A new study published in the open access journal BMJ Health & Care Informatics has found that a combination of facial thermal imaging and artificial intelligence (AI) can accurately predict the presence of coronary artery disease.
Traditional methods of diagnosing coronary heart disease often rely on assessing risk factors, which may not always be accurate. These methods can also be time-consuming and invasive, involving procedures such as ECG readings, angiograms, and blood tests.
In contrast, thermal imaging is a non-invasive technique that captures temperature distribution on the surface of an object by detecting the infrared radiation emitted. It has shown promise in identifying areas of abnormal blood circulation and inflammation through skin temperature patterns.
Researchers conducted a study with 460 participants to develop an AI-assisted imaging model for detecting coronary artery disease using thermal imaging of their faces. The study found that the thermal imaging plus AI approach was more effective in predicting coronary artery disease than traditional risk assessment methods.
Key findings of the study included the importance of variables such as the overall left-right temperature difference of the face, maximal facial temperature, and average facial temperature in predicting the presence of coronary artery disease. Specific features like the average temperature of the left jaw region and temperature ranges of other facial areas were also significant predictors.
While the study had limitations such as a small sample size and being conducted at a single center, the results suggest that thermal imaging combined with AI could improve the accuracy of diagnosing coronary artery disease. Further research with larger and more diverse patient populations is needed to validate these findings.
The researchers believe that this approach could streamline clinical workflows, save time for physicians and patients, and enable mass prescreening for coronary artery disease. By leveraging advanced machine learning technology, thermal imaging has the potential to enhance disease assessment beyond traditional clinical measures.
In conclusion, the study underscores the potential of thermal imaging and AI technology in predicting coronary artery disease. Further research is needed to validate these findings and explore future applications in clinical practice.
