This technology could be amazing!
Researchers in Iraq and Australia say they have developed a computer algorithm that can analyze the color of a person’s tongue to determine their health in real time – with 98% accuracy.
“Typically, diabetics have a yellow tongue, cancer patients have a purple tongue with a thick, fatty coating, and patients with an acute stroke have an unusually shaped red tongue,” explains lead study author Ali Al-Naji, who teaches at the Middle Technical University in Baghdad and the University of South Australia.
“A white tongue may indicate anemia; people with severe cases of COVID-19 are likely to have a deep red tongue,” Al-Naji continued. “An indigo or purple-colored tongue indicates vascular and gastrointestinal problems or asthma.”
Al-Naji says his proposed imaging system mimics the traditional Chinese medicine practice of examining the tongue for signs of disease.
5,260 images were used to train the artificial intelligence model to recognize tongue color and the corresponding condition. The researchers tested it with 60 tongue images from two teaching hospitals in the Middle East.
The patients sat about 20 centimeters away from a laptop equipped with a webcam that took a picture of their tongue. The program was able to detect the disease in almost all cases.
The results were published in the journal Technologies.
Study co-author Javaan Chahl, a professor at the University of South Australia, says the technology will ultimately be used for a smartphone app that can diagnose diabetes, stroke, anemia, asthma, liver and gallbladder problems, COVID-19 and other diseases.
“These results confirm that computer-assisted tongue analysis is a safe, efficient, user-friendly and cost-effective method for disease prevention that complements modern methods with a centuries-old practice,” said Chahl.
There are still some hurdles to overcome, including patient reluctance to provide data and reflections captured by the camera that mislead the algorithm.
A review of five years of AI-powered tongue image analysis in 2023 also raised concerns that researchers would have to create their own data sets because there was no definitive dataset.
However, the technology was found to have “enormous value” in diagnosing and treating diseases.
