Health Australia (Commonwealth Union) – The practice of tongue inspection in traditional Chinese medicine (TCM) is an ancient diagnostic method that dates back thousands of years. This holistic approach to health assessment has stood the test of time and is still widely used in Chinese health practices today. This article explores the history, techniques, and significance of tongue inspection in Chinese health.
Tongue inspection as a diagnostic tool can be traced back to the earliest Chinese medical texts. Ancient Chinese physicians observed that the tongue’s appearance and coating provided valuable insights into a person’s overall health. Over centuries, this practice has been refined and incorporated into TCM, becoming an integral part of the diagnostic process.
This 2000-year-old tradition employed by Chinese herbalists, involving the analysis of the human tongue for indications of disease, is now finding favor among computer scientists harnessing machine learning and artificial intelligence.
The utilization of tongue diagnostic systems is rapidly gaining momentum, primarily driven by the global surge in remote health monitoring. A study conducted by researchers from Iraq and Australia further substantiates the increasing accuracy of this technology in disease detection according to researchers of a recent study.
Engineers from the Middle Technical University (MTU) in Baghdad and the University of South Australia (UniSA) employed a USB web camera and a computer to capture images of the tongues of 50 patients afflicted with diabetes, renal failure, and anemia. These images were then compared with a database of 9000 tongue images, using advanced image processing techniques. Remarkably, they achieved a 94 percent accuracy rate in diagnosing the diseases, surpassing traditional laboratory results. Additionally, a voicemail was dispatched, conveying both the tongue’s color and the identified disease via text message to the patient or their designated healthcare provider.
Professor Ali Al-Naji, an Adjunct Associate at MTU and UniSA, and his fellow researchers have summarized the global advancements in computer-aided disease diagnosis based on tongue color in a newly published paper within the AIP Conference Proceedings.
Associate Professor Al-Naji indicated that history points out to us, that a millennia ago, Chinese medicine blazed a trail in the practice of tongue examination for the detection of illnesses.
“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.
“Computerised tongue analysis is highly accurate and could help diagnose diseases remotely in a safe, effective, easy, painless, and cost-effective way. This is especially relevant in the wake of a global pandemic like COVID, where access to health centres can be compromised.”
Diabetes patients often exhibit a yellowish tongue, while cancer patients tend to display a purple tongue covered in a thick, greasy coating. Acute stroke patients, on the other hand, typically present with a red tongue that may appear crooked.
In a 2022 study conducted in Ukraine, researchers examined tongue images from 135 COVID patients using a smartphone. The findings revealed that 64% of patients with mild COVID infections had a pale pink tongue, 62% of those with moderate infections displayed a red tongue, and 99% of patients with severe COVID infections exhibited a dark red tongue.
Prior investigations utilizing tongue diagnostic systems have successfully identified conditions such as appendicitis, diabetes, and thyroid disease.
According to Associate Professor Al-Naji, it is feasible to diagnose more than 10 diseases that manifest as visible changes in tongue color with an accuracy rate of 80 percent. In their study, they achieved a 94 percent accuracy in diagnosing three diseases, indicating the potential for further refinement of this research.
