Researchers developed an AI algorithm using artificial intelligence.

Researchers develop algorithm that can identify the condition with 99 per cent accuracy

A unique screening tool for Addison’s disease hailed to be ’superior to any other’, has been developed by researchers at the University of California Davis School of Veterinary Medicine.


In a new study published in the Domestic Animal Endocrinology Journal, researchers report the development of an algorithm using artificial intelligence (AI) to detect this serious, life-threatening illness in dogs. The scientists created an alert system that utilises information from routine screening tests.


Dr Krystle Regan from UC Davis collaborated with an electrical and computer engineer to develop the algorithm that can detect Addison’s disease with an accuracy rate of greater than 99 per cent.


"The alert should be able to inform veterinarians when Addison’s disease is likely, and prompt further investigation,” she said.

Addison’s is a serious disease that occurs when the adrenal glands fail to produce hormones that are needed to maintain health. However, its wide range of symptoms are similar to those of kidney and intestinal disease, making it incredibly difficult to diagnose.


Blood testing is often performed on sick dogs for the purpose of diagnosis. However, the loss of hormones associated with Addison’s results in subtle irregularities in the blood tests that can be mistaken for other diseases.

In the study, researchers used this routine blood work to identify complex patterns from more than 1,000 dogs previously treated at UC Davis. The program was able to learn these patterns with high accuracy to determine if a dog has Addison’s disease.

“Veterinarians need a safety net to prevent dogs with Addison’s from falling through the cracks,” said Dr Reagan. “This AI program is now that safety net. It has the potential to revolutionise the detection of Addison’s and save many dogs’ lives.”

Owing to the program’s success, the team has already filed a non-provisional patent through the UC Davis Office of Research and plans to license it to large laboratories, whose services are used by most veterinary practices. It is anticipated that the tool will be available for commercial use by the end of 2020.


Furthermore, because Addison’s also affects humans, the researchers are working with physicians and researchers to increase the use of AI to advance human medicine. Scientists say the research also shows ‘great promise’ for the early detection of leptospirosis.