A Systematic Review of ECG Arrhythmia Classification: Adherence to Standards, Fair Evaluation, and Embedded Feasibility

The classification of electrocardiogram (ECG) signals is crucial for early detection of arrhythmias and other cardiac conditions. However, despite advances in machine learning, many studies fail to follow standardization protocols, leading to inconsistencies in performance evaluation and real-world applicability. Additionally, hardware constraints essential for practical deployment, such as in pacemakers, Holter monitors, and wearable ECG patches, are often overlooked. Since real-world impact depends on feasibility in resource-constrained devices, ensuring efficient deployment is critical for continuous monitoring. This review systematically analyzes ECG classification studies published between 2017 and 2024, focusing on those adhering to the E3C (Embedded, Clinical, and Comparative Criteria), which include inter-patient paradigm implementation, compliance with Association for the Advancement of Medical Instrumentation (AAMI) recommendations, and model feasibility for embedded systems. While many studies report high accuracy, few properly consider patient-independent partitioning and hardware limitations. We identify state-of-the-art methods meeting E3C criteria and conduct a comparative analysis of accuracy, inference time, energy consumption, and memory usage. Finally, we propose standardized reporting practices to ensure fair comparisons and practical applicability of ECG classification models. By addressing these gaps, this study aims to guide future research toward more robust and clinically viable ECG classification systems.

• Publication year

  2025

• Venue

  arXiv.org

• Publication date

  2025-03-10

• Fields of study

  Medicine, Computer Science, Engineering

• Identifiers
  DOI 10.48550/arXiv.2503.07276arXiv 2503.07276
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Atrial Fibrillation Detection From Electrocardiogram Signal on Low Power Microcontroller

  2024cited by this paper
• A lightweight hybrid CNN-LSTM explainable model for ECG-based arrhythmia detection

  2024cited by this paper
• Advanced detection of cardiac arrhythmias using a three-stage CBD filter and a multi-scale approach in a combined deep learning model

  2024cited by this paper
• MSGformer: A multi-scale grid transformer network for 12-lead ECG arrhythmia detection

  2024cited by this paper
• ECG arrhythmia detection in an inter-patient setting using Fourier decomposition and machine learning.

  2024cited by this paper
• A novel imbalanced dataset mitigation method and ECG classification model based on combined 1D_CBAM-autoencoder and lightweight CNN model

  2024cited by this paper
• Arrhythmia detection in inter-patient ECG signals using entropy rate features and RR intervals with CNN architecture

  2024cited by this paper
• Binarized spiking neural network optimized with momentum search algorithm for fetal arrhythmia detection and classification from ECG signals

  2024cited by this paper
• An Energy-Efficient ECG Processor Based on HDWT and a Hybrid Classifier for Arrhythmia Detection

  2023cited by this paper
• An enhanced ResNet-50 deep learning model for arrhythmia detection using electrocardiogram biomedical indicators

  2023cited by this paper
• A review of on-device machine learning for IoT: An energy perspective

  2023cited by this paper
• Deep Representation Learning With Sample Generation and Augmented Attention Module for Imbalanced ECG Classification

  2023cited by this paper
• A configurable hardware-efficient ECG classification inference engine based on CNN for mobile healthcare applications

  2023cited by this paper
• IM-ECG: An interpretable framework for arrhythmia detection using multi-lead ECG

  2023cited by this paper
• A Low-Power ECG Processor ASIC Based on an Artificial Neural Network for Arrhythmia Detection

  2023cited by this paper
• Evaluation of uncertainty quantification methods in multi-label classification: A case study with automatic diagnosis of electrocardiogram

  2023cited by this paper
• Multimodal multi-instance learning for long-term ECG classification

  2023cited by this paper
• Hardware implementation of 1D-CNN architecture for ECG arrhythmia classification

  2023influential reference
• A Tiny Matched Filter-Based CNN for Inter-Patient ECG Classification and Arrhythmia Detection at the Edge

  2023influential reference
• A Multi-View Multi-Scale Neural Network for Multi-Label ECG Classification

  2023cited by this paper
• Fuzz-ClustNet: Coupled fuzzy clustering and deep neural networks for Arrhythmia detection from ECG signals

  2023cited by this paper
• Generative adversarial network with transformer generator for boosting ECG classification

  2023cited by this paper
• Lightweight Shufflenet Based CNN for Arrhythmia Classification

  2022cited by this paper
• An automatic arrhythmia classification model based on improved Marine Predators Algorithm and Convolutions Neural Networks

  2022cited by this paper
• Electrocardiogram classification using TSST-based spectrogram and ConViT

  2022cited by this paper
• An Efficient Unstructured Sparse Convolutional Neural Network Accelerator for Wearable ECG Classification Device

  2022influential reference
• Lightweight Multireceptive Field CNN for 12-Lead ECG Signal Classification

