Dr. Candace Chu, an assistant professor at the Texas A&M University College of Veterinary Medicine and School of Biomedical Sciences, is developing artificial intelligence tools aimed at improving the learning experience for veterinary students. Dr. Chu says the technology has the potential to improve the veterinary profession by enhancing diagnostic, teaching and learning capabilities.
Charis Olson ’25 / Texas A&M College of Veterinary Medicine and Biomedical Sciences
Researchers at the Texas A&M College of Veterinary Medicine and Biomedical Sciences (VMBS) are finding new ways for veterinarians to use artificial intelligence (AI) tools both in the clinic and in the classroom.
Candice Chu, PhD, assistant professor in the VMBS Department of Veterinary Pathobiology, developed VetClinPathGPT, a learning tool for veterinary students based on ChatGPT technology.
The tool helps students studying clinical pathobiology, a branch of veterinary medicine that focuses on diagnosing, treating and preventing disease. The tool allows students to “chat” with the AI to ask questions about terms and concepts, or ask the tool to provide a list of study questions.
Chu also A list of methods has been published AI increases efficiency and extends the capabilities of educators and clinicians.
“AI is a powerful assistant that can help clinicians, educators and students reduce the time they spend on repetitive tasks,” Chu said. “By reducing repetitive tasks, individuals can spend their time on the most important parts of their jobs, like completing assignments and helping students and patients.”
Improving Veterinary Education with AI
Chu believes AI will become a regular part of veterinary medicine classes.
“Imagine having a microscope connected to a camera with AI capabilities, and students can look down at a slide while a clinical pathologist is there explaining what they’re looking at,” Chu says. “Students can ask the AI, ‘What is this cell?’, and the AI can tell them not only what type of cell it is, but also how to identify it.”
“Veterinarians are in high demand, so having lots of students in the classroom is a good thing,” she says, “but one instructor can’t teach every student individually at the same time, so in my ideal world, AI would help with that.”
For now, Chu is supporting efforts to bring AI to veterinary education by creating tools such as VetClinPathGPT, which provides students with a virtual learning partner.
“One of the best ways students can use AI is to upload what they’ve read in class to an AI tool and ask it to create study questions based on the text,” she says. “Once they’ve read the passage, they can test their knowledge or use AI to help them prepare for an exam.”
Educators can also use AI to reduce the time they spend on repetitive tasks, such as creating exam questions.
“The key to getting high-quality, relevant answers to your questions is making sure the information uploaded to the AI is trustworthy,” Chu said. “For example, VetClinPathGPT doesn’t just use any information on the internet. eClinPath WebsiteIt is an online textbook developed by the Cornell University College of Veterinary Medicine.
The Future of Veterinary Medicine
Chu also expects to see AI being used in clinical settings to assist with record-keeping and other tasks that take up more of your time with patient interactions.
“It would be extremely helpful to have a tool that could look at medical records and pull examples from cases,” Chu said. “Imagine having a tool that could fill out the medical record while you’re talking to the patient’s owner.”
While the technology exists, the challenge is ensuring that AI tools do not infringe on the privacy of medical records.
“Training an AI tool to accurately read a patient’s medical records would require sharing the records with developers, which violates patient privacy laws,” Chu said. “The same goes for clinicians who want to use AI to identify important information in a patient’s file. If they have to spend a lot of time removing all the personal information, they’ll probably end up reviewing the records themselves.”
But in Chu’s opinion, it’s only a matter of time before someone develops an AI tool that meets the needs of hospitals, clinicians and patients.
“There are already ways to build a custom version of ChatGPT and keep it private so others can’t use it,” she says. “Another option is to use an AI tool that only lives locally on your computer or your clinic’s network.”
Partnership, not acquisition
From Chu’s perspective, the use of AI will always be a partnership between humans and artificial intelligence.
“Neither is perfect on their own, so when you combine them, you improve your ability to diagnose, teach and learn,” she says. “One thing I tell people is don’t worry that AI is going to replace you. The people who will replace you are the ones who know how to use it. I think in the future, knowing how to embrace this technology will be a fundamental requirement to be an effective and competitive veterinary educator in the job market.”
In addition to his work on lab tools, Chu is partnering with VMBS’s Digestive Institute and the Texas A&M Data Science Institute on a machine learning project to see whether AI can help diagnose acute pancreatitis in dogs.
She has also been invited to deliver a keynote address at the American College of Veterinary Radiology Scientific Conference this fall, and will present her AI research at two other fall conferences: the Texas Taiwan Biotechnology Association Symposium and the American College of Veterinary Pathologists Annual Meeting.
“This technology is still very new, so there’s a lot of opportunity for innovation,” she said.
