CardioMark: An open-source MATLAB toolbox for ECG annotation for machine learning and academic research
With the growing use of machine learning, especially deep learning, in ECG analysis, access to well-annotated databases has become increasingly important. However, most public ECG databases lack detailed QRS morphology labels or complete 12-lead ECG recordings. Manual annotation remains essential but is time-consuming, subjective, and often requires multiple reviewers. CardioMark is an open-access MATLAB toolbox that simplifies and improves ECG annotation through an intuitive graphical interface. It supports multi-observer input, session-based work, and easy export for machine learning applications. Its modular design allows customization for various ECG tasks, making it a useful tool for both research and education in clinical cardiology.
Authors
- James C. Lacefield (ORCID: https://orcid.org/0000-0002-9438-9189)
- Vijay Parsa (ORCID: https://orcid.org/0000-0002-4305-8347)
- Samir Abdel-Rahman (ORCID: https://orcid.org/0000-0002-0224-643X)
- Pavel Antiperovitch
- Anthony Tang
Institutions
- Western University (CA)
- Robarts Clinical Trials (CA)
Publication Details
- Journal
- SoftwareX
- Published
- 2025-10-25
- DOI
- https://doi.org/10.1016/j.softx.2025.102423
- Primary Topic
- ECG Monitoring and Analysis
- Type
- article
- Field-Weighted Citation Impact
- 0.00