Latest News And Breaking Headlines

Exploring the biometric data that could predict racehorse injury

horse race

Credit: Pixabay/CC0 public domain

Imagine having the knowledge to prevent a catastrophic event ahead of time. In horse racing this could be a possibility.

New research examined whether the same systems used to help gamblers choose a winning racehorse can provide the data needed to protect that same racehorse from injury.

A problem with measuring

Efforts to date in predicting injuries in racehorses have not been much better than the flip of a coin. In the past, horse racing injuries were treated as a binary outcome: a horse is injured or uninjured.

But injuries, largely due to bone damage, start gradually.

An injury can develop over weeks or months unless it is due to a traumatic event (such as a horse hitting a fence), so it rarely happens the day it is sighted. We know this because most catastrophic injuries in racehorses have demonstrated pre-existing bone damage.

This damage accumulates during training and racing over time due to repetitive strain on the musculoskeletal system. With each step taken by a horse galloping at a moderate speed, loads of up to four tons have been measured on the surface of the ball joint.

Bot can withstand only a limited number of these loads, and the steps taken at higher speeds produce greater loads.

Often the first detection of an injury is when the horse gives up or shows signs of lameness, indicating that the threshold for bone damage has already been reached.

But instead of waiting for that injury to become apparent, we realized there was a need for a way to measure horses’ response to the training and race load.

The dawn of the data-driven era

So, what if there was a way to measure injury onset using already established data collection systems? As it happened, there is.

It all started in 2010 when Tasmania’s premier racing authority, Tasracing, teamed up with StrideMASTER, a nascent technology company developing training monitoring systems for the racing industry.

They developed one of the first race day timing systems using GPS and accurate motion sensor data. The original purpose of this data was for real-time sectional timing and positional data from racehorses then intended for use as a broadcast and deployment product.

I had worked with Tasracing before and in 2016, on my return to Australia, we got back together.

As Tasracing prides itself on being data-driven, it is this approach that gave us a potential solution.

With access to biometrics, such as racehorse speed, stride length and stride frequency, we now have the tools to measure changes in horses’ racing careers that can signal injury before it’s too late.

A horse that slows down is a horse to watch

Our research primarily linked StrideMASTER’s biometric data with other field information and veterinary findings from Tasracing between 2011 and 2016.

Using a statistical method not previously used in this setting, we first modeled the changes in stride characteristics during successive race starts, and then modeled the number of race starts before an injury occurred.

Finally, the two models were integrated into what is called a “joint model” to determine whether observed changes in stride characteristics predicted injury.

And they did.

For horses well into their careers, those who sustained an injury during a race start slowed their race speed and shortened their stride length more quickly around six races beforehand.

My colleague, Professor Chris Whitton, noted that while we expected to see changes in speed and stride in races that would lead to injury, the fact that we saw those changes so long ago is surprising. Yes, we thought we might change one or two races, but not six – that’s pretty amazing.

For horses that have suffered an injury earlier in their career – if we only look at the first few races where there is still insufficient data on their normal stride characteristics – additional monitoring during training may be needed to predict these early career injuries.

A horse’s risk of injury increased by 18 percent when the speed was reduced by 0.1 meters per second, or by 11 percent when the stride length was shortened by just 10 centimeters in the last part of each race.

And our findings even took into account factors that affect speed and stride, such as race distance and track conditions.

While these changes may sound small, in an individual horse with its own unique stride, they are a sign that something is not right.

This may be because they cannot withstand the workload, are in pain, or otherwise physiologically compensate for the accumulated bone damage.

It is at this point that veterinary advice should be sought.

Established systems used in meaningful ways

Our study, published in the Veterinary magazine for horsesis just the beginning of how data-driven research could improve wellbeing and safety in the racing industry using new and meaningful ways to reuse data.

Our findings also demonstrate the enormous potential for identifying and preventing injuries in racehorses before they become catastrophic.

Racing authorities should lead the way and push for the wider implementation of motion sensor technology that can track both training and racing. This would cover the elements we’re still unclear about, such as whether the same slowing of speed and shortening of stride also occurs during training.

With other jurisdictions now using similar systems that collect biometrics, there will be more information, leading to refined algorithms, improved predictions and, ultimately, greater safety for horses.

Male jockeys have no more influence on racehorse performance than female jockeys

More information:
Adelene SM Wong et al, Changes in speed and stride characteristics of whole blood during consecutive races and their association with musculoskeletal injuries, Veterinary magazine for horses (2022). DOI: 10.1111/evj.13581

Provided by the University of Melbourne

Quote: Exploring the Biometrics That Can Predict Racehorse Injury (June 2022, June 20), retrieved June 20, 2022 from https://phys.org/news/2022-06-exploring-biometric-racehorse-injury.html

This document is copyrighted. Other than fair dealing for personal study or research, nothing may be reproduced without written permission. The content is provided for informational purposes only.

This website uses cookies to improve your experience. We'll assume you're ok with this, but you can opt-out if you wish. Accept Read More