Related Experiment Video
Updated: Jul 13, 2025
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
Published on: April 14, 2023
Machine learning aided non-invasive diagnosis of coronary heart disease based on tongue features fusion
Mengyao Duan1,2, Yiming Zhang3, Yixing Liu4
1School of Life Science, Beijing University of Chinese Medicine, Beijing, China.
Insights
This study introduces a novel, non-invasive method for early coronary heart disease (CHD) diagnosis using tongue images and machine learning. The developed algorithm shows promising accuracy for detecting CHD in hypertensive patients.
Area of Science:
- Medical Informatics
- Artificial Intelligence in Medicine
- Cardiology
Background:
- Coronary heart disease (CHD) is a leading global cause of mortality.
- Hypertension is a primary independent risk factor for CHD.
- Early CHD diagnosis in hypertensive patients is crucial for risk reduction.
Purpose of the Study:
- To develop a non-invasive method for early coronary heart disease (CHD) diagnosis.
- Utilize tongue image features and machine learning (ML) techniques for CHD detection.
- Improve early diagnosis of CHD in patients with hypertension.
Main Methods:
- Collected standard tongue images for analysis.
- Extracted features using the Tongue Diagnosis Analysis System (TDAS) and ResNet-50.
- Developed a customized ML algorithm for non-invasive CHD diagnosis based on tongue features.
Main Results:
- The XGBoost model achieved high performance with fused features.
- Key performance metrics include accuracy (0.869), AUC (0.957), AUPR (0.961), precision (0.926), recall (0.806), and F1-score (0.862).
- Feature fusion enhanced the diagnostic algorithm's effectiveness.
Conclusions:
- A feasible, convenient, and non-invasive method for CHD diagnosis and screening is presented.
- Tongue image analysis shows potential as an effective biomarker for CHD detection.
- This approach can aid in large-scale screening of coronary heart disease.
Background:
Coronary heart disease (CHD) is the first cause of death globally. Hypertension is considered to be the most important independent risk factor for CHD. Early and accurate diagnosis of CHD in patients with hypertension can plays a significant role in reducing the risk and harm of hypertension combined with CHD.
Objective:
To propose a non-invasive method for early diagnosis of coronary heart disease according to tongue image features with the help of machine learning techniques.
Methods:
We collected standard tongue images and extract features by Diagnosis Analysis System (TDAS) and ResNet-50. On the basis of these tongue features, a common machine learning method is used to customize the non-invasive CHD diagnosis algorithm based on tongue image.
Results:
Based on feature fusion, our algorithm has good performance. The results showed that the XGBoost model with fused features had the best performance with accuracy of 0.869, the AUC of 0.957, the AUPR of 0.961, the precision of 0.926, the recall of 0.806, and the F1-score of 0.862.
Conclusion:
We provide a feasible, convenient, and non-invasive method for the diagnosis and large-scale screening of CHD. Tongue image information is a possible effective marker for the diagnosis of CHD.
Related Concept Videos
01:26Assessment of the Mouth
Mouth Inspection
The inspection begins with visually examining the mouth for symmetry, color, and size.
01:30Coronary Artery Disease I: Introduction
01:25Imaging Studies for Cardiovascular System VI: Calcium -Scoring CT