Challenge Open Access

Will Two Do? Varying Dimensions in Electrocardiography: the PhysioNet - Computing in Cardiology Challenge 2021

Matthew Reyna Nadi Sadr Erick Andres Perez Alday Chengyu Liu Salman Seyedi Amit Shah Gari Clifford

Published: Jan. 31, 2021. Version: 1.0.1 <View latest version>

When using this resource, please cite: (show more options)
Reyna, M., Sadr, N., Perez Alday, E. A., Liu, C., Seyedi, S., Shah, A., & Clifford, G. (2021). Will Two Do? Varying Dimensions in Electrocardiography: the PhysioNet - Computing in Cardiology Challenge 2021 (version 1.0.1). PhysioNet.

Additionally, please cite the original publication:

Perez Alday EA, Gu A, Shah AJ, Robichaux C, Wong AI, Liu C, Liu F, Rad AB, Elola A, Seyedi S, Li Q, Sharma A, Clifford GD, Reyna MA. Classification of 12-lead ECGs: the PhysioNet/Computing in Cardiology Challenge 2020. Physiol Meas. 2020 Nov 11.

Please include the standard citation for PhysioNet: (show more options)
Goldberger, A., Amaral, L., Glass, L., Hausdorff, J., Ivanov, P. C., Mark, R., ... & Stanley, H. E. (2000). PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals. Circulation [Online]. 101 (23), pp. e215–e220.


The electrocardiogram (ECG) is a non-invasive representation of the electrical activity of the heart. Although the twelve-lead ECG is the standard diagnostic screening system for many cardiological issues, the limited accessibility of twelve-lead ECG devices provides a rationale for smaller, lower-cost, and easier to use devices. While single-lead ECGs are limiting, reduced-lead ECG systems hold promise, with evidence that subsets of the standard twelve leads can capture useful information and can even be comparable to twelve-lead ECGs in some limited contexts. In 2017 we challenged the public to classify AF from a single-lead ECG, and in 2020 we challenged the public to diagnose a much larger number of cardiac problems using twelve-lead recordings. However, there is limited evidence to demonstrate the utility of reduced-lead ECGs for capturing a wide range of diagnostic information.

In this year's Challenge, we ask the following question: 'Will two do?' This year's Challenge builds on last year's Challenge, which asked participants to classify cardiac abnormalities from twelve-lead ECGs. We are asking you to build an algorithm that can classify cardiac abnormalities from either twelve-lead, six-lead, three-lead, and two-lead ECGs. We will test each algorithm on databases of twelve-lead, six-lead, three-lead, and two-lead ECGs, and the differences in performances of the algorithms on these databases will reveal the utility of reduced-lead ECGs in comparison to standard twelve-lead EGCs.


The goal of the 2021 Challenge is to identify clinical diagnoses from twelve-lead, six-lead (I, II, III, aVL, aVR, and aVF), three-lead (I, II, and V2) and two-lead (II and V5) ECG recordings.

We ask participants to design and implement a working, open-source algorithm that, based only on the provided twelve-lead ECG recordings and routine demographic data, can automatically identify any cardiac abnormalities present in the recording. We will award prizes for the top performing twelve-lead algorithm and the top performing two-lead and six-lead algorithms.

For more details and updates about the objectives of this year’s Challenge, please see This webpage will be updated after the end of the Challenge.


We invite participants from academia, industry, and elsewhere to participate in the Challenge. Like previous years, the Challenge has both an unofficial phase and an official phase than run over the course of several months, culminating with Computing in Cardiology on 12-15 September 2021. For more details and updates about participating in this year’s Challenge, including important rules and deadlines, please see

Data Description

We have obtained twelve-lead ECG recordings and labels from diverse sources for the public training and hidden test sets for the Challenge. We have posted multiple databases of twelve-lead ECG recordings and labels as public training sets and sequester databases of twelve-lead, six-lead, and three-lead, and two-lead ECG recordings as private test sets. For more details about the data for this year’s Challenge, please see


To better capture the importance of correctly identifying cardiac abnormalities, we defined an evaluation metric to score participant algorithms by assigning different weights to different classes and classification errors. For more details about the evaluation metric for this year’s Challenge, please see

Conflicts of Interest

The authors have no conflicts of interest to declare.


Access Policy:
Anyone can access the files, as long as they conform to the terms of the specified license.

License (for files):
Creative Commons Attribution 4.0 International Public License

Corresponding Author
You must be logged in to view the contact information.


Total uncompressed size: 14.6 KB.

Access the files

Folder Navigation: <base>
Name Size Modified
LICENSE.txt (download) 14.5 KB 2021-01-30
SHA256SUMS.txt (download) 77 B 2021-01-31