A quick heart trace taken during a warm-up trot could identify racehorses at risk of cardiac arrhythmias during high-intensity exercise, according to a new study led by the University of Surrey.

The screening method analyses short, routine electrocardiogram (ECG) recordings that could be used to help prevent cardiac events in otherwise healthy horses, where no obvious signs of arrhythmia have been detected.

Researchers from the University of Surrey, the University of Minnesota, Rossdales Veterinary Surgeons and Wisconsin Equine Clinic have utilised an AI-system (previously developed at the University of Surrey) that measures any “disorderliness” of the heart’s electrical signal. The team’s AI can distinguish horses likely to develop premature beats at peak exercise using only short ECG recordings taken at rest or light exercise – when heart rates sit between 60 and 100 beats per minute.

Published in Scientific Reports, the study recorded ambulatory ECGs from 110 US-based Thoroughbred and Standardbred racehorses during routine training. The team used 60-second ECG segments from each of the horses and tested six different algorithms across multiple heart rate ranges and signal features. The best-performing algorithm achieved an area under the curve of 0.86 – well above the 0.5 that would indicate chance – in distinguishing horses with exercising arrhythmias from those without.

Critically, the test was shown to be highly effective at ruling out horses that are not at risk. Horses that screen positive could then be referred for a full exercising ECG to confirm the type and severity of any arrhythmia.

Professor Kamalan Jeevaratnam, Head of School of Veterinary Medicine at the University of Surrey and co-corresponding author of the study, said:

“What this work shows is that we can pick up warning signs for more impactful rhythm disturbances from a simple, short heart recording taken before the horse ever reaches peak intensity. Instead of waiting for an arrhythmia to appear, we can flag at-risk horses during a routine warm-up and support closer monitoring of these horses during exercise.”

Cardiac arrhythmias are extremely common in athletic horses. Most are harmless, but in some severe cases, they can lead to poor athletic performance, collapse or life-threatening cardiac episodes. The challenge is identifying which horses are at risk.

Currently, this involves monitoring ECGs during high-intensity exercise, but earlier identification of those horses at greater risk can support more informed monitoring and management – helping to improve safety and welfare on and off the racecourse.

The study builds on previous work by the Jeevaratnam group demonstrating that similar complexity-based ECG analysis can detect paroxysmal atrial fibrillation – the most common sustained arrhythmia in both horses and humans. The two methods work at different heart rate ranges, meaning vets could potentially screen for both conditions within a single diagnostic session conducted at low exercise intensity.

The research was funded by the Grayson Jockey Club Foundation and the Engineering and Physical Sciences Research Council Impact Acceleration Award to the University of Surrey.