Key result
Lightweight 1D-CNN identifies arrhythmia with ~96% test accuracy and ultra-low latency.
Why the study?
Manual review of ambulatory ECG recordings is labor-intensive and prone to error, while existing automated deep learning models are often computationally expensive or miss rare pathological beats due to severe class imbalance.
Does a lightweight 3-stage 1D-CNN trained with hybrid resampling and Gaussian noise augmentation improve real-time five-class arrhythmia classification accuracy and sensitivity on ambulatory ECG recordings compared to existing baseline models?
Does a lightweight 3-stage 1D-CNN trained with hybrid resampling and Gaussian noise augmentation improve real-time five-class arrhythmia classification accuracy and sensitivity on ambulatory ECG recordings compared to existing baseline models?
A lightweight 3-stage 1D-CNN model trained with hybrid resampling and Gaussian noise augmentation achieves 95.5% accuracy and sub-millisecond (0.88 ms) inference latency on the MIT-BIH arrhythmia dataset, demonstrating computational feasibility for real-time edge deployment on wearable ECG monitors.
Supports edge-device arrhythmia detection feasibility; leaves open prospective clinical validation before practice adoption.
Cardiac arrhythmias serve as important biomarkers of cardiovascular disease and therefore require continuous, accurate and timely monitoring to enable clinical intervention. Ambulatory electrocardiogram (ECG) recordings produce large volumes of data, making manual review for diagnosis labor-intensive and subject to fatigue-induced error. Currently, automated deep learning solutions are often computationally expensive or fail due to severe class imbalance common in clinical datasets missing detection of rare but clinically important pathological beats. A lightweight one-dimensional Convolutional Neural Network (1D-CNN) for five-class arrhythmia classification was introduced in this study. For extreme skew in the epidemiological data, we create a hybrid resampling pipeline with additional synthetic Gaussian noise augmentation (σ=0.5) to apply at training time that regularizes decision boundaries against clinical noise. The three-stage convolutional model was tested on the independent unseen testing partition of the publicly available benchmark PhysioNet MIT-BIH Arrhythmia Database, which consists of 21,892 unaugmented cardiac beats. The framework demonstrated a total diagnostic test accuracy of 95.5%, with strong macro-averaged sensitivity across all AAMI categories, achieving 88.87, 92.05, and 88.27% for supraventricular ectopic, ventricular ectopic, and fusion beats respectively the proposed model achieves sub-millisecond inference latency while being deployed in real-time on wearable edge telemetry platforms by reducing parameters to 118,341. This method is clinically feasible and computationally efficient for continuous cardiac health monitoring.
No takes yet. Share an insight, caveat, or question.
Rahman et al. (2026) studied Cardiac arrhythmias (n=47). Lightweight 3-stage 1D-CNN with hybrid resampling and Gaussian noise augmentation (σ=0.5) vs. Established baseline ECG classification methods (e.g., Residual 1D-CNN, Deep 9-Layer 1D-CNN, LDA) was evaluated on Overall diagnostic classification accuracy across five AAMI heartbeat classes on the unseen test partition. A lightweight 3-stage 1D-CNN with hybrid resampling and noise augmentation achieved 95.5% test accuracy and 92.24% macro-sensitivity across five arrhythmia classes with 0.88 ms inference latency.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: