Dr. Cazer
Citation: American Journal of Veterinary Research 86, S1; 10.2460/ajvr.86.s1.editorial
Dr. Basran
Citation: American Journal of Veterinary Research 86, S1; 10.2460/ajvr.86.s1.editorial
Dr. Ivanek-Miojevic
Citation: American Journal of Veterinary Research 86, S1; 10.2460/ajvr.86.s1.editorial
Artificial intelligence is beginning to permeate our daily lives, and veterinary medicine is no exception. Artificial intelligence is a broad umbrella term encompassing the many ways computer algorithms can perform difficult tasks that previously required human intelligence. Veterinary professionals may take different approaches with this new technology, from enthusiastic engagement to skeptical avoidance. This special issue introduces busy veterinary professionals to AI principles and applications in veterinary medicine and research.
On April 19 to 21, 2024, nearly 200 veterinarians, scientists, students, educators, and engineers gathered at Cornell University for the first Symposium on Artificial Intelligence in Veterinary Medicine (SAVY) and shared how AI is already changing companion animal health, livestock health, population medicine, and One Health. We are excited to share some highlights of the ideas presented at SAVY with AJVR readers in this supplemental issue.
In roundtable discussions and facilitated workshops, SAVY participants explored the future benefits and challenges that AI will bring to veterinary medicine. Several themes emerged from these group discussions. First, there is a pressing need for education and awareness on AI in veterinary medicine. In many cases, veterinarians are already using AI-powered tools in their practices without fully understanding how these technologies work and the potential impact on diagnostic accuracy, patient and client privacy, and animal health. Artificial intelligence should be added to veterinary curriculums and continuing education so that clinicians are prepared to safely integrate these tools into veterinary medicine. Second, ethical guidelines, regulations, and performance standards for AI in veterinary medicine are lacking. Third, translational research is needed to bridge the gap between AI research and real-world veterinary medicine. Finally, the success of AI applications hinges on access to diverse, extensive, and organized data resources, necessitating the development of data collection and analysis systems.
Authors in this special issue of AJVR and of companion reviews in JAVMA discuss many of these themes and propose possible paths forward for responsible and innovative integrations of AI into veterinary medicine. Here’s a primer on how you can use this special issue to advance your understanding of AI.
Start with a gentle introduction to learn about the areas where AI and machine learning are likely to impact veterinary medicine and some of the scientific limitations and ethical considerations of using these new technologies.1 Next, learn about how AI may be used to support government regulatory processes and safety surveillance for products used in veterinary medicine.2
Dive into specific use cases, including AI-powered sensors and models for predicting bovine respiratory disease,3,4 computer vision for dog-breed identification,5 large language model prompts to generate educational messages about antimicrobial resistance,6 and machine learning models for imaging interpretation, early disease detection,7 and disease risk factor identification8 that promise to improve pet health and longevity. Learn from a survey of your peers about benefits and challenges in integrating AI into your veterinary practice.9 Farmers and veterinarians can peek into the future, when advances in big data and digitization could significantly improve livestock health and welfare.
Artificial intelligence is also showing up in research processes, potentially making veterinary research more efficient and impactful. For example, scientists are using computer vision and deep learning models to speed up research tasks, generating a deeper understanding of animal behavior.10 Machine learning prediction models can fill in missing antimicrobial resistance data, enhancing our resistance surveillance systems.11 Finally, AI can be used to predict infectious disease burdens, providing a warning to epidemiologists and veterinarians of future risks to animal and human health.12
The papers in this special issue are just the beginning, the “early adopters” of AI. There is still a lot of work to be done to establish AI as a trustworthy and effective tool in clinical practice and veterinary research. Whether you embrace AI tools with optimism or a healthy dose of skepticism, this special issue can be your starting point for engaging with this technology that will transform veterinary medicine.
Acknowledgments
We would like to thank Dr. Amy Kuceyeski, Nahla Minges, and Cortney Decker, who were members of the Symposium on Veterinary Medicine and Artificial Intelligence steering committee. The symposium would not have been a success without them. The symposium was partially funded through a generous grant from the NIH, Center for Veterinary Medicine (R13-FD007813-01), in participation with the US FDA. We would also like to thank Dr. Lisa Fortier for the opportunity to share this research with the veterinary community.
References
- 1.↑
Sobkowich KE. Demystifying artificial intelligence for veterinary professionals: practical applications and future potential. Am J Vet Res. 2025;86(S1):S6–S15. doi:10.2460/ajvr.24.09.0275
- 2.↑
Duggirala HJ, Johnson JL, Tadesse DA, et al. Artificial intelligence and machine learning in veterinary medicine: a regulatory perspective on current initiatives and future prospects. Am J Vet Res. 2025;86(S1):S16–S21. doi:10.2460/ajvr.24.09.0285
- 3.↑
Prosser HM, Bortoluzzi EM, Valeris-Chacin RJ, Baker EC, Scott MA. Application of artificial intelligence and machine learning in bovine respiratory disease prevention, diagnosis, and classification. Am J Vet Res. 2025;86(S1): S22–S26. doi:10.2460/ajvr.24.10.0327
- 4.↑
Bakshi A, Stetson J, Wang L, Shi J, Caragea D, Miller LC. Toward a rapid, sensitive, user-friendly, field-deployable artificial intelligence tool for enhancing African swine fever diagnosis and reporting. Am J Vet Res. 2025;86(S1): S27–S37. doi:10.2460/ajvr.24.10.0305
- 5.↑
Perez G, He Y, Lyu Z, Chen Y, Howe NR, Rando HM. Standardizing canine breed data in veterinary records is challenging, but computer vision offers an alternative perspective on breed assignment. Am J Vet Res. 2025;86(S1): S38–S45. doi:10.2460/ajvr.24.10.0315
- 6.↑
Akinyede O, Yustyniuk V, Ochwo S, Aworh M, Wilkins M. Preliminary exploration of ChatGPT-4 shows the potential of generative artificial intelligence for culturally tailored, multilingual antimicrobial resistance awareness messaging. Am J Vet Res. 2025;86(S1):S46–S51. doi:10.2460/ajvr.24.09.0283
- 7.↑
Albergante L, O’Flynn C, De Meyer G. Artificial intelligence is beginning to create value for selected small animal veterinary applications while remaining immature for others. J Am Vet Med Assoc. 2025;263(3):388–394. doi:10.2460/javma.24.09.0617
- 8.↑
Hadar BN, Poljak Z, Bonnett B, Coe J, Stone EA, Bernardo TM. Machine learning predicts selected cat diseases using insurance data amid challenges in interpretability. Am J Vet Res. 2025;86(S1):S52–S62. doi:10.2460/ajvr.24.09.0282
- 9.↑
Gabor S, Danylenko G, Voegeli B. Familiarity with artificial intelligence drives optimism and adoption among veterinary professionals: 2024 survey. Am J Vet Res. 2025;86(S1):S63–S69. doi:10.2460/ajvr.24.10.0293
- 10.↑
Sun J. Toward collaborative artificial intelligence development for animal well-being. J Am Vet Med Assoc. Published online January 10, 2025. doi:10.2460/javma.24.10.0650
- 11.↑
Anil G, Glass J, Mosaddegh A, Cazer CL. Antimicrobial minimum inhibitory concentrations can be imputed from phenotypic data using a random forest approach. Am J Vet Res. 2025;86(S1):S70–S79. doi:10.2460/ajvr.24.10.0314
- 12.↑
Berke O, Chan ST, Orang A. Of Lyme disease and machine learning in a One Health world. Am J Vet Res. 2025;86(S1):S80–S83. doi:10.2460/ajvr.24.10.0300
