Artificial intelligence recognizes pain on the face of goats
Recognizing pain in some animals is not easy. A research team has therefore developed an AI that can identify pain in goats.
It's hard to see the pain in goats.
(Image: Astrid Gast / Shutterstock.com)
A research team from the College of Veterinary Medicine at the University of Florida has succeeded in using artificial intelligence (AI) to identify pain in goats based on their faces. The researchers believe that the system can also be applied to other animals and humans who are unable to communicate verbally.
The assessment of whether an animal is in pain or not is often subjective and based on years of experience. However, not every animal is equally good at seeing or hearing whether it feels pain or not. The researchers wanted to find out whether there are clear features in the faces of goats that indicate pain. They published their findings in the study "Automated acute pain prediction in domestic goats using deep learning-based models on video-recordings" in Scientific Reports.
The scientists created an AI model that was trained with videos of the faces of goats that were both in pain and not in pain. The model was trained with videos of a total of 40 goats. The researchers then tested the system on several goats. The system achieved a recognition performance of up to 80 percent in identifying goats in pain.
Videos by heise
Can also be applied to other animal species and humans
The researchers assume that their AI system can also be applied to other animal species, in which it is difficult to recognize whether they are experiencing pain. With appropriate training, the AI model could also be applied to them and generally to all patients who are unable to communicate verbally –, including certain humans.
"If we solve the problem in animals, we can also solve the problem in children and other non-verbal patients," said Ludovica Chiavaccini, Professor of Anesthesiology at the College of Veterinary Medicine at the University of Florida.
The researchers also developed a pain scale for goats based on the research results. Such a scale did not previously exist. However, the scale determined cannot currently be generalized, as the underlying data was only collected for male goats during castration.
(olb)
