2024-08-28 04:00:04
Analyzing the color of the tongue to diagnose diseases could well become a medical reality. Indeed, researchers from the Middle East Technical University (MTU) in Iraq and the University of South Australia (UniSA) have put to the test point a system ofimaging assisted by artificial intelligence (AI) capable of detecting multiple diseases with 98% accuracy.
Reconstruction results. The top block shows ten examples from the B2G dataset (GAN-generated stimuli), and the bottom block shows ten examples from the GOD dataset (natural stimuli). The first rows show the original stimuli, the middle rows the reconstructions by the PAM model (P), and the last rows the reconstructions by the linear decoder (L).
This technology is based on an ancient practice in Chinese medicine, which involves examining the tongue to assess the condition of health of a patient. Ali Al-Naji, associate professor at MTU and UniSA, explains that the colorthe shape and thickness of the tongue are key indicators of many medical conditions. For example, a tongue jaune could reveal a diabeteswhile a purple tongue with a thick coating could indicate a cancer. In addition, a language rouge unusually formed is often associated with strokes.
The researchers trained their algorithm using 5,260 images of tongues from two hospitals in the Middle East, where patients had various health conditions. By analyzing these images, the AI model learned to associate the color of the tongue with the corresponding diseases. In the majority of cases, the results obtained in real time by the AI were almost always accurate.
The team used six machine learning algorithms, including random forests and gradient boosting, to optimize the accuracy of the predictions. They also tuned the system to work under a variety of lighting conditions, leveraging five different color models.
Javaan Chahl, co-author of the study and professor at UniSA, already envisions that this technology could be adapted to a smartphone. This would allow everyone to easily monitor their health through a simple analysis of the tongue. This method thus combines tradition with innovation, offering a solution that is not only fast and effective, but also accessible and inexpensive.
With this advance, AI once again shows its potential in the medical field, not only to speed up diagnoses, but also to offer widely available screening tools. The researchers’ study, published in the journal Technologiesthus paves the way for more preventive and personalized medicine.
1724867472
#diagnoses #diseases #photo #tongue #reliability
