Algorithm Trained by Researchers to Detect Disease Patterns by Scanning Tongue
According to Chinese medicine, a new technology is showing promise for disease diagnosis.
Researchers have utilized over 5,000 images of tongues to train an AI algorithm in the traditional method of disease diagnosis.
“One of the most fascinating findings from our research is that the color of the tongue can accurately reflect internal illnesses,” shared Ali Al-Naji, a senior author of the study and adjunct associate professor at the University of South Australia (UniSA), with The Epoch Times via email.
“Through analyzing the color of the tongue, we have identified various health conditions, showcasing the potential of this approach for non-invasive diagnosis,” he explained.
The algorithm has demonstrated a 98 percent accuracy rate in detecting illnesses. Diseases such as diabetes, stroke, appendicitis, gastrointestinal issues, and cancer have been identified based on the color of the tongue.
Study Specifics
The study outlines how the human tongue possesses distinct features linked to the body’s internal organs, such as color, shape, and thickness, allowing for successful disease detection and tracking.
“The tongue can provide indications of overall health and various illnesses by reflecting changes in the body’s internal state,” Al-Naji shared with The Epoch Times.
Related Stories
- Yellow tongue indicates diabetes.
- Purple tongue with a thick greasy coating is observed in cancer patients.
- Acute stroke patients display an unusually shaped red tongue.
- A white tongue can be a sign of anemia.
- Individuals with severe cases of COVID-19 may have a deep red tongue.
- An indigo or violet-colored tongue suggests vascular and gastrointestinal problems or asthma.
Research engineers from UniSA and Middle Technical University in Iraq utilized 5,260 tongue images to train AI in detecting and analyzing tongue color under different lighting conditions.
Researchers experimented with six machine learning algorithms employing seven color classes (red, yellow, green, blue, gray, white, and pink) to determine the most accurate one, with diagnostic precision ranging from approximately 91 percent to 99 percent. Following the results, the algorithm with the highest accuracy (98.71 percent), named XGBoost, was chosen for the proposed imaging system and integrated into a visual user interface to assess tongue color and associated diseases.
The imaging system was then tested in real-time using 60 tongue images from patients with various health conditions provided by two teaching hospitals in the Middle East. The diseases included diabetes mellitus, mycotic infection, asthma, anemia, fungiform papillae, and COVID-19.
Even the research team was astonished by the precision of the algorithm.
“We were amazed by the system’s accuracy, especially in real-time conditions and under varying lighting. The high accuracy of over 98% in detecting tongue colors surpassed our expectations, indicating the effectiveness of AI in tongue diagnosis,” Al-Naji informed The Epoch Times.
“With our algorithm, we were able to predict multiple diseases related to tongue colors, like diabetes, mycotic infections, asthma, COVID-19, and anemia, by assessing changes in tongue color. Each condition exhibited distinct color patterns that the system was able to accurately detect,” he added.
The study utilized cameras positioned 20 centimeters away from patients to capture their tongue color, with the system analyzing the data to predict their health status in real-time.
UniSA professor and co-author Javaan Chahl believes that smartphones will one day diagnose diseases this way.
“These findings confirm that computerized tongue analysis is a secure, efficient, user-friendly, and cost-effective method for disease screening that complements modern approaches with a centuries-old practice,” Chahl stated in a press release.
Tongue Diagnosis in Chinese Medicine
The above research builds upon an ancient technique utilized in Chinese medicine. In this system, the tongue serves as a crucial diagnostic tool that examines various aspects such as color, shape, coating, and moisture to identify patterns, visualize the condition of internal organs, diagnose illnesses, and forecast their prognosis.
Giovanni Maciocia, who passed away in 2018, was a highly regarded author, lecturer, and practitioner of Chinese medicine. Throughout his career, he authored numerous textbooks on the subject utilized by institutions worldwide—including one on tongue diagnosis.
“Tongue observation is a fundamental aspect of diagnosis as it provides visible clues to the patient’s disharmony. Tongue diagnosis is remarkably reliable: in complex conditions with conflicting manifestations, the tongue almost always reflects the basic underlying pattern,” he wrote in his book “The Foundations of Chinese Medicine.”
Final Thoughts
Regarding when we might expect to see this screening technique in clinics and hospitals, Al-Naji hopes it will be within the next few years.
“While the technology shows potential and promise, further testing, validation, and regulatory approval are required before it can be widely implemented for clinical purposes,” he concluded.
