Comparison between AI and human expert performance in acute pain assessment in sheep
Abstract This study explores the question whether Artificial Intelligence (AI) can outperform human experts in animal pain recognition using sheep as a case study. It uses a dataset of N = 48 sheep undergoing surgery with video recordings taken before (no pain) and after (pain) surgery. Four veterin...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-024-83950-y |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841559643886714880 |
|---|---|
| author | Marcelo Feighelstein Stelio P. Luna Nuno O. Silva Pedro E. Trindade Ilan Shimshoni Dirk van der Linden Anna Zamansky |
| author_facet | Marcelo Feighelstein Stelio P. Luna Nuno O. Silva Pedro E. Trindade Ilan Shimshoni Dirk van der Linden Anna Zamansky |
| author_sort | Marcelo Feighelstein |
| collection | DOAJ |
| description | Abstract This study explores the question whether Artificial Intelligence (AI) can outperform human experts in animal pain recognition using sheep as a case study. It uses a dataset of N = 48 sheep undergoing surgery with video recordings taken before (no pain) and after (pain) surgery. Four veterinary experts used two types of pain scoring scales: the sheep facial expression scale (SFPES) and the Unesp-Botucatu composite behavioral scale (USAPS), which is the ‘golden standard’ in sheep pain assessment. The developed AI pipeline based on CLIP encoder significantly outperformed human facial scoring (AUC difference = 0.115, p < 0.001) when having access to the same visual information (front and lateral face images). It further effectively equaled human USAPS behavioral scoring (AUC difference = 0.027, p = 0.163), but the small improvement was not statistically significant. The fact that the machine can outperform human experts in recognizing pain in sheep when exposed to the same visual information has significant implications for clinical practice, which warrant further scientific discussion. |
| format | Article |
| id | doaj-art-2259f0c123844a4fa6194d6707b86d8b |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-2259f0c123844a4fa6194d6707b86d8b2025-01-05T12:16:22ZengNature PortfolioScientific Reports2045-23222025-01-011511710.1038/s41598-024-83950-yComparison between AI and human expert performance in acute pain assessment in sheepMarcelo Feighelstein0Stelio P. Luna1Nuno O. Silva2Pedro E. Trindade3Ilan Shimshoni4Dirk van der Linden5Anna Zamansky6Department of Information Systems, University of HaifaSchool of Veterinary Medicine and Animal Science, Sao Paolo State University (Unesp)School of Veterinary Medicine and Animal Science, Sao Paolo State University (Unesp)Department of Population Pathobiology, North Carolina State UniversityDepartment of Information Systems, University of HaifaDepartment of Computer and Information Sciences, Northumbria UniversityDepartment of Information Systems, University of HaifaAbstract This study explores the question whether Artificial Intelligence (AI) can outperform human experts in animal pain recognition using sheep as a case study. It uses a dataset of N = 48 sheep undergoing surgery with video recordings taken before (no pain) and after (pain) surgery. Four veterinary experts used two types of pain scoring scales: the sheep facial expression scale (SFPES) and the Unesp-Botucatu composite behavioral scale (USAPS), which is the ‘golden standard’ in sheep pain assessment. The developed AI pipeline based on CLIP encoder significantly outperformed human facial scoring (AUC difference = 0.115, p < 0.001) when having access to the same visual information (front and lateral face images). It further effectively equaled human USAPS behavioral scoring (AUC difference = 0.027, p = 0.163), but the small improvement was not statistically significant. The fact that the machine can outperform human experts in recognizing pain in sheep when exposed to the same visual information has significant implications for clinical practice, which warrant further scientific discussion.https://doi.org/10.1038/s41598-024-83950-y |
| spellingShingle | Marcelo Feighelstein Stelio P. Luna Nuno O. Silva Pedro E. Trindade Ilan Shimshoni Dirk van der Linden Anna Zamansky Comparison between AI and human expert performance in acute pain assessment in sheep Scientific Reports |
| title | Comparison between AI and human expert performance in acute pain assessment in sheep |
| title_full | Comparison between AI and human expert performance in acute pain assessment in sheep |
| title_fullStr | Comparison between AI and human expert performance in acute pain assessment in sheep |
| title_full_unstemmed | Comparison between AI and human expert performance in acute pain assessment in sheep |
| title_short | Comparison between AI and human expert performance in acute pain assessment in sheep |
| title_sort | comparison between ai and human expert performance in acute pain assessment in sheep |
| url | https://doi.org/10.1038/s41598-024-83950-y |
| work_keys_str_mv | AT marcelofeighelstein comparisonbetweenaiandhumanexpertperformanceinacutepainassessmentinsheep AT steliopluna comparisonbetweenaiandhumanexpertperformanceinacutepainassessmentinsheep AT nunoosilva comparisonbetweenaiandhumanexpertperformanceinacutepainassessmentinsheep AT pedroetrindade comparisonbetweenaiandhumanexpertperformanceinacutepainassessmentinsheep AT ilanshimshoni comparisonbetweenaiandhumanexpertperformanceinacutepainassessmentinsheep AT dirkvanderlinden comparisonbetweenaiandhumanexpertperformanceinacutepainassessmentinsheep AT annazamansky comparisonbetweenaiandhumanexpertperformanceinacutepainassessmentinsheep |