Artificial Intelligence

Artificial Intelligence at Weill School of Veterinary Medicine

Researchers at the UC Davis Weill School of Veterinary Medicine are applying artificial intelligence and machine learning to questions in animal health, human health, food safety, and agricultural production.

AI and machine learning research at Weill SVM brings together expertise from across UC Davis. Published collaborations connect veterinary medicine with computer science, mathematics, animal science, and pediatrics, alongside the MIND Institute and Center for Mind and Brain. These partnerships combine computational methods with clinical and biological expertise to investigate disease risks, analyze biomedical images, and understand complex biological systems.

Explore our research areas and selected publications below. Each entry includes the complete author list and a link to the publication. WSVM-affiliated (or affiliated at time of publication) authors are shown in bold; affiliation reflects the publication record and does not necessarily indicate current employment.

Research Areas

Clinical Diagnostics and Health Records

Artificial intelligence is being investigated as a tool for veterinary diagnosis, quantitative pathology, and clinical information management. Applications include diagnostic classifiers, analysis of feline intestinal biopsies, thermal-image classification of canine tumors, and integration of machine learning into electronic health records. Studies also examine model reliability and reproducibility to understand how these tools could support veterinary care.

Disease Surveillance and One Health

Machine learning can help investigate disease risks across wildlife, livestock, humans, and shared environments. WSVM studies include predicting viral host associations and zoonotic potential, modeling climate-related changes in spillover risk, analyzing equine disease outbreaks, and combining receptor-binding experiments with computational prediction. Other work uses natural language processing to classify wildlife clinical records and support early detection of unusual illness and mortality events.

Microbiomes and Agricultural Systems

Research in livestock and agricultural systems connects machine learning with animal health, microbiome science, pathogen genomics, and environmental monitoring. Examples include examining how rumen microbiomes relate to feed efficiency, reassessing diagnostic measurements for calf infections, and identifying dairy-management factors associated with antimicrobial resistance. Additional applications investigate bacterial host associations and estimate dairy-farm wastewater turbidity from images.

Imaging and Computational Analysis

Medical images and microscopy provide opportunities to identify patterns and measure biological features using computational methods. Applications at WSVM include deep-learning segmentation of equine PET scans, radiomics analysis of bone fractures and brain disease, and three-dimensional cellular segmentation. Related work combines brain imaging with mitochondrial measurements to investigate neurological disease and develop predictive models.

Drug Modeling and Food Safety

Predicting how drugs behave across animal species is a growing application of machine learning and chemical language models. Recent studies involving WSVM authors address plasma and tissue half-lives, drug-residue depletion, and clearance, alongside tools that improve access to regulatory and residue-testing data. These approaches support pharmacology and food-safety research, with further validation needed before predictions can inform clinical or regulatory decisions.

Responsible AI and Research Tools

Reliable AI use requires attention to reproducibility, human oversight, and the needs of veterinary professionals. Studies evaluate large language models for extracting information from veterinary records and screening animal-health literature, while surveys examine AI literacy and use among students and specialists. This work helps identify useful applications, limitations, and training needs for responsible adoption in veterinary medicine and research.