Heart and circulatory disease (also called cardiovascular diseases) are the commonest cause of death around the world. It is estimated that 1 in 3 people are living with cardiovascular disease and since 1997 the number of people living with cardiovascular disease around the world has doubled. More information about heart and circulatory disease can be found on the British Heart Foundation (BHF) [website](https://www.bhf.org.uk/-/media/files/for-professionals/research/heart-statistics/bhf-cvd-statistics-global-factsheet.pdf?rev=5ae062031a884f1d9a98d3f9ecd08804&hash=0670F13FCB5E0BF4F2CB149D24F794F3). 
 
For many people with suspected cardiovascular disease the first test that they have is an electrocardiogram (also called an electrokardiogram, ECG or EKG).  An ECG is a simple test which records the electrical activity of the heart, including its rate and rhythm. More information about ECGs can be found [here](https://www.bhf.org.uk/informationsupport/tests/ecg).

Changes in the ECG appearance can be used to detect a variety of heart diseases. During an ECG the electrical activity of the heart is recorded, and this is displayed graphically as a series of waves and intervals. Around the world access to digital tools varies, and frequently ECG images are displayed on a screen or printed out. Existing artificial intelligence/machine learning tools which have been developed for waveform ECG data may perform poorly on ECG images. Developing tools to automate the analysis of ECG images will improve patient care by helping to improve the speed and accuracy of diagnoses. 

The [British Heart Foundation Data Science Centre](https://www.hdruk.ac.uk/helping-with-health-data/bhf-data-science-centre/) is organising this challenge in collaboration with researchers from the [University of Edinburgh](https://ecci-cvs.github.io). The challenge aims to assess whether artificial intelligence/machine learning can be used to identify and classify disorders of heart rhythm from synthetic ECG images which have been created to incorporate common artefacts. 

This challenge will use the [GenECG dataset](https://www.medrxiv.org/content/10.1101/2023.12.27.23300581v1). This dataset contains synthetically generated ECG images which have been created to incorporate artefacts common on paper ECG images which are typically scanned or photographed. The wave form data to create this dataset is part of the [PTB-XL dataset](https://www.nature.com/articles/s41597-020-0495-6) containing diagnoses that have been adjudicated by two cardiologists. The GenECG dataset contains 21,799 ECG images which have passed a clinical Turing test where expert observers could not distinguish between synthetic and real ECGs. 

This challenge will focus on the identification of five important heart disease diagnoses. These include myocardial infarction, atrial fibrillation, hypertrophy, conduction disturbance, and ST/T change. Further information on these diagnoses can be found in the data section.

The top scoring teams will be invited to participate in a British Heart Foundation Data Science Centre webinar about the challenge and the best performing will be invited to present their results at the British Cardiovascular Society (BCS) meeting in June 2025. Participation in these activities will require code sharing.