Technology 3 min read

AI Reads ECG Data to Measure Patient's Overall Health Status

Researchers trained an AI system to read ECG data, allowing it to predict the health status and physiological age of patients accurately.

Image courtesy of Shutterstuck

Image courtesy of Shutterstuck

Soon, health professionals may be able to deduce patients’ overall health status by using artificial intelligence to read ECG data.

An electrocardiogram is a test that measures the electrical activity of the heart. However, a paper published in the American Heart Association suggests that ECG or electrocardiogram data could provide more information when paired with AI.

According to the researchers, not only can ECG or EKG data and artificial intelligence determine a patient’s gender, but their physiological age too. Unlike the chronological age, the physiological age is a measure of the overall standard of the body function, including health status.

So, the researchers decided to test their hypothesis.

Training a Convolutional Neural Network With ECG Data

The team trained a type of artificial intelligence called convolutional neural network using the ECG data of about 500,000 patients. They tasked the machine to find the similarities among the input and output data.

After undergoing the training, the researchers then tested the neural network for accuracy using the data of an additional 275,000 patients. It had to predict the output when only given the input data.

The AI passed with flying colors. Not only did it determined the patient’s gender accurately 90 percent of the time, but the AI could also predict a patient’s physiological age group with 72 percent accuracy.

It estimated a patients’ physiological age as higher if they had experienced adverse health conditions such as coronary heart disease, low injection fraction, and heart attack in the past. Meanwhile, patients that have experienced few or no adverse health event had a lower physiological age.

In a statement, study author and director for Augmented and Virtual Reality Innovation at Mayo Clinic in Rochester, Suraj Kapa said:

“While physicians already consider whether a patient ‘appears [their] stated age’ as part of their baseline physical examination, the ability to more objectively and consistently assess this may impact healthcare on multiple levels.”

How an AI-Enhanced Cardiogram Could Change Healthcare

With the ability to accurately assess overall health status, doctors can conveniently diagnose asymptomatic or silent diseases, ultimately leading to early intervention. According to Kapa, an AI-enhanced electrocardiogram can help health professionals keep up with new issues or comorbid conditions that they would otherwise be unaware of.

Kapa noted:

“This evidence – that we might be gleaning some sort of ‘physiologic age’ — was certainly both surprising and exciting for its potential role in future outcomes research, and may foster a new area of science where we seek to understand the biologic underpinnings of such a finding better.”

Although the study involved a large sample size, all the subjects in the study were patients. As such, the EKGs were administered for another clinical indication.

That means further studies with healthy sample size is required to revalidate the neural network’s results.

Read More: AI Hardware Startup Unveils the World’s Largest AI Accelerator

First AI Web Content Optimization Platform Just for Writers

Found this article interesting?

Let Sumbo Bello know how much you appreciate this article by clicking the heart icon and by sharing this article on social media.


Profile Image

Sumbo Bello

Sumbo Bello is a creative writer who enjoys creating data-driven content for news sites. In his spare time, he plays basketball and listens to Coldplay.

Comments (0)
Least Recent least recent
You
share Scroll to top

Link Copied Successfully

Sign in

Sign in to access your personalized homepage, follow authors and topics you love, and clap for stories that matter to you.

Sign in with Google Sign in with Facebook

By using our site you agree to our privacy policy.