98% accuracy in predicting diseases by the colour of the tongue
Researchers developed a computer algorithm that diagnoses diseases with 98% accuracy by analyzing tongue color, identifying conditions like diabetes and COVID-19, and envisioning smartphone-based diagnostics for real-time analysis.
Read original article
A recent study by researchers from Middle Technical University and the University of South Australia has developed a computer algorithm capable of diagnosing various diseases with 98% accuracy by analyzing the color of the human tongue. This innovative imaging system can identify conditions such as diabetes, stroke, anemia, asthma, liver and gallbladder diseases, COVID-19, and other vascular and gastrointestinal issues. The algorithm was trained using 5,260 images, including 60 from patients with diverse health conditions. The AI model successfully correlated tongue color with specific diseases, replicating a practice from traditional Chinese medicine that has been in use for over 2,000 years. The study suggests that the color, shape, and thickness of the tongue can provide significant health insights. For instance, a yellow tongue may indicate diabetes, while a purple tongue could suggest cancer. The researchers envision a future where smartphones could be used for real-time disease diagnosis through tongue analysis, making this method a secure, efficient, and affordable option for disease screening.
- A computer algorithm can diagnose diseases with 98% accuracy by analyzing tongue color.
- The system can identify conditions like diabetes, stroke, and COVID-19.
- The research combines modern technology with traditional Chinese medicine practices.
- Future applications may include smartphone-based diagnostics.
- The study highlights the potential of AI in advancing medical diagnostics.
Related
Study reveals why AI models that analyze medical images can be biased
A study by MIT researchers uncovers biases in AI models analyzing medical images, accurately predicting patient race from X-rays but showing fairness gaps in diagnosing diverse groups. Efforts to debias models vary in effectiveness.
It's not just hype. AI could revolutionize diagnosis in medicine
Artificial intelligence (AI) enhances medical diagnosis by detecting subtle patterns in data, improving accuracy in identifying illnesses like strokes and sepsis. Challenges like costs and data privacy hinder widespread adoption, requiring increased financial support and government involvement. AI's potential to analyze healthcare data offers a significant opportunity to improve diagnostic accuracy and save lives, emphasizing the importance of investing in AI technology for enhanced healthcare outcomes.
A Blood Test Accurately Diagnosed Alzheimer's 90% of the Time, Study Finds
A study in JAMA shows a blood test can diagnose Alzheimer’s disease with 90% accuracy, outperforming traditional methods. It may lead to routine cognitive impairment screenings in primary care. Further validation is needed.
A Blood Test Accurately Diagnosed Alzheimer's 90% of the Time, Study Finds
Researchers developed a blood test diagnosing Alzheimer’s with 90% accuracy, outperforming traditional methods. It may standardize cognitive impairment screening but should only be used for symptomatic individuals. Further validation is needed.
Simple Diagnostics for Common Diseases
A study has developed a diagnostic method using infrared light and machine learning to detect metabolic disorders from a single blood sample, achieving high accuracy and promising early detection potential.
3 comments> This study proposes a new imaging system to analyze and extract tongue color features at different color saturations and under different light conditions from five color space models (RGB, YcbCr, HSV, LAB, and YIQ). The proposed imaging system trained 5260 images classified with seven classes (red, yellow, green, blue, gray, white, and pink) using six machine learning algorithms, namely, the naïve Bayes (NB), support vector machine (SVM), k-nearest neighbors (KNN), decision trees (DTs), random forest (RF), and Extreme Gradient Boost (XGBoost) methods, to predict tongue color under any lighting conditions. The obtained results from the machine learning algorithms illustrated that XGBoost had the highest accuracy at 98.71%, while the NB algorithm had the lowest accuracy, with 91.43%
Related
Study reveals why AI models that analyze medical images can be biased
A study by MIT researchers uncovers biases in AI models analyzing medical images, accurately predicting patient race from X-rays but showing fairness gaps in diagnosing diverse groups. Efforts to debias models vary in effectiveness.
It's not just hype. AI could revolutionize diagnosis in medicine
Artificial intelligence (AI) enhances medical diagnosis by detecting subtle patterns in data, improving accuracy in identifying illnesses like strokes and sepsis. Challenges like costs and data privacy hinder widespread adoption, requiring increased financial support and government involvement. AI's potential to analyze healthcare data offers a significant opportunity to improve diagnostic accuracy and save lives, emphasizing the importance of investing in AI technology for enhanced healthcare outcomes.
A Blood Test Accurately Diagnosed Alzheimer's 90% of the Time, Study Finds
A study in JAMA shows a blood test can diagnose Alzheimer’s disease with 90% accuracy, outperforming traditional methods. It may lead to routine cognitive impairment screenings in primary care. Further validation is needed.
A Blood Test Accurately Diagnosed Alzheimer's 90% of the Time, Study Finds
Researchers developed a blood test diagnosing Alzheimer’s with 90% accuracy, outperforming traditional methods. It may standardize cognitive impairment screening but should only be used for symptomatic individuals. Further validation is needed.
Simple Diagnostics for Common Diseases
A study has developed a diagnostic method using infrared light and machine learning to detect metabolic disorders from a single blood sample, achieving high accuracy and promising early detection potential.