AI predicts diseases with 98% accuracy in real-time using tongue color

In the last three years healthcare technology professionals have been using artificial intelligence (AI) to their advantage and using it to narrow down diseases in patients quickly and precisely.

From achieving over 90 percent accuracy in AI predicting lung disease to even general AI models predicting the potential of diseases even before conventional diagnoses have been made, the technology has developed at a fast pace today.

Now, engineering researchers from Middle Technical University (MTU) in Baghdad, Iraq, and the University of South Australia (UniSA), Adelaide, Australia accomplished a breakthrough in training machine learning algorithms to spot diseases via tongue color analysis.

A 98 percent accuracy rate was achieved in predicting different diseases when the AI algorithm examined the color of the human tongue.

AI diagnosed diabetes, stroke, COVID-19

According to a statement by the scientists, the AI model diagnosed diabetes, stroke, anemia, asthma, liver and gallbladder conditions, COVID-19, and a range of vascular and gastrointestinal issues.

Ali Al-Naji, senior author, MTU, and UniSA Adjunct associate professor, stated that AI is replicating a 2000-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 added.

“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.”

Al-Naji also noted that 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.

AI model trained with 5260 images

Therefore, experts trained the computer vision systems equipped with a new imaging system by using 5260 images distinguished with seen classes of colors – red, yellow, green, blue, gray, white, and pink.

Six machine-learning algorithms were used to train the AI-backed computer algorithms to predict tongue color in any lighting conditions.

These systems are – the naïve Bayes (NB), support vector machine (SVM), k-nearest neighbors (KNN), decision trees (DTs), random forest (RF), and Extreme Gradient Boost (XGBoost) methods,

The authors stated in the study that the research proposes a new AI image system to analyze and extract tongue color features at different color saturations and under different light conditions from five color space models (RGB, YcbCr, HSV, LAB, and YIQ).

To test the system, 60 images of patients’ tongues who were experiencing certain health conditions were sourced from two teaching hospitals in the Middle East.

The AI model successfully matched the tongue color to the diseases diagnosed in those patients in most cases, the statement spotlighted.

Additionally, to capture the images of the patient’s tongue, the cameras were positioned 20 centimeters apart from the fleshy muscular organ.

Real-time diagnosis

This confirmed that AI could indeed advance the field of medicine by detecting diseases faster and providing an on-the-spot diagnosis by scrutinizing tongue colors imminently.

The real-time diagnosis could make lines move faster and reduce wait time in hospitals. While validating the patients’ diseases might be needed by a human, however, the AI model would help professionals confirm the diagnosis faster.

Javaan Chahl, a co-author from UniSA and a professor stated 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,” he says.

The study was published in the journal – Technologies .