New veterinary algorithm reads between the lines
DeepTag scrutinizes a practitioner’s clinical notes to identify a likely diagnosis.
The diagnosis might be hiding in your clinical notes.
A newly developed algorithm has shown promise in its ability to burrow into a veterinarian’s typed notes from a patient encounter and predict diseases the animal might have, Stanford University reported.
Colorado State University’s College of Veterinary Medicine contributed to the creation of DeepTag, a form of artificial intelligence, by annotating and assigning disease codes to more than 112,000 clinical notes.
“We’re not explicitly telling the algorithm what words are associated with what disease. Instead, it’s finding the keywords that are associated with specific diagnoses,” said Stanford researcher James Zou, Ph.D.
Dr. Zou and his team, including research scientist Ashley Zehnder, DVM, Ph.D., detailed their findings in a paper published in npj Digital Medicine.
DeepTag serves a practical purpose, said Dr. Zou, an assistant professor of biomedical data science.
“Millions of vet clinical records … are essentially wasted because they’re so cumbersome to work with,” he said. “Clinics don’t have the infrastructure to extract information from these medical records, but there’s a lot of really interesting information in them.”
The algorithm is about ready for broader use.
“Since the paper published, Zou has been discussing applying the DeepTag algorithm to large veterinary clinics around the country, and locally in the San Francisco Bay Area,” according to Stanford.
After that, perhaps worldwide.
“Once the platform is online, any veterinarian could go and use the platform to annotate their notes and see the results in real time,” Dr. Zou said.