This article is also available in:
עברית (Hebrew)
The AI revolution we are currently part of touches almost every field. In recent years, the healthcare industry has worked hard to harness the power of AI to its advantage, and new discoveries are being made on a regular basis.
Recently, a machine learning-based algorithm that can diagnose diseases based on tongue color with 98% accuracy was developed by engineers at the Middle Technical University (MTU) in Baghdad and the University of South Australia (UniSA) in Adelaide. This innovative algorithm was able to diagnose a wide range of diseases, including diabetes, stroke, anemia, asthma, liver and gallbladder diseases, COVID-19, and a variety of vascular and gastrointestinal problems.
The scientists explain that examining the tongue for signs of disease has been a practice in traditional Chinese medicine for centuries, and that examining its color, shape and thickness can reveal many health conditions.
The AI model was trained on 5260 images. It was trained using multiple machine learning algorithms to predict tongue color under different lighting conditions, using different saturations and five color space models (RGB, YcbCr, HSV, LAB, and YIQ).
In tests, the system was able to identify the correct diseases in most of the 60 tongue images of patients from two hospitals in the Middle East. The cameras were placed 20 centimeters from the patients’ tongues.
This study is an interesting milestone in terms of real-time initial diagnosis of patients. Hospitals are often overcrowded and waiting times are often very long. If such technology were implemented in an app that allows patients to receive an initial diagnosis from a photo they take at home with their smartphone, queues could potentially become shorter and doctors would have to spend less time diagnosing various diseases. This highlights the impact that AI could have on the field of medicine, helping patients and doctors alike.
The study was published in the journal Technologies.
