Symposium on Artificial Intelligence and Veterinary Medicine (SAVY)
Ithaca, NY | April 19-21, 2024
Artificial Intelligence and Veterinary Medicine
Veterinary medicine is a broad and growing discipline that includes topics such as companion animal health, population medicine and zoonotic diseases, and agriculture. There is tremendous growth and potential in the development, application, and clinical use of artificial intelligence (AI) in human healthcare, and the emergence of AI in veterinary medicine poses exciting and new opportunities to improve the quality of life of animals and those who care for them. These new opportunities also come with challenges to understanding, interpreting, and adopting this powerful and evolving technology given the pace of research and commercial product developments.
AI and Veterinary Medicine at Cornell
Cornell University boasts an immense and unique collection of resources, such as the Machine Learning in Medicine (A Weill Cornell Medicine / Cornell Ithaca collaborative); Cornell University AI for Science Institute and Cornell Institute for Digital Agriculture (an ecosystem of scholars and teachers) in addition to the numerous research units including the College of Computer and Information Sciences, departments, and faculty across campus.
Shaping the Future of AI and Veterinary Medicine
The collection of these leading-edge colleges and institutes positions the College of Veterinary Medicine to lead the development and application of novel technologies. It raises the exciting possibility of creating an ecosystem of scholars, veterinary practitioners and stakeholders that can catalyze innovation and shape the future of AI in veterinary medicine and One Health.
With links to facilities such as the Animal Health and Diagnostic Center, the Cornell University Companion Animal Hospital, Cornell is uniquely positioned to leverage data for computer vision, natural language processing, and speech recognition tasks. AI-related research within the College of Veterinary Medicine ranges from population medicine, pathology and infectious disease, livestock and agriculture, and companion animals. Below are some of the researchers actively working in veterinary medicine/One Health and AI.
Associate Research Professor
Project(s): Radiomics on ultrasound images to predict whether cats have an inflammation of the small intestines or lymphoma; CT data analysis of horse limbs to predict Thoroughbred racehorse catastrophic breakdown;automated systems to leverage computer vision to help farmers and veterinarians improve the quality of milk from dairy cows using conventional and infrared imaging; novel ways to deliver radiation to dogs to minimize normal tissue toxicity while controlling or eradicating the tumor; computerized medical image analysis approaches with the aid of deep networks and machine learning
- Species: Humans, cattle, horses, dogs
- Summary: Radiation Dosimetry and Treatment Planning; Medical Image Processing and Analysis; and Medical Physics Training and Education. I have keen interests in machine learning methods in radiation oncology, radiomics, and stereotactic ablative radiation therapies and hypo-fractionation.
- Publications: The role of artificial intelligence in veterinary radiation oncology; Artificial intelligence 101 for veterinary diagnostic imaging; Radiomics Modeling of Catastrophic Proximal Sesamoid Bone Fractures in Thoroughbred Racehorses Using μCT.
Project(s): Multidrug resistance surveillance (there are several funded projects falling under this theme)
- Species: Humans, cattle, cats, dogs
- Summary: We use association mining, an unsupervised machine learning method, to analyze multidrug resistance in bacterial populations. Our goals are to understand trends in multidrug resistance over time and across populations. For example, in cattle we are investigating whether multidrug resistance in Salmonella Dublin changed after national antimicrobial use restrictions.
- Publications: Analysis of Multidrug Resistance in Staphylococcus aureus with a Machine Learning-Generated Antibiogram; Shared Multidrug Resistance Patterns in Chicken-Associated Escherichia coli Identified by Association Rule Mining
- Project(s): Lead impacts to bald eagles, lethal parasites in Adirondack moose, chronic wasting disease in cervids, demography of northeastern furbearers
- Species: Bald eagle , moose, white-tailed deer, American marten, fisher, river otter, muskrat, bobcat
- Summary: We program computers to consider wildlife demographic and health data to conduct probabilistic searches and mathematical optimization designed to pinpoint underlying systemic mechanisms in questions that have long evaded scientific examination using traditional statistical approaches. Recent publications include our computer’s novel computation of the population-scale impact of lead in bald eagles, which we published, only to have our findings corroborated in the journal Science one month later by an independent team using traditional approaches. We continue to apply these novel methods to solve long-standing questions in resource management, with current endeavors to use computer optimization to reduce cost of disease surveillance, or to finally crack the analytical linkage between harvest data and a species’ demographic properties. If we can succeed in that latter goal, then our work will benefit wildlife species from furbearers to fisheries, where only harvest data exists for their sustainable management.
- Publications: Environmental lead reduces the resilience of bald eagle populations; MoosePOPd: Population Dynamics in the Presence of Lethal Parasites; Surveillance Optimization Project for Chronic Wasting Disease (SOP4CWD)
Project(s): Control of infectious diseases, antimicrobial use in food animals, control of COVID-19 in the food industry; improving food safety and optimizing food production systems, decision support tools for the food industry
- Species: Humans, cattle, poultry, horses
Summary: The overarching goal of our computer lab is to advance One Health — the interconnected health of people, animals, plants, and their shared environment. We strive to improve lives through better health and food systems.
We develop sustainable data- and model-driven approaches for improving food safety, controlling infectious diseases, and optimizing food production systems.
- Publications: Using agent-based modeling to compare corrective actions for Listeria contamination in produce packinghouses; Examining Patterns of Persistent Listeria Contamination in Packinghouses using Agent-Based Models; In Silico Models for Design and Optimization of Science-Based Listeria Environmental Monitoring Programs in Fresh-Cut Produce Facilities.
Whether you are a learner interested in educational opportunities in AI and Veterinary Medicine, a researcher interested in collaborating with our faculty, or a business interested in working with Cornell, reach us at: firstname.lastname@example.org