The color, shape, and thickness of the tongue can reveal a whole range of health complaints. (Representative)
New Delhi:
Researchers have developed a new computer algorithm that can predict several diseases, such as diabetes and stroke, by analyzing only the color of the human tongue, with 98 percent accuracy.
The imaging system developed by Middle Technical University (MTU) and the University of South Australia (UniSA) in Australia can diagnose conditions such as diabetes, stroke, anemia, asthma, liver and gallbladder problems, Covid-19 and other vascular and gastrointestinal diseases.
“The colour, shape and thickness of the tongue can reveal a whole range of health problems,” said Ali Al-Naji, associate professor at MTU and UniSA.
“People with diabetes typically have a yellow tongue, cancer patients have a purple tongue with a thick, greasy coating, and patients who have had an acute stroke often have an unusually shaped red tongue,” he added.
The breakthrough was achieved through a series of experiments that used 5,260 images to train machine-learning algorithms to detect tongue color.
Researchers received 60 tongue images from two teaching hospitals in the Middle East, representing patients with a variety of health conditions. The AI model matched tongue color to the correct disease in almost all cases.
The paper, published in Technologies, describes how the system analyzes tongue color to make real-time diagnoses, showing that AI can significantly improve medical practice.
Al-Naji explained that AI mimics a 2,000-year-old technique from traditional Chinese medicine, which uses the color, shape and thickness of the tongue to diagnose health problems.
For example, people with diabetes typically have a yellow tongue, while cancer patients have a purple tongue with a thick, greasy coating. Stroke patients often present with an unusually shaped red tongue. A white tongue can indicate anemia, severe cases of Covid-19 are associated with a deep red tongue, and an indigo or violet tongue indicates vascular or gastrointestinal problems or asthma.
The study involved placing cameras 20 centimeters away from the patient to record the color of the tongue. The imaging system then predicted the health status in real time.
Study co-author, Professor Javaan Chahl from UniSA, noted that this technology could eventually be adapted for use with smartphones, making disease screening more accessible.
(Except for the headline, this story has not been edited by DailyExpertNews staff and is published via a syndicated feed.)
