You can access the full article here.
Today I was chatting with a client about whether or not her horse might suffer from some level of hind guy dysfunction. The mare is on Succeed (a supplement which helps ease some types of hind gut dysfunction), and the owner feels that the mare is more comfortable. The difficulty is that at the moment, the veterinary world has limited tools available to investigate and diagnose hindgut dysfunction. It would be so much easier if our horses could just tell us when they’re hurting, and when they’re feeling better!
That’s what a team of researchers are looking into. There have been several studies over the past 10 years into the ‘equine pain face’, or how to tell when a horse is hurting. It’s hard enough to tell in humans, let alone in horses. And it’s known that the more suffering you see, the less well you’re able to evaluate it, which makes it even more difficult for veterinary professionals to recognise pain and discomfort in their patients.
In the human field, technology plays a big part in being able to recognise pain, and this team hopes that in the future, the same might apply to horses.
Facial activity can convey valid information about the experience of pain in a horse. However, scoring of pain in horses based on facial activity is still in its infancy and accurate scoring can only be performed by trained assessors. Pain in humans can now be recognized reliably from video footage of faces, using computer vision and machine learning. We examine the hurdles in applying these technologies to horses and suggest two general approaches to automatic horse pain recognition. The first approach involves automatically detecting objectively defined facial expression aspects that do not involve any human judgment of what the expression “means”. Automated classification of pain expressions can then be done according to a rule-based system since the facial expression aspects are defined with this information in mind. The other involves training very flexible machine learning methods with raw videos of horses with known true pain status. The upside of this approach is that the system has access to all the information in the video without engineered intermediate methods that have filtered out most of the variation. However, a large challenge is that large datasets with reliable pain annotation are required. We have obtained promising results from both approaches.
Andersen, P.H.; Broomé, S.; Rashid, M.; Lundblad, J.; Ask, K.; Li, Z.; Hernlund, E.; Rhodin, M.; Kjellström, H. Towards Machine Recognition of Facial Expressions of Pain in Horses. Animals 2021, 11, 1643. https://doi.org/10.3390/ani11061643
You can access the full article here.
© Sue Palmer, The Horse Physio, 2021
Treating your horse with care, connection, curiosity and compassion
