What does this research mean for the field?

The xECGArch model achieved 94.1%-95.3% accuracy in detecting atrial fibrillation and 1st-degree AV block from ECGs, demonstrating reliable performance and clinical interpretability. Novelty: ClaimNovelty.NOVEL_FINDING. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

This research aims to enhance the interpretability and explainability of deep learning models for ECG analysis, focusing on detecting specific cardiac conditions.

February 8, 2026

Explainable and interpretable AI visualises self-learned clinically relevant ECG characteristics of rhythm and morphology paving the way for trustworthy diagnostic support

Key Result

xECGArch combining rhythm and morphology models detected AFib, AFlut, and AVB-I from single-lead ECGs with 91.1%-95.3% accuracy, improving interpretability.

Key Points

This research aims to enhance the interpretability and explainability of deep learning models for ECG analysis, focusing on detecting specific cardiac conditions.
Developed xECGArch, a self-learning deep learning architecture for ECG analysis.
Trained using lead II ECGs from five public databases with balanced pathological and normal sinus rhythm data.
Utilized deep Taylor decomposition for model explanation generation to ensure interpretability.
Implemented 5-fold cross-validation for training and testing the model on ECG datasets.
Achieved 92.4%−95.0% accuracy for AVB-I and AFib, improving to 94.1%−95.3% with xECGArch.
AFlut detection achieved 91.1% accuracy, though with a lower precision of 85.5%.
The rhythm model emphasized QRS complexes for AFib, while the morphology model highlighted features like fibrillatory waves.

Structured PICO

Does the xECGArch deep learning architecture accurately detect and provide interpretable explanations for AFib, AFlut, and AVB-I from single-lead ECGs?

Population

Lead II ECGs from 5 public databases (Chapman-Shaoxing/Ningbo, CPSC2018, Georgia, PTB, PTB-XL) containing 90% pathological and 10% normal sinus rhythm ECGs (n(AFib)=n(non-AFib)=4,927, n(AFlut)=n(non-AFlut)=8,374, n(AVB-I)=n(non-AVB-I)=3,530)

Intervention

xECGArch (explainable deep learning architecture combining rhythm and morphology models)

Outcome

Detection accuracy for atrial fibrillation, atrial flutter, and 1st-degree AV block, and interpretability of model explanationssurrogate

An explainable deep learning architecture combining rhythm and morphology models accurately detects arrhythmias from single-lead ECGs while providing clinically interpretable explanations.

Main Result

Absolute Event Rate: 0% vs 0%

Abstract

Abstract Introduction Artificial Intelligence (AI), particularly deep learning (DL), has demonstrated high performance in diagnostic issues, including the detection of cardiovascular diseases (CVDs) from the electrocardiogram (ECG). In long-term monitoring, AI approaches can improve early detection of CVDs and increase the chance of detecting paroxysmal cases. However, due to their black-box nature, the decision making of DL lacks explainability and their self-learned features lack interpretability. Nevertheless, both are essential for physicians to assess AI-based diagnostic recommendations, which is a prerequisite for clinical integration. Purpose We demonstrate the capabilities of the self-learning DL architecture for explainable ECG analysis (xECGArch) in detecting atrial fibrillation (AFib), atrial flutter (AFlut), and 1st-degree AV block (AVB-I). xECGArch combines 2 models, with one focusing on rhythm and the other on morphology. Methods from explainable AI (xAI) generate explanations for the individual decisions of both models. Their fused representation (xFuseMap) enables interpretability in line with clinical knowledge. Methods xECGArch was trained to detect AFib, AFlut, and AVB-I using lead II ECGs from 5 public databases (Chapman-Shaoxing/Ningbo, CPSC2018, Georgia, PTB, PTB-XL). The CVD data was balanced with reference ECGs, containing 90% pathological and 10% normal sinus rhythm ECGs (n(AFib)=n(non-AFib)=4,927, n(AFlut)=n(non-AFlut)=8,374, n(AVB-I)=n(non-AVB-I)=3,530). We used the middle 10 s of each ECG, discarding shorter ECGs. The training was conducted on randomly selected 90% of the ECGs in a 5-fold cross-validation with testing on the remaining ECGs. Model explanations were generated using deep Taylor decomposition, the most reliable in a systematic comparison of 13 xAI methods. Results The rhythm and morphology models achieved 92.4%−95.0% accuracy for AVB-I and AFib, increasing to 94.1%−95.3% using xECGArch (Tab. 1). For AFlut, xECGArch reached 91.1% accuracy caused by a lower precision of 85.5%. The model explanations (Fig. 1) confirm that the rhythm model focuses on QRS complexes, especially for AFib detection, while the morphology model focuses on clinically relevant morphology features, like fibrillatory or flutter waves and the absence of P waves in AFib, or the PQ duration in AVB-I. Conclusions Both rhythm and morphology models reliably detect AFib, AFlut, and AVB-I from single-lead ECGs, competing with state-of-the-art methods. Their combination in xECGArch further improves performance. xECGArch is inspired by the medical reading of ECGs by considering rhythm and morphology characteristics and is therefore interpretable by design. The explanations align with diagnostic criteria for AFib, AFlut, and AVB-I. With high accuracy and improved interpretability, xECGArch provides a trustworthy method for automated ECG analysis and meets the prerequisite for integration into clinical routine for diagnostic support.Tab. 1:Datset and model performance Fig. 1:Model explanations

KI fragen

Bookmark

Cite This Study

Hammer et al. (Sat,) reported a other. xECGArch combining rhythm and morphology models detected AFib, AFlut, and AVB-I from single-lead ECGs with 91.1%-95.3% accuracy, improving interpretability.

synapsesocial.com/papers/698828770fc35cd7a8848037 https://doi.org/https://doi.org/10.1093/eurheartj/ehaf784.4412

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

KI fragen

Bookmark