performs a suitable accuracy (77.6 %). Results show a congruence value of internal validation index among tested patients that is enough to reconstruct the patterns over the atria to located critical sites with the benefit of avoiding previous manual classification of AF types. CONCLUSIONS:To the best knowledge of the authors, this is the first work reporting semi-supervised clustering for distinguishing patterns in fractionated electrograms. The proposed methodology provides high performance for the detection of unknown patterns associated with critical EGM morphologies. Particularly, obtained results of semi-supervised training show the advantage of demanding fewer labeled data and less training time without significantly compromising accuracy. This paper introduces a new method, providing an objective scheme that enables electro-physiologist to recognize the diverse EGM morphologies reliably.

Dataset Information

Deep Learning Classification of Unipolar Electrograms in Human Atrial Fibrillation: Application in Focal Source Mapping.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets