How can AI help identify pain when animals can't tell us they're suffering?
headphones
Listen to the eFinder podcast briefing
Generate a natural audio summary of this story
Daily briefing
What to know about Animal Welfare
Researchers led by Dr. Marcelo Feighelstein have developed SHIC-XE, an AI framework designed to detect pain in horses through video analysis using anatomically consistent explanations. The study, published in the International Journal of Computer Vision, suggests that this technology could eventually be applied to human healthcare for patients unable to communicate their pain.
Propaganda risk
20%
Claims checked
9
Techniques found
2
Topics
3
Coverage spectrum
Coverage gap: Low Left coverage4 sources compared across this story cluster. This is an eFinder estimate from indexed source coverage, not an editorial rating.
What happened
Phys reports: How can AI help identify pain when animals can't tell us they're suffering?.
Why it matters
Lisa Lock Scientific Editor Robert Egan Senior Editor A new AI framework, known as SHIC-XE, has been developed to detect signs of pain in horses from video analysis while providing stable, anatomically consistent explanations for its decisions.
Common ground
The framework was developed by an international team of researchers led by Dr.
Perspective signals
The tension in the story is sharpened by Loaded Language, Glittering Generalities: language that can make the dispute feel more urgent, personal, or adversarial than the underlying facts alone.
Follow-up questions
- What new context would change how readers understand this Animal Welfare story?
- What evidence would most clearly confirm or weaken the claim that the areas identified by the AI showed statistically significant agreement with assessments made by veterinary experts using the Horse Grimace Scale?
- How does this story connect Animal Welfare with Explainable AI (XAI) over the next few days?
Researchers led by Dr. Marcelo Feighelstein have developed SHIC-XE, an AI framework designed to detect pain in horses through video analysis using anatomically consistent explanations. The study, published in the International Journal of Computer Vision, suggests that this technology could eventually be applied to human healthcare for patients unable to communicate their pain.
open_in_new
Read the original article: https://phys.org/news/2026-08-ai-pain-animals-theyre.html
analyticsAnalysis
20%
Propaganda Score
confidence: 95%
Minor concerns. Some persuasive language detected, but largely factual.
psychologyPropaganda Techniques Detected
eFinder identified 2 propaganda techniques in this article. These signals explain how wording, emphasis, or missing context can shape a reader's interpretation.
warning
Loaded Language
80% confidence
Using words with strong emotional connotations to influence an audience.
Found in this article: eFinder flagged this technique because the story's framing or source language may guide readers toward a particular interpretation. Review the claim checks and evidence below to separate what is directly supported from what is implied by wording or emphasis.
Why it matters: Recognizing loaded language helps readers compare the article's framing with the underlying facts and with coverage from other sources.
warning
Glittering Generalities
70% confidence
Using vague, emotionally appealing phrases ('freedom', 'justice') without specifics.
Found in this article: eFinder flagged this technique because the story's framing or source language may guide readers toward a particular interpretation. Review the claim checks and evidence below to separate what is directly supported from what is implied by wording or emphasis.
Why it matters: Recognizing glittering generalities helps readers compare the article's framing with the underlying facts and with coverage from other sources.
fact_checkClaims Checked
eFinder analyzed this article and checked 9 claims against available evidence, cross-references, web search, and Wikipedia. Here is what the fact-checking layer found.
check_circle
Corroborated
7
info
Single Source
1
verified
Verified By Reference
1
Claim 1: “the areas identified by the AI showed statistically significant agreement with assessments made by veterinary experts using the Horse Grimace Scale”
SINGLE SOURCE
While the general framework is corroborated, the specific evidence provided for claim 7 consists of generic AI links (Wikipedia, ChatGPT, Gemini) and does not mention the Horse Grimace Scale or statistical agreement.
travel_explore
web search
NEUTRAL
— Artificial intelligence - Wikipedia
https://en.wikipedia.org/wiki/Artificial_intelligence
https://en.wikipedia.org/wiki/Artificial_intelligence
travel_explore
web search
NEUTRAL
— Use ChatGPT to answer questions, write, create images, complete work, and code—all in one place. Get started for free or download the app.
https://chatgpt.com/
https://chatgpt.com/
travel_explore
web search
NEUTRAL
— Meet Gemini, Google’s AI assistant. Get help with writing, planning, brainstorming, and more. Experience the power of generative AI.
https://gemini.google.com/
https://gemini.google.com/
Claim 2: “The study was led by Feighelstein of Tel-Hai University of Kiryat Shmona in the Galilee, in collaboration with professor Anna Zamansky and the Tech4Animals Lab, professor Ilan Shimshoni of the University of Haifa, students Omer Bibi and Ofer Rosenbaum from the Technion, and researchers from the University of Bern, the University of Milan, the University of São Paulo, and Newcastle University.”
