The Incredible Breakthrough in Disease Diagnosis: Predicting Illness with a Tongue

Imagine being able to know if you have diabetes, stroke, anaemia, asthma, or even COVID-19, just by looking at the colour of your tongue. Thanks to a groundbreaking computer algorithm developed by Iraqi and Australian researchers, this may soon become a reality. With an impressive 98% accuracy rate, this innovative imaging system has the potential to revolutionize the field of medicine.

The team of engineering researchers from Middle Technical University (MTU) and the University of South Australia (UniSA) managed to achieve this remarkable feat through a series of experiments using 5260 images to train machine learning algorithms to detect tongue colour. Two teaching hospitals in the Middle East provided the researchers with 60 tongue images from patients with various health conditions, and the AI model was able to accurately match the tongue colour with the disease in almost all cases.

Their findings were recently published in the scientific journal Technologies, outlining how this new system can analyze tongue colour to provide instant diagnosis. Senior author, MTU and UniSA Adjunct Associate Professor Ali Al-Naji, points out the historical significance of this method, stating that AI is emulating a practice that has been used for over 2000 years in traditional Chinese medicine—examining the tongue for signs of disease.

“The colour, shape, and thickness of the tongue can reveal a litany of health conditions,” says Professor Al-Naji. “For example, people with diabetes typically have a yellow tongue, while cancer patients may present with a purple tongue with a thick greasy coating. An acute stroke can result in an unusually shaped red tongue, and a white tongue can indicate anaemia. The colour of the tongue can even provide insights into severe cases of COVID-19, with a deep red tongue often observed. Indigo or violet coloured tongues may signal vascular and gastrointestinal issues or asthma.”

The imaging system, which involves cameras placed 20 centimetres from the patient to capture their tongue colour, is able to predict their health condition in real time. Co-author UniSA Professor Javaan Chahl envisions a future where this technology can be integrated into smartphones for easy and convenient disease diagnosis.

“Computerized tongue analysis is proving to be a secure, efficient, user-friendly, and affordable method for disease screening that combines modern technology with ancient wisdom,” says Prof Chahl.