This new AI-based technique can detect heart conditions, which could help prevent heart attacks

In what could lead to the development of new treatments for heart diseases, researchers have created a new artificial intelligence (AI) technique that can detect plaque erosion in heart arteries. The technique uses optical coherence tomography (OCT) imaging to monitor arterial plaque. This finding is important because the breakdown of plaque can be a precursor to a heart attack or other serious heart disease. OCT, which is an optical imaging technique, can be used in blood vessels to create 3D images of the coronary arteries that carry blood to the heart muscle.

OCT technique was used to mark plaque erosion. However, the volume of data generated and the difficulty in interpreting the images caused significant variation between the host of observations. To solve this problem, the researchers introduced AI in the OCT technique to identify plaque erosion.

“If the cholesterol plaque lining the inside of the arteries starts to erode, it can lead to a sudden decrease in blood flow to the heart known as acute coronary syndrome, which requires urgent treatment. Our new method could help improve the clinical diagnosis of plaque erosion and be used to develop new treatments for patients with heart disease.” speak Zhao Wang from the University of Electronic Science and Technology of China. Wang is also the lead author of the study published in Biomedical Optics Express.

The new AI method consists of two main steps, the first of which is an AI model called a neural network that analyzes the original image and two pieces of shape information to predict areas of plaque erosion.

This prediction is then refined through a post-processing algorithm that simulates the knowledge of professional doctors to make the diagnosis. “We had to develop a new AI model that incorporates clear conformational information, a key feature used to identify plaque erosion in OCT images. The underlying endovascular OCT imaging technology is also important as it is currently the highest resolution imaging modality that can be used to diagnose plaque erosion in living patients,” said Wang.

The researchers tested the new technique and found that the automated method was able to predict 80% of cases of plaque erosion with a positive 73% predictive value. Moreover, the diagnosis made by AI technique is very consistent with those made by experienced doctors.