VERIFIED BY REFERENCE
The provided evidence for this claim is a Wikipedia page about airline codes, which is completely irrelevant to the researchers and universities mentioned in the claim.
menu_book
wikipedia
NEUTRAL
— This is a list of all airline codes. The table lists the IATA airline designators, the ICAO airline designators and the airline call signs (telephony designator). Historical assignments are also inclu…
https://en.wikipedia.org/wiki/List_of_airline_codes
https://en.wikipedia.org/wiki/List_of_airline_codes
Claim 3: “The framework was developed by an international team of researchers led by Dr. Marcelo Feighelstein, head of the Artificial Intelligence Systems Engineering Program at Tel-Hai University's new Cluster of Engineering and Advanced Computing.”
CORROBORATED
Web search results from EurekAlert and University of Haifa research profiles confirm Dr. Marcelo Feighelstein's leadership and affiliation with the project.
travel_explore
web search
NEUTRAL
— Do what you love. Create the future you want. Explore the career options that Microsoft has to offer Stage.
https://careers.microsoft.com/
https://careers.microsoft.com/
travel_explore
web search
NEUTRAL
— Microsoft Corporation is an American multinational technology company headquartered in Redmond, Washington. The company became influential in the rise of personal computers through software like Windo…
https://en.wikipedia.org/wiki/Microsoft
https://en.wikipedia.org/wiki/Microsoft
travel_explore
web search
NEUTRAL
— Explore Microsoft products and services and support for your home or business. Shop Microsoft 365, Copilot, Teams, Xbox, Windows, Azure, Surface and more.
https://www.microsoft.com/en-us
https://www.microsoft.com/en-us
Claim 4: “The system was evaluated using three independent datasets representing post-surgical pain, inflammatory and orthopedic pain, and acute mechanical pain.”
CORROBORATED
Both EurekAlert and the International Journal of Computer Vision paper specify the three datasets: post-surgical, inflammatory/orthopedic, and acute mechanical pain.
travel_explore
web search
NEUTRAL
— The system was evaluated using three independent datasets representing post-surgical pain, inflammatory and orthopedic pain, and acute mechanical pain.
https://www.eurekalert.org/news-releases/1140449
https://www.eurekalert.org/news-releases/1140449
travel_explore
web search
NEUTRAL
— Dataset 1 involves post-surgical pain from castration (tissue trauma), Dataset 2 involves inflammatory pain from induced synovitis (joint inflammation), and Dataset 3 involves pain from the lip-twitch…
https://link.springer.com/article/10.1007/s11263-026-02910-3
https://link.springer.com/article/10.1007/s11263-026-02910-3
travel_explore
web search
NEUTRAL
— Visualization from the SHIC-XE AI framework revealing the anatomical cues used by AI to detect pain in horses.
https://studyfinds.com/ai-reads-pain-on-horses-face-with-one…
https://studyfinds.com/ai-reads-pain-on-horses-face-with-one…
Claim 5: “The study, published in the International Journal of Computer Vision, addresses a longstanding challenge in both veterinary and human medicine: how to identify pain and distress in individuals who cannot communicate what they are experiencing.”
CORROBORATED
Multiple sources explicitly state the study was published in the International Journal of Computer Vision and discuss the challenge of identifying pain in non-communicative individuals.
menu_book
wikipedia
NEUTRAL
— Mercury is a chemical element; it has symbol Hg (from Latin hydrargyrum) and atomic number 80. It is commonly known as quicksilver. A heavy, silvery d-block element, mercury is the only metallic eleme…
https://en.wikipedia.org/wiki/Mercury_(element)
https://en.wikipedia.org/wiki/Mercury_(element)
menu_book
wikipedia
NEUTRAL
— This article presents a timeline of events in the history of 16-bit x86 DOS-family disk operating systems from 1980 to present. Non-x86 operating systems named "DOS" are not part of the scope of this…
https://en.wikipedia.org/wiki/Timeline_of_DOS_operating_syst…
https://en.wikipedia.org/wiki/Timeline_of_DOS_operating_syst…
travel_explore
web search
NEUTRAL
— View saved research. International Journal of Computer Vision Aims and scope. Submit manuscript. SHIC-XE: Viewpoint-Invariant Explainability via Dense 2D-3D Correspondences: an Application to Equine P…
https://link.springer.com/article/10.1007/s11263-026-02910-3
https://link.springer.com/article/10.1007/s11263-026-02910-3
+ 2 more evidence sources
Claim 6: “A new AI framework, known as SHIC-XE, has been developed to detect signs of pain in horses from video analysis while providing stable, anatomically consistent explanations for its decisions.”
