New AI-driven diagnostic tool can predict chronic kidney disease in cats two years before traditional diagnosis

Powered by data science, RenalTech™ predictive diagnostic tool is a first for veterinarians, signaling new potential for personalized health care for pets

Biomarkers

Mars Petcare

Welfare and Behaviour

Antech Diagnostics, part of Mars Petcare, has launched a new diagnostic tool that was developed using artificial intelligence and veterinary records. The resulting biomarker model allows the accurate prediction of the disease that is the number one cause of death for cats over the age of five. The RenalTech™ tool is now available to veterinarians in the U.S. and enables a new way to partner with cat owners on proactive health care plans for their pets that are tailored to their specific needs.

The RenalTech™ tool was developed from a research project led by Richard Bradley at WALTHAM that was published in Journal of Veterinary Internal Medicine (Bradley et al., 2019). The project involved mining the veterinary records of more than 150,000 cats that visited BANFIELD® Pet Hospitals in partnership with the Mars Advanced Research Institute (MARI) and Process Integration and Predictive Analytics (PIPA LLC).

What is CKD?
Chronic kidney disease (CKD) is the number one cause of death for cats over five and affects 30-40 percent of all cats over the age of 10. It is a highly complex disease that historically has been difficult to diagnose. The current methods are only able to confirm the disease in a pet once significant and irreversible kidney damage has occurred, which makes any intervention and treatment challenging.
As with so many diseases, being able to accurately predict the ailments that will impact health in the future offers many possibilities. Veterinarians will now be able to create tailored proactive care plans for cats and work to delay the onset of CKD.

How was the new RenalTech™ tool developed?
The new diagnostic tool uses a biomarker of six common feline health measurements (creatinine, blood urea nitrogen, white blood cell count, urine specific gravity, urine protein, urine pH–along with approximate age) to predict CKD up to two years before traditional diagnosis.

RenalTech™ is the result of a complex research question that WALTHAM was in a unique position to answer due to the number of detailed veterinary records needed. Access to large data sets allows data scientists to use computers to search for patterns that can predict an event occurring in the future. In this case, historic health records spanning 20 years from 750,000 veterinary hospital visits for over 150,000 cats were examined to hunt for changes that were characteristic of the pets that were known to go on to develop CKD, when compared to those who remained healthy. This approach also allows for these predictive patterns to be tested to determine how accurate the diagnosis is. For the RenalTech™ tool, they found the accuracy was greater than 95 percent.

“When we looked at the historic data from thousands of pets, it was clear that the data had a story to tell” explains Richard Bradley, author and Data Science Technical Lead at WALTHAM. 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.”

The exciting additional element to this project is that whilst a biomarker with such high accuracy was identified, a product solution has also been delivered through fellow Mars Petcare family members, Antech Diagnostics.

What does this mean to veterinarians?
“This is a paradigm shifting moment for veterinary medicine” says Jonathan Elliott, MA, Vet MB, PhD, Cert SAC, Dip ECVPT, MRCVS and Vice Principal for Research and Innovation at the University of London Royal Veterinary College and partner in the development of the tool. “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.”

What else does the future hold?
The approach taken to develop the RenalTech™ tool signals the beginning of a new wave of predictive diagnostics. There are many more diseases and conditions that in future may be managed proactively, allowing veterinarians and pet owners together extend the health span of their pets.

Listen to Kay O'Donnell as she explains how his new tool is giving veterinarians "a 2-year head start":



Read more about Mars Petcare’s ambition for preventive health care.

Further Reading
Bradley et al. 2019. Predicting early risk of chronic kidney disease in cats using routine clinical laboratory tests and machine learning. Journal of Veterinary Internal Medicine. https://doi.org/10.1111/jvim.15623
RenalTech tool


Read more on preventive health