Self-Attention LSTM-FCN model for arrhythmia classification and uncertainty assessment.

This paper presents ArrhyMon , a self-attention-based LSTM-FCN model for arrhythmia classification from ECG signal inputs. ArrhyMon targets to detect and classify six different types of arrhythmia apart from normal ECG patterns. To the best of our knowledge, ArrhyMon is the first end-to-end classification model that successfully targets the classification of six detailed arrhythmia types and compared to previous work does not require additional preprocessing and/or feature extraction operations separate from the classification model. ArrhyMon 's deep learning model is designed to capture and exploit both global and local features embedded in ECG sequences by integrating fully convolutional network (FCN) layers and a self-attention-based long and short-term memory (LSTM) architecture. Moreover, to enhance its practicality, ArrhyMon incorporates a deep ensemble-based uncertainty model that generates a confidence-level measure for each classification result. We evaluate ArrhyMon 's effectiveness using three publicly available arrhythmia datasets (i.e., MIT-BIH, Physionet Cardiology Challenge 2017 and 2020/2021) to show that ArrhyMon achieves state-of-the-art classification performance (average accuracy 99.63%), and that confidence measures show close correlation with subjective diagnosis made from practitioners. • We propose a fully end-to-end arrhythmia classification system, ArrhyMon, based on a self-attention-based LSTM-FCN deep learning architecture. • ArrhyMon adopts a deep ensemble-based approach to self-quantify uncertainty levels for its classification results. As a result, ArrhyMon offers per-classification output confidence information to assist clinical decision-making processes. • Using representative ECG datasets, we show that ArrhyMon achieves state-of-the-art performance in classifying six arrhythmia types and distinguishing them from normal ECG patterns. Furthermore, we show that the epistemic uncertainty of ArrhyMon's classification results are reliable for clinical use [ABSTRACT FROM AUTHOR]