Stick out your tongue and say, “AHHH.”
Now, take a picture of it…with your computer camera.
No, we’re not joking.
Your tongue could be key to early disease detection. An AI program can identify ailments from tongue scans with nearly 97% accuracy.
Researchers from Australia and Iraq have developed a cutting-edge system that can diagnose diseases simply by examining the tongue. This innovative approach combines artificial intelligence with traditional Chinese medicine and can potentially transform how we identify illnesses.
For more than two thousand years, traditional Chinese medicine practitioners have been using patients’ tongues to gain insight into their overall health. The tongue’s color, texture, and coating can provide valuable information about the body’s internal condition. A team led by Ali Al-Naji, an adjunct associate professor from Middle Technical University and the University of South Australia, has modernized this ancient practice. They have developed a system that employs machine learning algorithms to analyze tongue images and accurately predict potential health issues.
The system, outlined in a recent paper published in the journal Technologies, combines a simple webcam with sophisticated image processing and artificial intelligence to examine tongue characteristics in real-time.
Think about it.
Imagine you’re not feeling well and trying to figure out if you should go see a doctor. Instead of making an appointment or going to urgent care, you could sit in front of your computer, stick out your tongue, and let the AI do its thing. The system captures an image of the tongue, processes it using various color models, and then compares it to a vast database of tongue images associated with different health conditions.
In a matter of seconds, the system can inform you if your tongue appears healthy or if it shows indications of potential issues, such as diabetes, respiratory problems, or even early stages of certain cancers. It is not intended to substitute a proper medical diagnosis, but it could serve as an early warning system, prompting you to seek professional medical attention when needed.
The researchers trained the system using over 5,000 tongue images, categorizing them into seven different colors: red, yellow, green, blue, gray, white, and pink (the color of a healthy tongue). Each color can indicate various health conditions. For instance, a yellow tongue might suggest diabetes or liver issues, while a purple tongue could be a sign of poor circulation or even certain types of cancer.
Ali Al-Naji says in a statement, “The color, shape, and thickness of the tongue can reveal a litany of health conditions,” Ali Al-Naji says in a statement. “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.”
The system surpasses previous computerized tongue diagnosis attempts because it can adapt to different lighting conditions. Just like lighting can affect how colors appear in photos, it can also impact tongue images. The team trained their algorithms using images taken under various light intensities, creating a system that can accurately evaluate tongue color regardless of ambient lighting.
The researchers tested various machine learning algorithms to determine the most accurate method for classifying tongue colors. The winning technique was Extreme Gradient Boost (XGBoost), which achieved an impressive 98.71% accuracy in identifying tongue colors.
The team conducted a real-world test of their system in hospital settings, examining 60 patients with different conditions at two hospitals in Iraq. The results were impressive: The system correctly diagnosed 58 out of 60 cases, resulting in a real-world accuracy rate of 96.6%.
Of course, as with any new technology, there are limitations and ethical considerations to keep in mind. The researchers emphasized that their system is not meant to replace trained medical professionals. Instead, it is designed to complement them for early detection and monitoring of health issues.
However, the system requires capturing and storing images of people’s tongues, which may be considered sensitive medical information, so it’s crucial to protect and use this data ethically. Despite these concerns, the AI-powered tongue diagnosis system offers enormous potential benefits by combining ancient medical practices with modern technology for quick, non-invasive disease detection.
In the never-ending quest to make healthcare more efficient and accessible, machine learning and AI are an inevitable factor. It’s exciting to see such useful tools coming out so quickly!
Sources:
https://www.mdpi.com/2227-7080/12/7/97
https://www.who.int/health-topics/chronic-respiratory-diseases#tab=tab_1
https://my.clevelandclinic.org/health/diseases/7104-diabetes
https://www.mayoclinic.org/diseases-conditions/liver-problems/symptoms-causes/syc-20374502
https://www.healthline.com/health/poor-circulation-symptoms-causes
https://www.ibm.com/topics/machine-learning-algorithms