It can be difficult to tell if a human is hiding pain, let alone a cat. A study done in Israel, Brazil, and the United Kingdom used artificial intelligence (AI) to help recognize facial expressions that express pain in cats.
“Pain assessment and management in cats pose significant challenges, making them one of the most demanding species in this regard,” wrote the researchers. “There is currently a lack of consensus over key behavioral pain indicators. Moreover, population level visual differences in cat facial features based on pain status are extremely subtle.”
In a previous study, researchers analyzed 48 facial landmarks that indicate pain by using hand-picked single images and AI. This time, videos captured the information without interruption, with far greater accuracy.
“The presented pipeline reaches over 70% and 66% accuracy, respectively, in two different cat-pain datasets, outperforming previous automated landmark-based approaches using single frames under similar conditions, indicating that dynamics matter in cat pain recognition,” according to the study’s authors. The researchers hope that this work will eventually lead to improved app-based feline pain-recognition technology.
Martvel, G., et al. “Automated video-based pain recognition in cats using facial landmarks.” Scientific Reports 14, 28006 (2024).
