Facial temperature imaging and AI can accurately predict the presence of coronary artery disease

A combination of facial thermal imaging and artificial intelligence (AI) can accurately predict the presence of coronary artery disease, finds research published in BMJ Health & Care Informatics.

This non-invasive, real-time method is more efficient than conventional methods and can be adopted for clinical practice to improve diagnostic accuracy and work efficiency, while waiting for the diagnosis to be quantified. larger and more ethnically diverse patients, suggest the researchers.

Current heart disease screening guidelines are based on probabilistic assessments of risk factors that are often not accurate or very effective, the researchers said. Although these can be supplemented with other tests, such as ECG readings, angiograms, and blood tests, these are often time-consuming and invasive, the researchers add.

Thermal imaging, which captures the temperature distribution and variations on an object by detecting the infrared radiation emitted by the object, is non-invasive. It has emerged as a promising diagnostic tool, as it can identify abnormal areas of blood flow and inflammation from skin temperature patterns.

The advent of machine learning (AI) technology, with its ability to extract, process and integrate complex information, can improve the accuracy and efficiency of thermal image analysis.

Therefore, the researchers set out to look at the possibility of using thermal imaging together with AI to accurately predict the presence of coronary artery disease without the need for invasive, time-consuming procedures in 460 suspected patients. it’s heart disease. Their average age was 58 years; 126 (27.5%) of them were women.

Thermal images of their faces were taken before validation tests to develop and validate an AI-assisted image model for vascular disease detection.

In total, 322 participants (70%) were confirmed to have coronary artery disease. These people were usually older people and they were men. They were also more likely to have lifestyle, clinical, and biochemical risk factors, as well as higher use of preventive medicine.

Thermal imaging and AI were 13% better at predicting coronary artery disease than a pre-diagnosis risk assessment that included common risk factors and clinical signs and symptoms. Of the three most important predictors of temperature, the one that had the strongest influence was the overall temperature difference on the left side of the face, followed by high facial temperature, and normal facial temperature.

In particular, the average temperature of the left jaw area was the strongest predictor, followed by the temperature of the right eye area and the temperature difference in the left of the temple grounds.

This method also successfully identified common risk factors for coronary heart disease: high cholesterol; male gender; smoking; overweight (BMI); fasting blood sugar, as well as inflammatory symptoms.

The researchers acknowledge the small sample size of their study and the fact that it was conducted at only one institution. In addition, all participants were sent for confirmatory tests for suspected heart disease.

But the group nevertheless writes, “The possibility of [thermal imaging] established [coronary artery disease] The forecast suggests potential future applications and research opportunities… As a biophysiological-based health assessment approach, [it] provides more disease-related information than traditional clinical measures can improve [atherosclerotic cardiovascular disease] and diagnosis related to chronic condition.

“The non-contact, real-time nature of [it] it allows for immediate diagnosis at the point of care, which can streamline clinical work and save time for making important doctor-patient decisions. In addition, it has the potential to facilitate self-evaluation. ”

The researchers concluded, “We’ve improved [thermal imaging] predictive models, based on advanced [machine learning] technology, have shown promising potential compared to current standard clinical devices.

“Further studies involving larger sample sizes and different types of patients are needed to confirm the external validity and generalizability of the current findings.”