Accurate and reliable algorithms that can distinguish between true vs. false arrhythmia alarms can

Background and Objective: Differentiating wide complex tachycardia (WCT) is clinically critical yet challenging due to morphological similarities in electrocardiogram (ECG) signals between life-threatening ventricular tachycardia (VT) and supraventricular tachycardia with aberrancy (SVT-A). Misdiagnosis carries fatal risks. We propose a computationally efficient deep learning solution to improve diagnostic accuracy and provide model interpretability for clinical deployment. Methods: A novel lightweight parallel deep architecture is introduced. Each pipeline processes individual ECG leads using two 1D-CNN blocks to extract local features. Feature maps are concatenated across leads, followed by LSTM layers to capture temporal dependencies. Final classification employs fully connected layers. Explainability is achieved via Shapley Additive Explanations (SHAP) for local/global interpretation. The model was evaluated on a 35-subject ECG database using standard performance metrics. Results: The model achieved $95.63\%$ accuracy ($95\%$ CI: $93.07-98.19\%$), with sensitivity=$95.10\%$, specificity=$96.06\%$, and F1-score=$95.12\%$. It outperformed state-of-the-art methods in both accuracy and computational efficiency, requiring minimal CNN blocks per pipeline. SHAP analysis demonstrated clinically interpretable feature contributions. Conclusions: Our end-to-end framework delivers high-precision WCT classification with minimal computational overhead. The integration of SHAP enhances clinical trust by elucidating decision logic, supporting rapid, informed diagnosis. This approach shows significant promise for real-world ECG analysis tools.

Idiopathic ventricular arrhythmia (IVAs) is extra abnormal heartbeats disturbing the regular heart rhythm that can become fatal if left untreated. Cardiac catheter ablation is the standard approach to treat IVAs, however, a crucial prerequisite for the ablation is the localization of IVAs' origin. The current IVA localization techniques are invasive, rely on expert interpretation, or are inaccurate. In this study, we developed a new deep-learning algorithm that can automatically identify the origin of IVAs from ECG signals without the need for expert manual analysis. Our developed deep learning algorithm was comprised of a spatial fusion to extract the most informative features from multichannel ECG data, temporal modeling to capture the evolving pattern of the ECG time series, and an attention mechanism to weigh the most important temporal features and improve the model interpretability. The algorithm was validated on a 12-lead ECG dataset collected from 334 patients (230 females) who experienced IVA and successfully underwent a catheter ablation procedure that determined IVA's exact origins. The proposed method achieved an area under the curve of 93%, an accuracy of 94%, a sensitivity of 97%, a precision of 95%, and an F1 score of 96% in locating the origin of IVAs and outperformed existing automatic and semi-automatic algorithms. The proposed method shows promise toward automatic and noninvasive evaluation of IVA patients before cardiac catheter ablation.

The increasing availability of electrocardiogram (ECG) data has motivated the use of data-driven models for automating various clinical tasks based on ECG data. The development of subject-specific models are limited by the cost and difficulty of obtaining sufficient training data for each individual. The alternative of population model, however, faces challenges caused by the significant inter-subject variations within the ECG data. We address this challenge by investigating for the first time the problem of learning representations for clinically-informative variables while disentangling other factors of variations within the ECG data. In this work, we present a conditional variational autoencoder (VAE) to extract the subject-specific adjustment to the ECG data, conditioned on task-specific representations learned from a deterministic encoder. To encourage the representation for inter-subject variations to be independent from the task-specific representation, maximum mean discrepancy is used to match all the moments between the distributions learned by the VAE conditioning on the code from the deterministic encoder. The learning of the task-specific representation is regularized by a weak supervision in the form of contrastive regularization. We apply the proposed method to a novel yet important clinical task of classifying the origin of ventricular tachycardia (VT) into pre-defined segments, demonstrating the efficacy of the proposed method against the standard VAE.

The increasing availability of electrocardiogram (ECG) data has motivated the use of data-driven models for automating various clinical tasks based on ECG data. The development of subject-specific models are limited by the cost and difficulty of obtaining sufficient training data for each individual. The alternative of population model, however, faces challenges caused by the significant inter-subject variations within the ECG data. We address this challenge by investigating for the first time the problem of learning representations for clinically-informative variables while disentangling other factors of variations within the ECG data. In this work, we present a conditional variational autoencoder (VAE) to extract the subject-specific adjustment to the ECG data, conditioned on task-specific representations learned from a deterministic encoder. To encourage the representation for inter-subject variations to be independent from the task-specific representation, maximum mean discrepancy is used to match all the moments between the distributions learned by the VAE conditioning on the code from the deterministic encoder. The learning of the task-specific representation is regularized by a weak supervision in the form of contrastive regularization. We apply the proposed method to a novel yet important clinical task of classifying the origin of ventricular tachycardia (VT) into pre-defined segments, demonstrating the efficacy of the proposed method against the standard VAE.

In intensive care units (ICU), electrocardiogram (ECG) waveforms show diverse variationsunder different patients' physical conditions.In general, physicians can diagnose patients efficientlyby detecting any disorder of heart rate or rhythm and any change in the morphological pattern of ECG data,which contain underlying semantics.To help physicians better analyze ECG data in a fairly short time,it is essential to develop a novel method for mining semantics from ECG patterns.This paper is the very first time to characterize ECG patterns by using Prefix Scalable Pattern Tree (PSP-Tree).Comparing with similar currently existing methods, PSP-Tree can mine significant semantics,such as scalability, temporality and hierarchy over ECG patterns.We conduct extensive experiments on real ECG data set which are obtained from PhysioBank Community and Beijing No.3 People Hospital.The experiment results show that our method performs more feasibly and effectively than other related work.