  2022cited by this paper
• A 2.66 µW Clinician-Like Cardiac Arrhythmia Watchdog Based on P-QRS-T for Wearable Applications

  2022cited by this paper
• LightX3ECG: A Lightweight and eXplainable Deep Learning System for 3-lead Electrocardiogram Classification

  2022influential reference
• Snippet Policy Network V2: Knee-Guided Neuroevolution for Multi-Lead ECG Early Classification

  2022cited by this paper
• A Neuromorphic Processing System With Spike-Driven SNN Processor for Wearable ECG Classification

  2022cited by this paper
• On-Device Training Under 256KB Memory

  2022cited by this paper
• An Ultra-Energy-Efficient and High Accuracy ECG Classification Processor With SNN Inference Assisted by On-Chip ANN Learning

  2022influential reference
• Accurate ECG Classification Based on Spiking Neural Network and Attentional Mechanism for Real-Time Implementation on Personal Portable Devices

  2022influential reference
• Efficient hardware design of a deep U-net model for pixel-level ECG classification in healthcare device

  2022influential reference
• Deep Learning Models for Arrhythmia Detection in IoT Healthcare Applications

  2022cited by this paper
• BeatClass: A Sustainable ECG Classification System in IoT-Based eHealth

  2022cited by this paper
• A Scalable and Transferable Federated Learning System for Classifying Healthcare Sensor Data

  2022cited by this paper
• Global ECG Classification by Self-Operational Neural Networks With Feature Injection

  2022cited by this paper
• A transformer-based deep neural network for arrhythmia detection using continuous ECG signals

  2022cited by this paper
• Homecare-Oriented ECG Diagnosis With Large-Scale Deep Neural Network for Continuous Monitoring on Embedded Devices

  2022influential reference
• ECG-based real-time arrhythmia monitoring using quantized deep neural networks: A feasibility study

  2022influential reference
• Enhancing dynamic ECG heartbeat classification with lightweight transformer model

  2022cited by this paper
• A Novel Interpretable Method Based on Dual-Level Attentional Deep Neural Network for Actual Multilabel Arrhythmia Detection

  2022cited by this paper
• Arrhythmia classification of LSTM autoencoder based on time series anomaly detection

  2022cited by this paper
• Unsupervised semantic-aware adaptive feature fusion network for arrhythmia detection

  2022cited by this paper
• Explainable Deep Learning-Based Approach for Multilabel Classification of Electrocardiogram

  2021cited by this paper
• Automated Atrial Fibrillation Detection using a Hybrid CNN-LSTM Network on Imbalanced ECG Datasets

  2021cited by this paper
• Energy efficient ECG classification with spiking neural network

  2021influential reference
• ECG arrhythmia classification by using a recurrence plot and convolutional neural network

  2021cited by this paper
• Automatic ECG Classification Using Continuous Wavelet Transform and Convolutional Neural Network

  2021cited by this paper
• A Hybrid Deep CNN Model for Abnormal Arrhythmia Detection Based on Cardiac ECG Signal

  2021cited by this paper
• Arrhythmia classification from single-lead ECG signals using the inter-patient paradigm

  2021cited by this paper
• A Proof-of-Concept of Ultra-Edge Smart IoT Sensor: A Continuous and Lightweight Arrhythmia Monitoring Approach

  2021cited by this paper
• Transfer learning for ECG classification

  2021cited by this paper
• From ECG signals to images: a transformation based approach for deep learning

  2021cited by this paper
• Automated ECG classification using a non-local convolutional block attention module

  2021cited by this paper
• Self-supervised representation learning from 12-lead ECG data

  2021cited by this paper
• Designing ECG Monitoring Healthcare System with Federated Transfer Learning and Explainable AI

  2021cited by this paper
• Efficient Hardware Architecture of Convolutional Neural Network for ECG Classification in Wearable Healthcare Device

  2021cited by this paper
• A White Paper on Neural Network Quantization

  2021cited by this paper
• Arrhythmic Heartbeat Classification Using 2D Convolutional Neural Networks

  2021cited by this paper
• Interpatient ECG Heartbeat Classification with an Adversarial Convolutional Neural Network

  2021cited by this paper
• Sequence to Sequence ECG Cardiac Rhythm Classification Using Convolutional Recurrent Neural Networks

  2021cited by this paper
• Automated arrhythmia detection with homeomorphically irreducible tree technique using more than 10, 000 individual subject ECG records

  2021cited by this paper
• A 2.63 μW ECG Processor With Adaptive Arrhythmia Detection and Data Compression for Implantable Cardiac Monitoring Device

  2021cited by this paper
• Robust Heartbeat Classification for Wearable Single-Lead ECG via Extreme Gradient Boosting

  2021cited by this paper
• Real-Time Patient-Specific ECG Classification by 1D Self-Operational Neural Networks

  2021cited by this paper
• SqueezeNet

  2021cited by this paper
• Hybrid feature fusion for classification optimization of short ECG segment in IoT based intelligent healthcare system

