New AI Tongue Scanner Achieves 96% Accuracy in Diagnosing Illnesses

A groundbreaking artificial intelligence (AI) model, drawing on ancient techniques from traditional Chinese medicine, can now diagnose illnesses with remarkable accuracy by analyzing a patient’s tongue. This innovative approach, which combines millennia-old medical practices with modern machine learning technology, has been developed by researchers at the University of South Australia (UniSA) and Iraq’s Middle Technical University (MTU).

Traditional Chinese medicine has long used tongue examination to hint at underlying health conditions, assessing characteristics like color, shape, and coating to detect a range of ailments including cancer, diabetes, and gastrointestinal diseases. The new AI system builds on this foundation by using machine learning to analyze tongue images for signs of illness.

In their study published in the journal ‘Technologies’, the researchers explain that the tongue’s unique features, particularly its color, are linked to internal organ health and can indicate various diseases. “For instance, diabetes is often indicated by a yellow tongue, while a purple tongue with a thick coating could suggest cancer,” noted Ali Al-Naji, the paper’s senior author and an adjunct associate professor at UniSA.

The AI model was trained using over 5,260 images across various tongue colors, saturations, and lighting conditions, alongside real-time training at two Iraqi teaching hospitals. The system then underwent rigorous testing with volunteers who presented their tongues for scanning via a USB webcam.

The results were highly promising, with the AI demonstrating an accuracy rate of 96.6% in detecting different ailments based on tongue color changes. “The proposed system could efficiently detect different ailments that show apparent changes in tongue color,” the researchers highlighted in their study.

This AI tongue scanner represents a potential leap forward in medical diagnostics, offering a non-invasive, efficient, and cost-effective method for disease screening that could soon be integrated into medical facilities globally. The integration of such AI-driven tools in healthcare could significantly enhance early diagnosis and monitoring of various health conditions.