AI Model Analyzes Tongue Images to Detect Medical Conditions with 98% Accuracy

AI model to analyse tongue, detect medical conditions with 98% accuracy

The tongue can say a lot about our health. The colour and texture of the tongue can give away the underlying diseases that we are suffering from. Using this information, researchers in Iraq and Australia developed an AI model that can help in detecting diseases and conditions by analysing the tongue. The AI model can determine the diseases with an accuracy rate of 98%. Senior study author Ali Al-Naji, who teaches at Middle Technical University in Baghdad and the University of South Australia explained how the AI model works - he said that people with diabetes have yellow tongue, while cancer patients have a purple tongue with a thick greasy coating. Acute stroke patients usually have a red tongue with an unusual shape. Anaemia can be determined by a white tongue, while severe cases of COVID-19 can be determined by a deep red tongue. Vascular, gastrointestinal or asthma issues are determined by indigo- or violet-coloured tongue. ALSO READ: Does tongue position contribute to health? Here's what experts say The study is based on the traditional Chinese medical practice of determining the medical conditions by examining the tongue, added Ali Al-Naji. The artificial intelligence model was trained with 5200 images to determine the colour and texture of the tongue and understand the underlying medical conditions. 60 tongue images from two teaching hospitals in the Middle East were used for testing the accuracy of the AI model. Javaan Chahl, a professor at the University of South Australia and co-author of the study added that soon the AI model will be used as a smartphone app to determine various diseases - diabetes, stroke, anemia, asthma, liver issues, gallbladder problems and COVID-19. This will also ensure the accessibility of the AI model for everyone. "These results confirm that computerised tongue analysis is a secure, efficient, user-friendly and affordable method for disease screening that backs up modern methods with a centuries-old practice," Javaan Chahl said.

Algorithm achieves 98% accuracy in disease prediction via tongue color

A computer algorithm has achieved 98% accuracy in predicting different diseases by analyzing the color of the human tongue. The proposed imaging system developed by Iraqi and Australian researchers can diagnose diabetes, stroke, anemia, asthma, liver and gallbladder conditions, COVID-19, and a range of vascular and gastrointestinal issues. Engineering researchers from Middle Technical University (MTU) and the University of South Australia (UniSA) achieved the breakthrough in a series of experiments where they used 5,260 images to train machine learning algorithms to detect tongue color. Two teaching hospitals in the Middle East supplied 60 tongue images from patients with various health conditions. The artificial intelligence (AI) model was able to match the tongue color with the disease in almost all cases. A paper published in Technologies outlines how the proposed system analyzes tongue color to provide on-the-spot diagnosis, confirming that AI holds the key to many advances in medicine. Senior author, MTU and UniSA Adjunct Associate Professor Ali Al-Naji, says AI is replicating 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 litany of health conditions," he says. "Typically, people with diabetes have a yellow tongue; cancer patients a purple tongue with a thick greasy coating; and acute stroke patients present with an unusually shaped red tongue. "A white tongue can indicate anemia; people with severe cases of COVID-19 are likely to have a deep red tongue; and an indigo or violet colored tongue indicates vascular and gastrointestinal issues or asthma." In the study, cameras placed 20 centimeters from a patient captured their tongue color and the imaging system predicted their health condition in real time. Co-author UniSA Professor Javaan Chahl says that down the track, a smartphone will be used to diagnose disease in this way. "These results confirm that computerized tongue analysis is a secure, efficient, user-friendly and affordable method for disease screening that backs up modern methods with a centuries-old practice," Prof Chahl says.

AI model to detect diabetes, stroke, COVID with 98% accuracy by studying the color, shape of tongue - Times of India

Researchers at Middle Technical University and University of South Australia developed an AI imaging system capable of diagnosing various diseases by analyzing the tongue's appearance. The system identifies conditions such as diabetes, cancer, and Covid-19 by evaluating tongue color and other features. The study, published in Technologies journal, showcased a 96.6% diagnostic accuracy rate.

Why Google symptoms? New AI model can detect diseases just by looking at your tongue!

A new AI model analyses tongue color with 98% accuracy to predict what disease you have, using 5,260 tongue images to match colors with specific health issues, and could soon be available as a smartphone app. Do you often find yourself Googling every minor symptom, only to end up convinced you have cancer or some other serious illness? If that sounds like you, this new AI model might be just what you need. And no, we're not being tongue-in-cheek -- but this AI model does require you to stick out your tongue to accurately predict what disease you might have. Researchers from Iraq and Australia have developed a computer algorithm that can analyse tongue color to detect medical conditions with 98% accuracy. They trained the AI model using 5,260 images to match tongue colors with specific health issues. This study builds on the traditional Chinese medicine practice of tongue examination, which assesses various characteristics such as color, shape, texture, and moisture to diagnose diseases. The new technology leverages computer vision and artificial intelligence to enhance this process. Credit: Unsplash Co-author of the study Javaan Chahl envisions integrating this technology into a smartphone app, which will eventually help diagnose a range of conditions, including diabetes, stroke, anemia, asthma, liver and gallbladder problems, and COVID-19. "These results confirm that computerized tongue analysis is a secure, efficient, user-friendly and affordable method for disease screening that backs up modern methods with a centuries-old practice," Chahl said.