Related Experiment Video
Updated: Feb 23, 2026
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
Published on: April 14, 2023
Effective Heart Disease Detection Based on Quantitative Computerized Traditional Chinese Medicine Using
Ting Shu1, Bob Zhang1, Yuan Yan Tang1
1Department of Computer and Information Science, University of Macau, Taipa, Macau.
Insights
This study introduces a noninvasive method using facial images to detect heart disease. The novel approach analyzes facial color features, achieving high accuracy and offering a faster, less invasive alternative to traditional diagnostics.
Area of Science:
- Biomedical Engineering
- Medical Imaging
- Traditional Chinese Medicine
Background:
- Heart disease remains the leading global cause of mortality.
- Current diagnostic methods (e.g., blood tests, ECG, CT, MRI) are often time-consuming and invasive.
- There is a need for efficient, noninvasive heart disease detection techniques.
Purpose of the Study:
- To propose and validate a noninvasive computerized method for quantitative heart disease detection using facial images.
- To explore the application of Traditional Chinese Medicine principles in facial analysis for disease detection.
- To optimize and evaluate a specific machine learning classifier for this task.
Main Methods:
- Extraction of facial key block color features from digital images.
- Utilizing the Probabilistic Collaborative Representation Based Classifier (PCRBC) for analysis.
- Parameter optimization of the PCRBC was performed.
- Experimentation on a dataset of 581 heart disease and 581 healthy individuals.
Main Results:
- The proposed facial image analysis method achieved the highest accuracy compared to other classifiers.
- The PCRBC demonstrated effectiveness in quantitative heart disease detection.
- Facial key block color features derived from Traditional Chinese Medicine principles were found to be informative.
Conclusions:
- The developed noninvasive method based on facial image analysis is effective for heart disease detection.
- This approach offers a promising, less invasive, and potentially faster alternative to traditional diagnostic tools.
- Further research can explore broader applications of facial analysis in cardiovascular health assessment.
Abstract:
At present, heart disease is the number one cause of death worldwide. Traditionally, heart disease is commonly detected using blood tests, electrocardiogram, cardiac computerized tomography scan, cardiac magnetic resonance imaging, and so on. However, these traditional diagnostic methods are time consuming and/or invasive. In this paper, we propose an effective noninvasive computerized method based on facial images to quantitatively detect heart disease. Specifically, facial key block color features are extracted from facial images and analyzed using the Probabilistic Collaborative Representation Based Classifier. The idea of facial key block color analysis is founded in Traditional Chinese Medicine. A new dataset consisting of 581 heart disease and 581 healthy samples was experimented by the proposed method. In order to optimize the Probabilistic Collaborative Representation Based Classifier, an analysis of its parameters was performed. According to the experimental results, the proposed method obtains the highest accuracy compared with other classifiers and is proven to be effective at heart disease detection.
More Related Videos
04:27Author Spotlight: Advantages of Pressure-Volume Loop Measurement Method in Cardiovascular Research
Published on: January 12, 2024
04:09Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
Published on: October 10, 2018
Related Concept Videos
01:30Heart Failure IV: Classification and Diagnostic Evaluation
01:25Imaging Studies for Cardiovascular System VI: Calcium -Scoring CT