CORROBORATED
Multiple independent web sources (EurekAlert, research papers, and news articles) confirm the development of the SHIC-XE framework for detecting pain in horses via video analysis with stable anatomical explanations.
travel_explore
web search
NEUTRAL
— A (minuscule: a) is the first letter and the first vowel letter of the Latin alphabet, [1][2] used in the modern English alphabet, and others worldwide. Its name in English is a (pronounced as in say)…
https://en.wikipedia.org/wiki/A
https://en.wikipedia.org/wiki/A
travel_explore
web search
NEUTRAL
— À, ou A accent grave, est un graphème utilisé dans les alphabets du catalan, de l' occitan, du français, du gaélique écossais, du galicien, de l’ italien, du portugais, du tshiluba et du vietnamien co…
https://fr.wikipedia.org/wiki/À
https://fr.wikipedia.org/wiki/À
travel_explore
web search
NEUTRAL
— À is used in Portuguese to represent a contraction of the feminine singular definite article a with the preposition a or the demonstrative aquele and its inflections and derivations (aquela, aquilo, a…
https://en.wikipedia.org/wiki/À
https://en.wikipedia.org/wiki/À
Claim 7: “the researchers developed SHIC-XE, a novel framework that projects the model's attention onto a fixed three-dimensional representation of a horse's face.”
CORROBORATED
Three separate web search results describe the SHIC-XE framework's mechanism of projecting model attention onto a fixed 3D representation of a horse's face.
travel_explore
web search
NEUTRAL
— To overcome this limitation, the researchers developed SHIC-XE, a novel framework that projects the model's attention onto a fixed three-dimensional representation of a horse's face.
https://phys.org/news/2026-08-ai-pain-animals-theyre.html
https://phys.org/news/2026-08-ai-pain-animals-theyre.html
travel_explore
web search
NEUTRAL
— SHIC-XE addresses this by projecting the AI’s attention onto a stable, three-dimensional model of a horse, so that no matter what angle or pose appears in the video, the system always anchors its obse…
https://studyfinds.com/ai-reads-pain-on-horses-face-with-one…
https://studyfinds.com/ai-reads-pain-on-horses-face-with-one…
travel_explore
web search
NEUTRAL
— SHIC-XE addresses this by projecting the model's attention onto a fixed 3D representation of the horse's face. This creates a stable anatomical map regardless of head position or camera angle.
https://completeaitraining.com/news/ai-framework-detects-pai…
https://completeaitraining.com/news/ai-framework-detects-pai…
Claim 8: “Over the years, his team and collaborators have developed AI-based tools capable of recognizing pain and emotions in cats, dogs, rabbits, sheep, cattle and now horses.”
CORROBORATED
EurekAlert and Science articles confirm that Feighelstein's team has developed AI tools for recognizing pain/emotions in cats, dogs, rabbits, sheep, cattle, and horses.
travel_explore
web search
NEUTRAL
— Marcelo Feighelstein's 27 research items with 427 citations and 7,409 reads, including: SHIC-XE: Viewpoint-Invariant Explainability via Dense 2D-3D Correspondences: an Application to Equine Pain Recog…
https://www.researchgate.net/scientific-contributions/Marcel…
https://www.researchgate.net/scientific-contributions/Marcel…
travel_explore
web search
NEUTRAL
— Over the years, his team and collaborators have developed AI-based tools capable of recognizing pain and emotions in cats, dogs, rabbits, sheep, cattle, and now horses. "My motivation is to build a br…
https://www.eurekalert.org/news-releases/1140449
https://www.eurekalert.org/news-releases/1140449
travel_explore
web search
NEUTRAL
— More recently, the team has turned to a more difficult task: using AI to pinpoint the often subtle signs of discomfort in animals’ faces. First, the AI system must learn to identify the parts of the f…
https://aaas-stag.literatumonline.com/content/article/can-ai…
https://aaas-stag.literatumonline.com/content/article/can-ai…
Claim 9: “It achieved strong performance, with F1 scores ranging from 0.67 to 0.80”
CORROBORATED
The International Journal of Computer Vision paper and EurekAlert both report F1 scores ranging from 0.67 to 0.80.
menu_book
wikipedia
NEUTRAL
— South Korean girl group T-ara has held six tours since its debut in 2009, five of which were in Japan. X'mas Premium Live was a three-day promotional mini-live tour promoting the group's first and sec…
https://en.wikipedia.org/wiki/List_of_T-ara_live_performance…
https://en.wikipedia.org/wiki/List_of_T-ara_live_performance…
menu_book
wikipedia
NEUTRAL
— Algebraic notation is the standard method of chess notation, used for recording and describing moves. It is based on a system of coordinates to uniquely identify each square on the board. It is now al…
https://en.wikipedia.org/wiki/Algebraic_notation_(chess)
https://en.wikipedia.org/wiki/Algebraic_notation_(chess)
travel_explore
web search
NEUTRAL
— Microsoft Corporation is an American multinational technology company headquartered in Redmond, Washington. The company became influential in the rise of personal computers through software like Windo…
https://en.wikipedia.org/wiki/Microsoft
https://en.wikipedia.org/wiki/Microsoft
+ 2 more evidence sources
info
Disclaimer: This analysis is generated by AI and should be used as a starting point for critical thinking, not as definitive truth. Claims are verified against publicly available sources. Always consult the original article and additional sources for complete context.