This New AI-Based Technique Can Detect Heart Conditions, May Help Avert Heart Attacks


The method keeps track of vascular plaque using pictures from optical coherence tomography (OCT).

Researchers have developed a revolutionary artificial intelligence (AI) method that can identify plaque erosion in heart arteries, which could result in the creation of new treatments for heart illnesses.The method keeps track of vascular plaque using pictures from optical coherence tomography (OCT).The discovery is important since the plaque’s dissolution can signal the beginning of a heart attack or other serious heart conditions.With the aid of the optical imaging technique known as OCT, which may be utilised inside blood vessels, it is possible to create 3D images of the coronary arteries that provide blood to the heart muscles.

Plaque erosion has been detected using the OCT method.However, the amount of data produced and the complexity of image interpretation result in significant interobserver variability.Researchers used AI to identify plaque erosion in the OCT technique in an effort to address this issue.

“Acute coronary syndrome, which necessitates immediate treatment, can occur if cholesterol plaque lining arteries begins to disintegrate. Acute coronary syndrome is characterised by an abrupt drop in blood flow to the heart”.According to Zhao Wang from the University of Electronic Science and Technology of China, “Our novel method could help enhance the clinical detection of plaque erosion and be utilised to develop new treatments for patients with heart disease”.The study that was published in Biomedical Optics Express likewise has Wang as its lead author.

The new AI method consists of two main processes, where the first evaluates the original image and two pieces of shape information using a neural network AI model to predict the areas of plaque erosion.

A post-processing algorithm that imitates the expertise of trained doctors is then used to refine this prediction and make the diagnosis.In order to recognise plaque erosion in OCT pictures, we have to create a novel AI model that includes explicit shape information.Because it is currently the highest resolution imaging technique that can be used to identify plaque erosion in living patients, the underlying intravascular OCT imaging technology is equally essential, according to Wang.

The novel method was put to the test by the researchers, who discovered that the automated approach had a 73% positive predictive value and could predict 80% of the cases of plaque erosion.Additionally, the diagnosis made using the AI technique correlated well with those made by qualified doctors.

Found this article interesting? Follow BG on Facebook, Twitter and Instagram to read more exclusive content we post.

0 0 votes
Article Rating
Notify of
Inline Feedbacks
View all comments

Latest news

Samsung Galaxy A23 5G With 6.6-Inch Infinity-V Display, 5,000mAh Battery Launched

Samsung has not yet revealed the Galaxy A23 5G's price or availability. The South Korean electronics giant today quietly unveiled...

LG Ultra Tab With 10.35-Inch Display, Snapdragon 680 SoC Launched

The 7,040mAh battery in the LG Ultra Tab supports 25W rapid charging. Although LG, a South Korean multinational company, may...

OnePlus 10T Glacier Mat Case With Sustainable Circulation Cooling, Bumper Case Sandstone Launched In India

Table of ContentsOnePlus 10T Glacier Mat Case, Bumper Case Sandstone, Tempered Glass price in India A tempered glass for the...

Nokia 110 (2022) With 1,000mAh Battery Launched In India

Table of ContentsNokia 110 (2022) priceNokia 110 (2022) specifications The Nokia 110 (2022) comes pre-loaded with games like Snake and...

Latest Updates

Must read

Apple Music Subscribers Can Now Get Free Beats Flex Earphones But Conditions Apply

However, Apple Music customers who are students in India...

ASUS VivoBook S14 S433 Review: Notebook For New Generation

Laptops are a quintessential part of the new norm,...

You might also likeRELATED
Recommended to you

Would love your thoughts, please comment.x