UCTECG-Net: Uncertainty-aware Convolution Transformer ECG Network for Arrhythmia Detection

TL;DR

UCTECG-Net is proposed, an uncertainty-aware hybrid architecture that combines one-dimensional convolutions and Transformer encoders to process raw ECG signals and their spectrograms jointly and provides more reliable and better-aligned uncertainty estimates than competing architectures, offering a stronger basis for risk-aware ECG decision support.

Abstract

Deep learning has improved automated electrocardiogram (ECG) classification, but limited insight into prediction reliability hinders its use in safety-critical settings. This paper proposes UCTECG-Net, an uncertainty-aware hybrid architecture that combines one-dimensional convolutions and Transformer encoders to process raw ECG signals and their spectrograms jointly. Evaluated on the MIT-BIH Arrhythmia and PTB Diagnostic datasets, UCTECG-Net outperforms LSTM, CNN1D, and Transformer baselines in terms of accuracy, precision, recall and F1 score, achieving up to 98.58% accuracy on MIT-BIH and 99.14% on PTB. To assess predictive reliability, we integrate three uncertainty quantification methods (Monte Carlo Dropout, Deep Ensembles, and Ensemble Monte Carlo Dropout) into all models and analyze their behavior using an uncertainty-aware confusion matrix and derived metrics. The results show that UCTECG-Net, particularly with Ensemble or EMCD, provides more reliable and better-aligned uncertainty estimates than competing architectures, offering a stronger basis for risk-aware ECG decision support.

Figures (8)

• Figure 1: Density plots of certainty values for correct and incorrect predictions, illustrating the model’s ability to separate confident correct outputs from uncertain errors.
• Figure 2: Architecture of the LSTM-based model
• Figure 3: Architecture of the 1D CNN model
• Figure 4: Architecture of the Transformer model
• Figure 5: Two samples of normal and abnormal ECG signals and their corresponding spectrograms. Subfigures \ref{['fig:normal_ecg']} and \ref{['fig:abnormal_ecg']} display time-domain ECG waveforms for normal and abnormal cardiac activity, respectively. Subfigures \ref{['fig:normal_spec']} and \ref{['fig:abnormal_spec']} illustrate their time–frequency representations, showing clear spectral differences between normal and abnormal patterns.