Skip to content
DraconiticResearch
Search Sources API
194,230 studies31 sourcesUpdated 18 min ago
Peer-reviewedCC BYResearch on Biomedical Engineering

A systematic review of ECG arrhythmia classification: embedded feasibility, adherence to standards, and fair evaluation

  • Guilherme A. L. Silva1
  • Pedro H. L. Silva2
  • Gladston J. P. Moreira2
  • Vander L. S. Freitas
  • Jadson Castro Gertrudes2
  • Eduardo Jose da Silva Luz
  1. 1Postgraduate Program in Computer Science, Federal University of Ouro Preto, Ouro Preto, Brazil
  2. 2Computing Department, Federal University of Ouro Preto, Ouro Preto, Brazil
Open at sourcePDFDOICite

Abstract

Background The classification of electrocardiogram (ECG) signals is essential for early arrhythmia detection. However, many studies fail to follow standardization protocols, leading to inconsistencies in performance evaluation and real-world applicability. Additionally, hardware constraints crucial for deployment in pacemakers, Holter monitors, and wearable ECG patches are often overlooked, limiting practical use in resource-constrained environments. Objective This review systematically analyzes ECG classification research published between 2017 and 2024, focusing on studies that meet the E3C (Embedded, Clinical, and Comparative Criteria). Methods These criteria include adherence to the inter-patient paradigm, compliance with AAMI recommendations, and evaluation of model feasibility for embedded deployment. We conduct a comparative analysis of accuracy, inference time, energy consumption, and memory usage, identifying state-of-the-art methods that align with the E3C. Results Our findings show that while many models achieve high accuracy, few address key constraints like patient-independent data partitioning and hardware limitations. Conclusions Finally, we propose standardized performance reporting to enable fair comparisons and enhance real-world applicability. By addressing these gaps, this study aims to guide research toward more robust and clinically viable ECG classification models.

Related

  1. A hybrid quantum algorithm for multi-resolution arrhythmia classification
    Melvin Yashnil Ramkhelawan, Santoso Wibowo, Srimannarayana Grandhi +1
    Scientific ReportsPeer-reviewedCC BY-NC-ND 4.0Full textCardiovascular medicineCrossref
  2. ArrhythmiaVision: resource-conscious deep learning models with visual explanations for ECG arrhythmia classification
    Z. Tanveer Baig, Sidra Nasir, Rizwan Ahmed Khan +1
    The Journal of SupercomputingPeer-reviewedLicence not statedFull text11 citedCardiovascular medicineOpenAlex
  3. Deep learning optimisation for cardiology: Neural Architecture Search-driven arrhythmia classification with electrocardiograms
    Erik Vanegas Müller, Arese Joe-Oshodi, Abhirup Banerjee +1
    PLOS OnePeer-reviewedCC BY 4.0Materials & polymersCardiovascular medicinePLOS
  4. Feasibility, Safety, Adherence, and Functional Outcomes of a Mobile Application-Facilitated, Unsupervised Remote Cardiac Rehabilitation Program with Exercise Intensity Optimization: A Single-Arm Clinical Trial
    Kazuhiro Terashima, Ruka Kanazawa, Zhehao Dai +6
    Journal of Clinical MedicinePeer-reviewedCC BY 4.0General medicineCrossref
  5. Process evaluation of the INTENSE study aimed at improving adherence to oral diabetes and/or hypertension medication in people with type 2 diabetes
    M. Langendoen-Gort, D. Bhattacharya, H. Al-Jabr +5
    medRxivPreprintAll rights reservedFull textGeneral medicinemedRxiv

Cite

BibTeXRIS
BibTeX
@article{silva2026systematic,
  title = {{A systematic review of ECG arrhythmia classification: embedded feasibility, adherence to standards, and fair evaluation}},
  author = {Guilherme A. L. Silva and Pedro H. L. Silva and Gladston J. P. Moreira and Vander L. S. Freitas and Jadson Castro Gertrudes and Eduardo Jose da Silva Luz},
  journal = {Research on Biomedical Engineering},
  year = {2026},
  month = jul,
  doi = {10.1007/s42600-026-00485-z},
  url = {https://doi.org/10.1007/s42600-026-00485-z},
  note = {CC BY},
}
RIS
TY  - JOUR
TI  - A systematic review of ECG arrhythmia classification: embedded feasibility, adherence to standards, and fair evaluation
AU  - Guilherme A. L. Silva
AU  - Pedro H. L. Silva
AU  - Gladston J. P. Moreira
AU  - Vander L. S. Freitas
AU  - Jadson Castro Gertrudes
AU  - Eduardo Jose da Silva Luz
PY  - 2026
DA  - 2026/07/17
JO  - Research on Biomedical Engineering
DO  - 10.1007/s42600-026-00485-z
UR  - https://doi.org/10.1007/s42600-026-00485-z
AB  - Background The classification of electrocardiogram (ECG) signals is essential for early arrhythmia detection. However, many studies fail to follow standardization protocols, leading to inconsistencies in performance evaluation and real-world applicability. Additionally, hardware constraints crucial for deployment in pacemakers, Holter monitors, and wearable ECG patches are often overlooked, limiting practical use in resource-constrained environments. Objective This review systematically analyzes ECG classification research published between 2017 and 2024, focusing on studies that meet the E3C (Embedded, Clinical, and Comparative Criteria). Methods These criteria include adherence to the inter-patient paradigm, compliance with AAMI recommendations, and evaluation of model feasibility for embedded deployment. We conduct a comparative analysis of accuracy, inference time, energy consumption, and memory usage, identifying state-of-the-art methods that align with the E3C. Results Our findings show that while many models achieve high accuracy, few address key constraints like patient-independent data partitioning and hardware limitations. Conclusions Finally, we propose standardized performance reporting to enable fair comparisons and enhance real-world applicability. By addressing these gaps, this study aims to guide research toward more robust and clinically viable ECG classification models.
SN  - 1517-3151
SN  - 1984-7742
SN  - 1984-7750
SN  - 2446-4732
SN  - 2446-4740
ER  -