October 13, 2019Journal of Healthcare EngineeringOpen Access

An Effective LSTM Recurrent Network to Detect Arrhythmia on Imbalanced ECG Dataset

View Full Paper

Ask AI

Bookmark

Why the study?

Complex variations and heavily imbalanced category distribution of ECG beats challenge computer-aided arrhythmia diagnosis systems.

Structured PICO

Population

ECG beats from the MIT-BIH arrhythmia database

Intervention

Long short-term memory (LSTM) recurrence network model with focal loss (FL)

Outcome

ECG beat classification/arrhythmia detection performance on imbalanced datasets

An LSTM network with focal loss effectively addresses category imbalance in ECG beat classification for computer-aided arrhythmia diagnosis.

Implication

May support AI tools for imbalanced ECG classification; leaves open prospective clinical validation.

Abstract

To reduce the high mortality rate from cardiovascular disease (CVD), the electrocardiogram (ECG) beat plays a significant role in computer-aided arrhythmia diagnosis systems. However, the complex variations and imbalance of ECG beats make this a challenging issue. Since ECG beat data exist in heavily imbalanced category, an effective long short-term memory (LSTM) recurrence network model with focal loss (FL) is proposed. For this purpose, the LSTM network can disentangle the timing features in complex ECG signals, while the FL is used to resolve the category imbalance by downweighting easily identified normal ECG examples. The advantages of the proposed network have been verified in the MIT-BIH arrhythmia database. Experimental results show that the LSTM network with FL achieved a reliable solution to the problem of imbalanced datasets in ECG beat classification and was not sensitive to quality of ECG signals. The proposed method can be deployed in telemedicine scenarios to assist cardiologists into more accurately and objectively diagnosing ECG signals.