DistantNews
Support us
🇮🇱 Israel /Technology

Straight from the horse’s mouth: Israeli AI helps detect when horses are in pain

From Jerusalem Post · () English

Translated from English and summarized by DistantNews. Read the original for the full story.

At a glance

In-depth Documents & data Context piece
  • Israeli researchers and international collaborators developed SHIC-XE, an AI framework that detects signs of pain in horses through video analysis.
  • The system provides explanations that remain stable across viewpoints, addressing a weakness in conventional visual heat-map methods.
  • The researchers say the approach could eventually help assess pain in nonverbal patients, including newborns, sedated intensive-care patients and people with neurological conditions.

A new Israeli artificial-intelligence system cannot make a horse speak, but it may help humans understand when the animal is suffering. SHIC-XE analyzes video for signs of equine pain and explains its decisions using stable, anatomically consistent markers.

Dr. Marcelo Feighelstein, who heads the Artificial Intelligence Systems Engineering Program at Tel Hai University of Kiryat Shmona in the Galilee, led the project. The collaboration included Prof. Anna Zamansky and the Tech4Animals Lab, Prof. Ilan Shimshoni of the University of Haifa, students from the Technion, and researchers from universities in Bern, Milan, São Paulo and Newcastle.

The research, published in the International Journal of Computer Vision, addresses a problem shared by veterinary and human medicine: recognizing pain in people and animals unable to communicate what they feel. Potential applications include newborns, sedated and ventilated intensive-care patients, and people affected by dementia, stroke, progressive aphasia, head injuries, tumors or serious infections. The system could also support analysis of neurological movement disorders and clinical or surgical video.

Traditional AI explanations often use saliency maps, or visual heat maps that highlight areas considered important by a model. In video, however, movement by the subject and camera can make those explanations unstable and flickering. The researchers said SHIC-XE allows AI-generated explanations to be quantitatively compared with expert assessments for the first time.

Feighelstein pointed to the consequences of poor pain recognition in medicine. “For a long time, doctors thought that newborns didn’t feel pain, so they didn’t take measures to prevent their suffering,” he said. The team described the new method as a step toward AI systems that can be trusted in clinical and healthcare settings.

For a long time, doctors thought that newborns didn’t feel pain, so they didn’t take measures to prevent their suffering.

· Marcelo FeighelsteinThe researcher highlighted the broader medical importance of recognizing pain in patients who cannot communicate.
About this summary

Originally published by Jerusalem Post in English. Translated, summarized, and contextualized automatically by DistantNews, with a note on how the source frames the story. Not individually reviewed before publishing. How this works.

More Stories

From Our Blog