The tongue: Highly effective disease-identifying tool that's right in your mouth


The tongue helps savour life but it could also help save lives. A study by researchers from the Middle Technical University (MTU) in Baghdad and the University of South Australia (UniSA) now provides evidence of the remarkable accuracy of employing the tongue diagnostic system in detecting diseases.

The practice rooted in Chinese herbal medicine for over two millennia has found itself at the forefront of modern health care, thanks to artificial intelligence (AI).

Using machine learning to analyse images of tongues, computer scientists correctly diagnosed diseases in 94 per cent of cases compared with laboratory testing.

The research compared colours from a database of 9,000 tongue images with photos from 50 patients with diabetes, renal failure and anaemia.

The system automatically generated voicemails specifying the patient’s tongue colour and the detected disease, which were sent as text messages to either the patient or their designated healthcare provider.

“Thousands of years ago, Chinese medicine pioneered the practice of examining the tongue to detect illness,” MTU and UniSA Adjunct Associate Professor Ali Al-Naji said. “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.”

Diabetes patients typically have a yellow tongue, while cancer patients a purple tongue with a thick greasy coating and acute stroke patients present with a red tongue that is often crooked. Incorporating such AI technology opens up the possibility for diagnosing diseases remotely and can even be done using just a smartphone. In the spirit of Universal Healthcare, such diagnostic technology is at the backbone of affordability, improved patient outcomes and a more efficient and effective healthcare system.

“Computerised tongue analysis is highly accurate and could help diagnose diseases remotely in a safe, effective, easy, painless, and cost-effective way,” Prof Al-Naji said.

“This is especially relevant in the wake of a global pandemic like Covid-19, where access to health centres can be compromised. This would then aid in delivering medical care where needed,” Al-Naji explains, further elaborating on the evolution of this ancient practice in the digital age.

Previous studies have found tongue analysis can also be used to diagnose appendicitis and thyroid disease.

A separate study in Ukraine in 2022 examined tongue images of 135 COVID-19 patients using a smartphone. The results revealed that 64 per cent of mild infection cases correlated with a pale pink tongue, 62 per cent of moderate cases showed a red tongue, and a striking 99 per cent of severe COVID infections featured a dark red tongue.

“It is possible to diagnose with over 80 per cent accuracy more than ten diseases that cause a visible change in tongue colour. In this study, we achieved a 94 percent accuracy with three diseases, so the potential is there to fine-tune this research even further,” notes Al-Naji.

The study is published in the journal AIP Conference Proceedings.  

[email protected]