What is the clinical evidence from this study?

Study design: Other. Population: ECG compression (n=46). Intervention: Deep learning-based adaptive ARIMA model. Primary outcome: Compression ratio (CR) and percentage root-mean-square difference (PRD%).

What question did this study set out to answer?

This research aims to develop a lossless ECG compression technique using deep learning to facilitate remote cardiac monitoring.

February 28, 2026

Deep Learning Based Approach for Lossless ECG Compression

Key Result

A deep learning-based adaptive ARIMA model for lossless ECG compression achieved a mean compression ratio of 41.51 and PRD of 0.209%, outperforming previously reported methods.

Key Points

This research aims to develop a lossless ECG compression technique using deep learning to facilitate remote cardiac monitoring.
Raw ECG signals were preprocessed and denoised to create beat-cells for compression.
An adaptive ARIMA model was employed, optimized with a deep learning-based autoencoder and MLPNN regressor.
Particle swarm optimization was used to improve model predictions and tuning.
Achieved a mean compression ratio of 41.51 and a prediction residual distortion of 0.209%.
No clinical feature deviations were observed in reconstructed ECG beats.
Outperformed previously published methods for ECG compression.

Structured PICO

Does a deep learning-based adaptive ARIMA model improve lossless ECG compression quality?

Population

46 records of mitdb under PhysioNet, including 10 major abnormal beats (H, A, V, P, L, R, a, f, F and j)

Intervention

Deep-learning method via an adaptive autoregressive integrated moving average (ARIMA) model for lossless ECG compression

Comparator

Prior published ECG compression methods

Outcome

Compression quality measured by mean Compression Ratio (CR) and Percentage Root-mean-square Difference (PRD%)surrogate

A novel deep learning-based adaptive ARIMA model achieves high-quality lossless ECG compression, potentially improving real-time telemonitoring applications.

Abstract

OBJECTIVE: Tele-monitoring is a useful platform for remote monitoring of cardiac patients, where compression plays a significant role in reducing the link burden and memory utilization of the source device. This paper describes a new approach for lossless ECG compression based on a deep-learning method via an adaptive autoregressive integrated moving average (ARIMA) model. METHODS: Raw ECG signals were denoised and preprocessed to generate beat-cells for further processing. The ARIMA model uses the individual cardiac cycles to generate model parameters, which are then compressed. In this research, the optimal model hyperparameters were predicted by a deep autoencoder followed by a multilayer perceptron neural network (MLPNN) regressor combination. The predictor was tuned offline via particle swarm optimization (PSO), which produced the reference data for MLPNN tuning. RESULTS: The technique uses 46 records of mitdb under PhysioNet, including 10 major abnormal beats: H, A, V, P, L, R, a, f, F and j. Because of the adaptive nature, compression quality is high with negligible loss. No deviations in the clinical features of the reconstructed beats are found. The mean CR and PRD% values were 41.51 and 0.209%, respectively, which are superior to those reported in published research on ECG compression. CONCLUSION: The proposed adaptive ECG compression model can be useful for real-time telemonitoring applications, efficient storage and transmission of streamlined data of critical patients under continuous monitoring.

Mark Helpful

Bookmark

Relay