Facial thermal imaging, AI can accurately predict heart disease risk
Coupled with AI, it has emerged as a promising tool for disease assessment as it can identify areas of abnormal blood circulation and inflammation from skin temperature patterns.
Representative Image (IANS)
NEW DELHI: Using a combination of facial thermal imaging and artificial intelligence (AI) can accurately detect coronary artery disease risk, finds research published in the journal BMJ Health & Care Informatics on Tuesday.
Caused by the buildup of plaques, coronary artery disease is the damage or disease in the heart's major blood vessels and can lead to heart attack.
Researchers led by Tsinghua University in Beijing, China showed that thermal imaging captures temperature distribution and variations on the object’s surface by detecting the infrared radiation emitted by that object.
Coupled with AI, it has emerged as a promising tool for disease assessment as it can identify areas of abnormal blood circulation and inflammation from skin temperature patterns.
It is non-invasive, gives real-time measurement, and is more effective than conventional methods which could be adopted for clinical practice, the researchers said.
On the other hand, current guidelines for the diagnosis of coronary heart disease rely on probability assessment of risk factors, not often accurate or widely applicable, coupled with ECG readings, angiograms, and blood tests, which are time-consuming and invasive.
Of 460 people with suspected heart disease in the study, using the new thermal imaging of faces and validating via an AI-assisted imaging model, 322 participants (70 per cent) were confirmed to have coronary artery disease.
The approach was about 13 per cent better at predicting coronary artery disease than the pretest risk assessment.
“The feasibility of [thermal imaging] based [coronary artery disease] prediction suggests potential future applications and research
opportunities,” the team said.
“As a biophysiological-based health assessment modality, [it] provides disease-relevant information beyond traditional clinical measures that could enhance [atherosclerotic cardiovascular disease] and related chronic condition assessment,” they added, calling for larger studies.