A computer algorithm has achieved a 98% accuracy in predicting different diseases by analysing the colour of the human tongue, say researchers, who suggest the proposed imaging system is able to diagnose diabetes, stroke, anaemia, asthma, liver and gallbladder conditions, Covid-19, and various vascular and gastrointestinal issues.
The engineering researchers from Middle Technical University (MTU) in Baghdad, 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 colour.
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 colour with the disease in almost all cases.
The resultant study, published in Technologies, outlines how the proposed system analyses tongue colour 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 said AI was replicating a 2 000-year-old practice widely used in traditional Chinese medicine – examining the tongue for signs of disease.
“The colour, shape and thickness of the tongue can reveal a litany of health conditions,” he said.
“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 anaemia; people with severe cases of Covid-19 are likely to have a deep red tongue; and an indigo or violet coloured tongue indicates vascular and gastrointestinal issues or asthma.”
In the study, cameras placed 20cm from a patient captured their tongue colour 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 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,” he adds.
Study details
Tongue Disease Prediction Based on Machine Learning Algorithms
Ali Raad Hassoon, Ali Al-Naji, Ghaidaa A. Khalid, Javaan Chahl.
Published in Technologies on 28 June 2024
Abstract
The diagnosis of tongue disease is based on the observation of various tongue characteristics, including colour, shape, texture, and moisture, which indicate the patient’s health status. Tongue colour is one such characteristic that plays a vital function in identifying diseases and the levels of progression of the ailment. With the development of computer vision systems, especially in the field of artificial intelligence, there has been important progress in acquiring, processing, and classifying tongue images. This study proposes a new imaging system to analyse and extract tongue colour features at different saturations and under different light conditions from five colour space models (RGB, YcbCr, HSV, LAB, and YIQ). The proposed imaging system trained 5260 images classified with seven classes (red, yellow, green, blue, grey, white, and pink) using six machine learning algorithms, namely, the naïve Bayes (NB), support vector machine (SVM), k-nearest neighbours (KNN), decision trees (DTs), random forest (RF), and Extreme Gradient Boost (XGBoost) methods, to predict tongue colour under any lighting conditions. The obtained results from the machine learning algorithms illustrated that XGBoost had the highest accuracy at 98.71%, while the NB algorithm had the lowest accuracy, with 91.43%. Based on these obtained results, the XGBoost algorithm was chosen as the classifier of the proposed imaging system and linked with a graphical user interface to predict tongue colour and its related diseases in real time. Thus, this proposed imaging system opens the door for expanded tongue diagnosis within future point-of-care health systems.
Technologies article – Tongue Disease Prediction Based on Machine Learning Algorithms (Open access)
See more from MedicalBrief archives:
AI ‘at best’ on a par with human experts when making image-based diagnoses – review
AI application to predict and diagnose life-threatening diseases