"AI" analyzes human language to detect diseases, the accuracy of the device to distinguish signs of problems reaches 98%

2024-08-19 13:53:45Lifestyle SHKRUAR NGA REDAKSIA VOX

"AI" analyzes human language to detect diseases, the accuracy of the

In recent years, healthcare technology professionals have used artificial intelligence to limit disease in patients quickly and accurately.

Engineering researchers from the Secondary Technical University in Baghdad, Iraq, and the University of South Australia, Adelaide, Australia, trained machine algorithms to distinguish diseases through color analysis of the tongue.

An accuracy rate of 98% was achieved in predicting various diseases when the artificial intelligence algorithm examined the color of the human tongue. According to a statement from the scientists, the model diagnosed diabetes, stroke, anemia, asthma, COVID-19 and a variety of vascular and gastrointestinal problems.

One of the project's authors stated that AI is replicating a 2,000-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 number of health conditions," he added.

People with diabetes usually have a yellow tongue; cancer patients a purple tongue with a fatty coating; while patients with acute heart attacks present with a red tongue with an unusual shape, according to doctors.

Experts trained the system using 5,260 different images with color classes, as well as computer algorithms supported by artificial intelligence to see the color of the tongue regardless of lighting conditions.

To test the system, 60 images of patients' tongues were taken from two teaching hospitals in the Middle East. The model successfully matched tongue color to the diseases diagnosed in those patients in most cases.


Video