According to the university's veterinary team, this screening tool is superior to any other that utilizes routine blood tests available to veterinarians.
Addison’s disease, or hypoadrenocorticism, is a rare, life-threatening illness in dogs that is notoriously difficult to recognize. But veterinarians at the University of California, Davis School of Veterinary Medicine have annouced the development of an algorithm to detect Addison’s disease accurately and more effectively.
Veterinarians teamed up with an electrical and computer engineer to develop the algorithm, which is powered by artificial intelligence (AI), and has reported that the new screening tool has an accuracy rate greater than 99%.
“We set out to create an alert system that uses information from routine screening tests,” Krystle Reagan, DVM, PhD, DACVIM (SAIM), a board-certified small animal internist with the UC Davis veterinary hospital and lead researcher on this tool, said in an article on the UC Davis School of Veterinary Medicine website. “The alert should be able to inform veterinarians when Addison’s disease is likely, and prompt further investigation.”
Often the first tests ordered when a sick dog visits a veterinarian are routine blood tests. The veterinary team used this routine blood work to train their AI program to detect complex patterns from more than 1,000 dogs previously treated at UC Davis. Once the tool analyzes the routine blood tests, it will alert the veterinarian when Addison’s disease is suspected.
The veterinarian can then take further action and give the canine patient an adrenocorticotropic hormone stimulation test—the gold standard to confirm Addison’s disease.
“We see dogs with Addison’s disease come through the clinic, and they’ve been misdiagnosed for two to three years,” Dr. Reagan continued. “Once Addison’s disease is properly detected, though, it is generally easy to treat with an excellent prognosis for the patient.”
Addison’s disease also affects many humans, which the veterinary team notes could be the next step in developing this tool. Dr. Reagan is currently collaborating with physicians and human health researchers on a translational component of the tool to help people with this disease.
The AI program may also surpass just Addison’s disease. UC Davis notes this program has potential to optimize detection of other veterinary diseases, including leptospirosis—a disease in which early diagnosis is crucial and current tests do not work well early in the infection.
According to the article, the Addison’s disease screening tool will be commercially available by the end of 2020.
“Veterinarians need a safety net to prevent dogs with Addison’s from falling through the cracks,” Dr. Reagan said. “This AI program is now that safety net. It has the potential to revolutionize the detection of Addison’s and save many dogs’ lives.”
For a look at the original research, click here.