  2021cited by this paper
• A Novel FrWT Based Arrhythmia Detection in ECG Signal Using YWARA and PCA

  2021cited by this paper
• A Hybrid Lightweight 1D CNN-LSTM Architecture for Automated ECG Beat-Wise Classification

  2021cited by this paper
• Application of deep learning techniques for heartbeats detection using ECG signals-analysis and review

  2020cited by this paper
• Deep Multi-Scale Fusion Neural Network for Multi-Class Arrhythmia Detection

  2020cited by this paper
• A Multitier Deep Learning Model for Arrhythmia Detection

  2020cited by this paper
• A Lightweight Deep Learning Model for Fast Electrocardiographic Beats Classification With a Wearable Cardiac Monitor: Development and Validation Study

  2020cited by this paper
• A Wearable Electrocardiogram Telemonitoring System for Atrial Fibrillation Detection

  2020cited by this paper
• An IoT and Fog Computing-Based Monitoring System for Cardiovascular Patients with Automatic ECG Classification Using Deep Neural Networks

  2020cited by this paper
• Automated heartbeat classification based on deep neural network with multiple input layers

  2020cited by this paper
• Inter-Patient ECG Classification With Symbolic Representations and Multi-Perspective Convolutional Neural Networks

  2020cited by this paper
• A framework for cardiac arrhythmia detection from IoT-based ECGs

  2020cited by this paper
• Generalization of Convolutional Neural Networks for ECG Classification Using Generative Adversarial Networks

  2020cited by this paper
• A high-precision arrhythmia classification method based on dual fully connected neural network

  2020cited by this paper
• Multi-class Arrhythmia detection from 12-lead varied-length ECG using Attention-based Time-Incremental Convolutional Neural Network

  2020cited by this paper
• What is the State of Neural Network Pruning?

  2020cited by this paper
• Semi-supervised learning for ECG classification without patient-specific labeled data

  2020cited by this paper
• HEARTBEAT CLASSIFICATION ALGORITHM BASED ON ONE-DIMENSIONAL CONVOLUTION NEURAL NETWORK

  2020cited by this paper
• PTB-XL, a large publicly available electrocardiography dataset

  2020influential reference
• Electrocardiogram heartbeat classification based on a deep convolutional neural network and focal loss

  2020cited by this paper
• ECG-based multi-class arrhythmia detection using spatio-temporal attention-based convolutional recurrent neural network

  2020cited by this paper
• Deep learning models for electrocardiograms are susceptible to adversarial attack

  2020cited by this paper
• Multi-information fusion neural networks for arrhythmia automatic detection

  2020cited by this paper
• Combining deep neural networks and engineered features for cardiac arrhythmia detection from ECG recordings

  2019cited by this paper
• Automated beat-wise arrhythmia diagnosis using modified U-net on extended electrocardiographic recordings with heterogeneous arrhythmia types

  2019cited by this paper
• Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network

  2019cited by this paper
• An Improved Convolutional Neural Network Based Approach for Automated Heartbeat Classification

  2019cited by this paper
• Thin MobileNet: An Enhanced MobileNet Architecture

  2019cited by this paper
• A Neural Network-Based ECG Classification Processor With Exploitation of Heartbeat Similarity

  2019cited by this paper
• Automatic detection of arrhythmia from imbalanced ECG database using CNN model with SMOTE

  2019cited by this paper
• On-Device Machine Learning: An Algorithms and Learning Theory Perspective

  2019influential reference

• Wearable Sensing Systems for Multi-Modal Body Fluid Monitoring: Sensing-Combination Strategy, Platform-Integration Mechanism, and Data-Processing Pattern

  2026cites this paper
• RhythmBERT: A Self-Supervised Language Model Based on Latent Representations of ECG Waveforms for Heart Disease Detection

  2026cites this paper
• Optimized ECG Processing System using FPGA with Polyphase Filter for Arrhythmia Classification

  2025cites this paper
• FoundationalECGNet: A Lightweight Foundational Model for ECG-based Multitask Cardiac Analysis

  2025cites this paper
• Exploring the Efficacy of Deep Residual Networks and CNN-ELM for Arrhythmia Classification in Lead II ECG

  2025cites this paper
• MAK-Net: A Multi-Scale Attentive Kolmogorov–Arnold Network with BiGRU for Imbalanced ECG Arrhythmia Classification

  2025cites this paper
• On-Demand Cardiac Digital Twins: A Case Study on DevOps workflows for Digital Twin Platforms

  2025cites this paper
• ECGNET-H: A Hybrid CNN-GRU Model for Real-Time ECG Signal Classification

  2025cites this paper
• ECG Heartbeat Classification Using CNN Autoencoder Feature Extraction and Attention-Augmented BiLSTM Classifier

  2025cites this paper
• Ecg Arrhythmia Classification Using Spatial Representations and Convolutional Neural Networks

  2025cites this paper