A researcher demonstrates how a camera takes pictures of the tongue and examines it for diseases. Image credit: Middle Technical University
A computer algorithm has achieved 98% accuracy in predicting various diseases by analyzing the color of the human tongue.
The imaging system, developed by Iraqi and Australian researchers, can diagnose diabetes, stroke, anemia, asthma, liver and gallbladder disease, COVID-19, and a range of vascular and gastrointestinal problems.
Engineering researchers from the Middle Technical University (MTU) and the University of South Australia (UniSA) made the breakthrough in a series of experiments in which they trained machine learning algorithms to recognize tongue color using 5,260 images.
Two teaching hospitals in the Middle East provided 60 tongue images from patients with different health conditions. The artificial intelligence (AI) model was able to match the tongue color to the disease in almost all cases.
An article published in Technologies describes how the proposed system analyzes tongue color to make an instant diagnosis, confirming that AI is key to many advances in medicine.
Lead author Ali Al-Naji, associate professor at MTU and UniSA, says AI mimics a 2,000-year-old practice widely used in traditional Chinese medicine – examining the tongue for signs of disease.
“The color, shape and thickness of the tongue can reveal a whole range of health conditions,” he says.
“Typically, diabetics have a yellow tongue, cancer patients have a purple tongue with a thick, fatty coating, and patients with an acute stroke have an unusually shaped red tongue.”
“A white tongue may indicate anemia; people with severe cases of COVID-19 are likely to have a deep red tongue; and an indigo or purple-colored tongue indicates vascular and gastrointestinal problems or asthma.”
As part of the study, cameras placed 20 centimeters away from the patient captured the color of his tongue and the imaging system predicted his health status in real time.
Co-author and UniSA professor Javaan Chahl says that one day smartphones could be used in this way to diagnose diseases.
“These results confirm that computer-assisted tongue analysis is a safe, efficient, user-friendly and cost-effective method for disease prevention that complements modern methods with a centuries-old practice,” says Prof. Chahl.
Further information:
Ali Raad Hassoon et al, Tongue disease prediction based on machine learning algorithms, Technologies (2024). DOI: 10.3390/technologies12070097
Provided by the University of South Australia
Quote: Algorithm achieves 98% accuracy in disease prediction based on tongue color (August 13, 2024), accessed August 13, 2024 from https://medicalxpress.com/news/2024-08-algorithm-accuracy-disease-tongue.html
This document is subject to copyright. Except for the purposes of private study or research, no part of it may be reproduced without written permission. The contents are for information purposes only.
