Scientists have developed an AI that can recognize pain in animals based on their facial expressions
Researchers at Tel Hai University in Kiryat Shmona in the Galilee, together with their colleagues, have developed an artificial intelligence model capable of recognizing pain in animals based on changes in their facial expressions.
The model analyzes the animal’s facial expressions and maps the resulting data onto a 3D model of its muzzle.
This approach allows for anatomical accuracy in interpreting facial expressions, even if the animal is moving or the camera angle changes.
The technology was tested on three independent datasets. It demonstrated a high level of accuracy in detecting postoperative, inflammatory, orthopedic, and acute pain.
The developers believe the system could serve as a tool for more objectively assessing the condition of animals that cannot communicate their pain on their own.
In the future, the technology could potentially be adapted for use in human medicine.
In particular, the technology could help assess the condition of newborns, patients in intensive care, and people with dementia and neurological disorders who have difficulty communicating their pain on their own.
Previously, scientists created the first viable bacteriophages whose genomes were entirely designed by generative artificial intelligence. The new viruses were able to destroy strains of E. coli that were resistant to natural bacteriophages. At the same time, researchers warn that while the technology opens up new possibilities for medicine, it also raises serious questions regarding biosafety.
Neuroscientists at the Friedrich Miescher Institute for Biomedical Research in Switzerland have discovered that memories can remain in the brain even after they cease to influence behavior. The researchers have termed these traces “silent.”
