AI outperforms cardiologists in diagnosing arrhythmias from ECG

Artificial Intelligence researchers from Stanford AI lab developed a deep neural network which can diagnose irregular heart rhythms, also known as arrhythmias, from single-lead ECG signals at a high diagnostic performance similar to that of cardiologists.

Cardiologist-level arrhythmia detection from ECG using AI

An ECG (electrocardiogram) provides the information about heart rate and it's rhythm, and shows if there is enlargement of the heart due to high blood pressure (hypertension) or evidence of a previous heart attack (myocardial infarction).

The term "arrhythmia" refers to any change from the normal sequence of electrical impulses. The electrical impulses may happen too fast, too slowly, or erratically – causing the heart to beat too fast, too slowly, or erratically  . It is one of the most common cause of sudden death.

In a study published in Nature Medicine, they developed a deep neural network to classify 10 arrhythmias as well as sinus rhythm and noise from a single-lead ECG signal, and compared its performance to that of cardiologists.

They constructed a large ECG dataset from 53,877 adult patients >18 years old that underwent expert annotation for a broad range of ECG rhythm classes. They then used this dataset to train their Deep Learning(AI) model.

They compared the performance of their algorithm and cardiologists on an independent test dataset.

Cardiologist-level arrhythmia detection from ECG using AI
Their algorithm had a higher average F1 scores than cardiologists. The trend of algorithm F1 scores tended to follow that of the averaged cardiologist F1 scores: both had lower F1 on similar classes, such as ventricular tachycardia and ectopic atrial rhythm (EAR).

Fixing the specificity at the average specificity level achieved by cardiologists, the sensitivity of their alogirthm exceeded the average cardiologist sensitivity for all rhythm classes section.

Cardiologist-level arrhythmia detection from ECG using AI

They found that the model met or exceeded the discriminative performance of the averaged cardiologist for all rhythm classes.

Read more at https://stanfordmlgroup.github.io/projects/ecg2/

Comments

  1. I admire this article for the well-researched content and excellent wording. I got so involved in this material that I couldn’t stop reading. I am impressed with your work and skill. Thank you so much. If anyone interested to know more about the Cost of EKG, acaweb is the best for you.

    ReplyDelete

Post a Comment

Popular posts from this blog

A simple explanation of Artificial Intelligence for people not belonging to the tech sector.

The best way to deal with depression and anxiety

AI replaces radiologist doctors on diagnosing pneumonia