Document type: scientific article published in Scientific Reports
Authors: Feighelstein M, Tomacheuski RM, Elias G, Shashoua N, van der Linden D, Luna SPL, Zamansky A
Abstract in French: Comparison of the performance of video-based deep learning models and experienced veterinarians in assessing pain in cattle
Accurate assessment of pain in animals is essential to ensure their well-being and guide veterinary interventions. Traditional pain assessment relies on veterinarians scoring pain-related behaviors, which can be influenced by variability in observations and individual expertise. The use of AI tools is attracting growing interest, and the question of whether artificial intelligence (AI) can outperform humans in recognizing pain in animals is only beginning to be explored. This study is the first to address pain recognition in cattle in this context. Specifically, we compare the performance of experienced veterinarians in the task of recognizing pain in cattle using video analysis. Our results show that machine learning models achieve high accuracy in pain classification and perform comparably to experienced veterinarians, with certain advantages in video-based assessments. These findings highlight the potential of machine learning to improve pain assessment in veterinary medicine by providing a scalable and more objective tool to enhance animal welfare.
Abstract in English: Accurate pain assessment in animals is crucial for ensuring animal welfare and guiding veterinary interventions. Traditional pain evaluation relies on scoring of pain behaviours by veterinarians, which can be influenced by observational variability and individual expertise. There is a growing interest in using AI tools, and the question whether Artificial Intelligence (AI) can outperform humans in animal pain recognition is only beginning to be explored. This study is the first to address cattle pain recognition in this context. Namely, we compare the performance of trained veterinarians in the task of pain recognition in cattle using video-based analysis. Our results show that machine learning models achieve high accuracy in pain classification and demonstrate performance comparable to trained veterinarians, with some advantages in video-based assessments. These findings highlight the potential of machine learning to enhance pain assessment in veterinary medicine, offering a scalable and more objective tool for improving animal welfare.
Publication that led to an article in Faunalytics on June 16, 2026: AI Can Detect Cow Pain Better Than Humans — What Now?
