Examining the human tongue for indicators of disease, a 2000-year-old technique of Chinese herbalists, is now being embraced by computer scientists utilizing machine learning and artificial intelligence. Tongue diagnostic systems are rapidly gaining traction as remote health monitoring becomes more prevalent around the world, and a study conducted by Iraqi and Australian researchers adds to the growing accuracy of this technology in detecting disease.
Engineers from Baghdad’s Middle Technical University (MTU) and Adelaide’s University of South Australia (UniSA) utilized a USB web camera and computer to record photographs of the tongues of 50 patients with diabetes, renal failure, and anaemia, and then compared the colors to a database of 9000 tongue images.
When compared to laboratory results, they properly diagnosed the disorders in 94% of cases using image processing techniques. A voicemail describing the tongue color and condition was also delivered to the patient or designated health provider via text message.
Computerized tongue analysis is highly accurate and could aid in the remote diagnosis of diseases in a safe, effective, simple, painless, and cost-effective manner. This is especially important in the aftermath of a worldwide epidemic like COVID, where access to health care may be limited.
Ali Al-Naji
In a new work published in the AIP Conference Proceedings, MTU and UniSA Adjunct Associate Professor Ali Al-Naji and his colleagues examined global developments in computer-aided disease diagnosis based on tongue color.
“Thousands of years ago, Chinese medicine pioneered the practice of examining the tongue to detect illness,” Al-Naji, the associate professor of Chinese medicine, explains.
“Conventional medicine has long endorsed this method, demonstrating that the colour, shape, and thickness of the tongue can reveal signs of diabetes, liver issues, circulatory and digestive problems, as well as blood and heart diseases. Taking this a step further, new methods for diagnosing disease from the tongue’s appearance are now being done remotely using artificial intelligence and a camera – even a smartphone.”
“Computerized tongue analysis is highly accurate and could aid in the remote diagnosis of diseases in a safe, effective, simple, painless, and cost-effective manner. This is especially important in the aftermath of a worldwide epidemic like COVID, where access to health care may be limited.”
Diabetes patients have a yellow tongue, cancer patients have a purple tongue with a thick greasy coating, and acute stroke patients have a red tongue that is frequently crooked.
A 2022 study in Ukraine that used a smartphone to analyze tongue photos of 135 COVID patients found that 64% of patients with light infections had a pale pink tongue, 62% of patients with moderate infections had a red tongue, and 99% of patients with severe COVID infections had a dark red tongue.
Previously, tongue diagnostic devices were used to accurately diagnose appendicitis, diabetes, and thyroid disorders.
“More than ten diseases that cause a visible change in tongue color can be diagnosed with 80% accuracy. We achieved 94% accuracy with three diseases in our study, so there is potential to fine-tune this research even further,” Assoc Prof Al-Naji explains.
