LOS ANGELES — By utilizing artificial intelligence (AI) technology and veterinary records, Antech Diagnostics, a branch of Mars Petcare, has developed a diagnostic tool to accurately predict chronic kidney disease (CKD) in cats. CKD is the leading cause for death among cats older than 5 years and affects up to 40% of cats older than 10 years, according to the WALTHAM Centre for Pet Nutrition.
The diagnostic tool, RenalTech, is the work of Richard Bradley, a data science technical lead at the WALTHAM Centre. Bradley’s research — conducted in part with Ilias Tagkopoulos, science advisor for Mars, Incorporated, University of California professor and AI entrepreneur, as well as eight other researchers — was published in the Journal of Veterinary Internal Medicine Sept. 26, 2019.
Veterinary data from more than 150,000 cats over the past 20 years, which amounted to approximately 750,000 veterinary visits, was gathered from BANFIELD Pet Hospitals and mined for this research and the development of RenalTech. The AI diagnostic tool uses biomarkers for six common health measurements among cats, which are creatinine, blood urea nitrogen, white blood cell count, urine specific gravity, urine protein, and urine pH in relation to approximate age.
RenalTech analyzes the veterinary records against the biomarkers to determine common health changes that occurred in cats that later developed CKD, and how they compared to cats that did not develop the disease. When testing the results of its data mining, the diagnostic tool was found to be more than 95% accurate and could predict CKD up to two years before traditional diagnosis, Mars Petcare explained.
“When we looked at the historic data from thousands of pets, it was clear that the data had a story to tell,” Bradley explained. “There were subtle changes in several of the blood and urine parameters long before disease was diagnosed, but they were different from pet to pet. Machine learning allowed us to imprint all the subtleties of the changes in a computer algorithm, which was then able to spot the small abnormalities and make a robust prediction.”
CKD is notoriously difficult to diagnose, Mars Petcare reported, and has traditionally been detected only when “significant and irreversible kidney damage has occurred, which makes any intervention and treatment challenging.” RenalTech is expected to pave the way for veterinarians to develop unique, proactive plans to delay or prevent CKD and other chronic pet diseases going forward.
“The ability to predict disease is a game changer for veterinarians,” said David Aucoin, DVM, chief technology officer at Antech Diagnostics. “Now, veterinarians can act early, before disease strikes, allowing them to create a highly personalized care plan enabling pet owners to take the necessary steps to minimize the effects of chronic kidney disease. We believe this will dramatically improve a veterinarian’s ability to keep pets with their people for as long as possible, which is truly why we all come to work every day.”
Jonathan Elliott, Ph.D., vice principal for research and innovation at the University of London Royal Veterinary College and partner in the development of RenalTech, added, “This is a paradigm shifting moment for veterinary medicine. The ability to use artificial intelligence on data collected in practice as part of routine health screens to address chronic kidney disease well before the disease becomes clinically apparent gives us an opportunity to leverage best practice medicine for cats not previously available to veterinarians. It’s also exciting that we were able to move so quickly from publication in the Journal of Veterinary Internal Medicine to making the tool available in practice.”
RenalTech is available exclusively through Antech Diagnostics and is free for veterinarians using Antech’s reference laboratories in the US. This is the first predictive diagnostic tool of many to be developed by Mars Petcare, according to Antech.
Stay up to date on news about the pet food processing industry on our News page.