A revolutionary computer algorithm has achieved a 98% accuracy rate in predicting various diseases by analyzing the colour of the human tongue. Developed by researchers from Iraq and Australia, this advanced imaging system can diagnose a range of health conditions including diabetes, stroke, anaemia, asthma, liver and gallbladder issues, COVID-19, and various vascular and gastrointestinal problems.
DEVELOPMENT AND COLLABORATION
Researchers from Middle Technical University (MTU) in Iraq and the University of South Australia (UniSA) spearheaded this groundbreaking work. They trained machine learning algorithms using 5260 images to detect and analyze tongue colour, achieving remarkable predictive accuracy.
DATA COLLECTION AND TRAINING
Two teaching hospitals in the Middle East contributed 60 images of patients’ tongues, each depicting different health conditions. These images were crucial in training the AI model, which successfully matched tongue colours to specific diseases in almost every case.
A new paper in the journal Technologies details how this innovative system works. The AI model analyzes tongue colour to provide real-time diagnoses, highlighting the potential of AI in advancing medical practices.
HISTORICAL CONTEXT AND METHODOLOGY
Adjunct Associate Professor Ali Al-Naji from MTU and UniSA notes that this AI technology mirrors a 2000-year-old practice from traditional Chinese medicine, where tongue examination is used to diagnose illnesses.
“The colour, shape, and thickness of the tongue can reveal a litany of health conditions,” says Professor Al-Naji.
HEALTH INDICATORS AND TONGUE COLOR
- Diabetes: Yellow tongue
- Cancer: Purple tongue with a thick greasy coating
- Acute Stroke: Unusually shaped red tongue
- Anaemia: White tongue
- Severe COVID-19: Deep red tongue
- Vascular and Gastrointestinal Issues or Asthma: Indigo or violet collared tongue
IMAGING SYSTEM AND REAL-TIME DIAGNOSIS
During the study, cameras positioned 20 centimetres from patients’ tongues captured their colour. The imaging system then predicted their health conditions in real time, showcasing the efficiency and accuracy of this method.
FUTURE APPLICATIONS
Co-author UniSA Professor Javaan Chahl envisions future applications where smart phones could be used for disease diagnosis through tongue colour analysis.
“These results confirm that computerized tongue analysis is a secure, efficient, user-friendly, and affordable method for disease screening, which complements modern medical practices with an ancient technique,” says Professor Chahl.
The collaboration between Iraqi and Australian researchers has yielded a significant breakthrough in medical diagnostics. By harnessing the power of AI to analyze tongue colour, this innovative system promises to revolutionize how diseases are diagnosed, offering a quick, non-invasive, and highly accurate method. As technology advances, the integration of AI in healthcare continues to open new frontiers, merging ancient wisdom with cutting-edge innovation.
FINAL THOUGHTS
The success of this AI model in predicting diseases through tongue colour analysis underscores the potential of combining traditional diagnostic methods with modern technology. With further development and widespread implementation, this approach could become a staple in medical diagnostics, making healthcare more accessible and efficient for everyone.
