What is the clinical evidence from this study?

Study design: Observational. Population: Atrial Fibrillation (n=78). Intervention: Deep learning (DL) classification model (1-D residual convolutional neural network) vs. Manual classification by cardiologists / Classic machine learning models. Primary outcome: Receiver operator characteristic area under curve (ROC AUC) for FaST classification in the testing cohort (95% CI 0.917-0.929).

July 30, 2021Open Access

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

Key Result

A novel deep learning model trained on raw unipolar electrograms accurately classified Focal Source and Trigger (FaST) sites during atrial fibrillation with an area under the curve of 0.923.

Study Design

Type

Observational (n=78)

Multicenter

Structured PICO

Does a deep learning model applied to raw unipolar EGMs accurately classify focal sources compared to manual classification by cardiologists in patients with atrial fibrillation?

Population

78 patients with atrial fibrillation from the Focal Source and Trigger (FaST) randomized controlled trial, providing 13,184 periodic unipolar EGMs (10,004 training, 3,180 testing).

Intervention

Deep learning (residual convolutional neural network) applied to raw unipolar EGMs to automate putative focal sources detection.

Comparator

Manual classification by cardiologists (FaST re-classification).

Outcome

Discrimination between FaST and non-FaST sites (measured by AUC, sensitivity, specificity, and accuracy).surrogate

A novel deep learning model trained on raw unipolar EGMs can accurately and automatically classify focal sources in atrial fibrillation, performing similarly to expert cardiologists.

Limitations

FaST sites were defined based on a single recording site and not the activation pattern from a multielectrode array.
EGMs were recorded for only 5 seconds, whereas longer recordings could increase sensitivity and specificity.
The study population and periodic unipolar EGM dataset is relatively small and sourced from a single center.
The prevalence of FaST was low, which can create class imbalance.
The DL model has inherent limitations in robustness and explainability.
The DL model was not used to guide real-time FaST ablation.

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.

Bookmark

View Full Paper