AI scanner will diagnose the disease by looking at the tongue

Science and Technology Desk: Diagnosing diseases by looking at the tongue is an ancient method. This thousand-year-old method is used by modern-day doctors as well. However, doctors can now diagnose diseases with a new type of AI tongue scanner instead of looking with the naked eye. Recent

Science and Technology Desk: Diagnosing diseases by looking at the tongue is an ancient method. This thousand-year-old method is used by modern-day doctors as well. However, doctors can now diagnose diseases with a new type of AI tongue scanner instead of looking with the naked eye. Recently, researchers have developed a machine learning model that can diagnose diseases by looking at the human tongue. This computer algorithm has achieved 98% accuracy in diagnosing various diseases by analyzing the color of human tongue. The imaging system developed by Iraqi and Australian researchers can diagnose diabetes, stroke, anemia, asthma, liver and gallbladder conditions, Covid-19 and various vascular and gastrointestinal problems.

tongue

The research team said that the color of the human tongue is the most important in diagnosing the disease. A team of joint engineering researchers from the University of South Australia and Iraq's Middle Technical University (MTU) recently published a paper in the journal Technologies. They present a machine learning program there. Similar to visual machine learning algorithmic programs, the research team developed their own system by training on two data sets.


First, they provided 5260 images spanning seven colors across different saturation and lighting conditions of the tongue. It has pictures of the color and condition of the tongue during different health conditions. Moreover, images of healthy human tongues are also input. Diagnoses include tongue pictures of a mix of disease conditions, including mycotic infections, asthma, covid-19, fungal papillitis, and anemia.

To test the entire system, the researchers captured the color of their tongue with a camera placed 20 centimeters away from the patient. Both healthy and diseased human tongues were examined using a computer web cam. This imaging system was able to diagnose the disease with 98 percent accuracy. They used 60 tongue images to diagnose the disease. Such a white tongue can indicate anemia; People with severe cases of Covid-19 are likely to have a red tongue; And a blue or purple tongue indicates vascular and gastrointestinal problems or asthma.

According to the researchers, they believe that this AI system can be a “safe, efficient, user-friendly diagnosis method.” The system will also be able to diagnose diseases with the help of a smart phone camera.


Monirul Islam

1044 Blog posts

Comments