Skip to content
MATLAB example classifier for the PhysioNet/Computing in Cardiology Challenge 2020
MATLAB HTML C JavaScript Shell Prolog Other
Branch: master
Clone or download

Latest commit

Latest commit 10dfac7 Feb 28, 2020


Type Name Latest commit message Commit time
Failed to load latest commit information.
Tools Add files via upload Feb 24, 2020
LICENSE.txt Update Feb 25, 2020
driver.m Add files via upload Feb 24, 2020
finalized_model.mat Add files via upload Feb 28, 2020
get_12ECG_features.m Add files via upload Feb 24, 2020

Example MATLAB classifier for the PhysioNet/CinC Challenge 2020


This classifier uses three scripts:

  • run_12ECG_classifier.m makes classifications on 12-Leads ECG data. Add your prediction code to the run_12ECG_classifier function. load_12ECG_model.m loads model weights, etc. for making classifications. To reduce your code's run time, add any code to the load_12ECG_model function that you only need to run once, such as loading weights for your model.
  • extract the features from the clinical time-series data. This script and function are optional, but we have included it as an example. It calls all the functions inside the Tools folder
  • driver.m calls load_12ECG_model once and run_12ECG_classifier many times. It also performs all file input and output. Do not edit this script -- or we will be unable to evaluate your submission.

Check the code in these files for the input and output formats for the load_12ECG_model and run_12ECG_classifier functions.


You can run this classifier code by starting MATLAB and running

driver(input_directory, output_directory)

where input_directory is a directory for input data files and output_directory is a directory for output classification files. The PhysioNet/CinC 2020 webpage provides a training database with data files and a description of the contents and structure of these files.


The driver.m, get_12ECG_score.m, and get_12ECG_features.m scripts need to be in the base or root path of the Github repository. If they are inside a subfolder, then the submission will fail.


“The baseline classifiers are simple logistic regression models. They use global electrical heterogeneity (GEH) computed from the WFDB signal file (the .mat file) with the [PhysioNet Cardiovascular Signal Toolbox] and demographic data taken directly from the WFDB header file (the .hea file) as predictors.

The code uses three main toolboxes:

You can’t perform that action at this time.