Advertisements
An AI model can detect heart failure from one heartbeat with 100 percent accuracy (stock)

New AI-based tool can detect & # 39; heart failure with just ONE heartbeat & # 39; and is 100% accurate, scientists claim

  • Scientists & # 39; fed & # 39; it with electrocardiograms consisting of 490,000 beats
  • The technology was then exposed to a series of & # 39; five-minute ECG fragments & # 39;
  • The scientists hope that their device will someday help doctors to diagnose HF faster
Advertisements

A new AI-based tool can detect heart failure from just one heartbeat, research suggests.

Advertisements

Scientists have fed the & # 39; system & # 39; with electrocardiograms (ECG) with more than 490,000 heart beats.

The technology was then exposed to a series of & # 39; five-minute ECG fragments & # 39; from recordings of 24 hours.

The results showed that the convolutional neural network, as it is called, was 100 percent accurate in detecting heart failure patients.

An AI model can detect heart failure from one heartbeat with 100 percent accuracy (stock)

An AI model can detect heart failure from one heartbeat with 100 percent accuracy (stock)

Advertisements

The team at the University of Surrey hopes that their tool will one day help physicians to diagnose HF more quickly, for the benefit of patients and relieving pressure on NHS agents.

Heart failure occurs when the muscles of the organ are too weak or stiff to pump blood effectively through the body.

This can be due to high blood pressure or narrowing of the arteries. Drinking too much alcohol can also cause it, says the NHS.

The condition affects around 26 million people worldwide, according to the European Society of Cardiology.

In the most serious cases, 40% of patients die from the condition, the researchers wrote.

Advertisements

It is also one of the main causes of hospitalization in the elderly, the team added.

With increasing life expectancy, the team started looking for a more accurate way to diagnose HF early.

Existing methods look at heart rate variability (HRV), which describes inconsistencies in the space between successive heart beats.

However, HF can usually only be diagnosed after a person's HRV has been viewed for about 24 hours.

To overcome this, the researchers led by Dr. Sebastiano Massaro relies on ECG signals instead of HRV.

Advertisements

They collected & # 39; long-term ECG recordings & # 39; of 15 serious HF patients from the BIDMC database for congestive heart failure.

The & # 39; control group & # 39; consisted of ECG & # 39; s from 18 healthy people from the Normal Sinus Rhythm Database.

Each participant had about 20 hours of ECG recording, the researchers wrote in the journal Biomedical Signal Processing and Control.

Dr. Massaro said: & # 39; Our model provided an accuracy of 100 percent. By checking just one heartbeat, we can detect if someone has heart failure. & # 39;

He added that their tool is one of the first to be able to identify the morphological features of the ECG related to the severity of heart failure.

Advertisements

Dr. Leandro Pecchia, president of the European Alliance for Medical and Biological Engineering, said it was a & # 39; great progress & # 39; provides in the detection of heart failure.

He added: & # 39; Giving doctors access to an accurate HF detection tool can have a significant social impact. & # 39;

Dr. Pecchia said patients can benefit from an early and more efficient diagnosis. and also said the tool & # 39; press NHS resources & # 39; can relieve.

HOW DO ARTIFICIAL INTELLIGENCE LEARN?

AI systems rely on artificial neural networks (ANNs), which try to simulate the way the brain works to learn.

ANNs can be trained to recognize patterns in information – including speech, text data or visual images – and form the basis for a large number of developments in AI in recent years.

Advertisements

Conventional AI uses input to teach & # 39; an algorithm on a specific topic & # 39; by giving it huge amounts of information.

AI systems rely on artificial neural networks (ANNs), which try to simulate the way the brain works to learn. ANN & # 39; s can be trained to recognize patterns in information - including speech, text data, or visual images

AI systems rely on artificial neural networks (ANNs), which try to simulate the way the brain works to learn. ANN & # 39; s can be trained to recognize patterns in information - including speech, text data, or visual images

AI systems rely on artificial neural networks (ANNs), which try to simulate the way the brain works to learn. ANN & # 39; s can be trained to recognize patterns in information – including speech, text data, or visual images

Practical applications include Google's language translation services, Facebook & # 39; s face recognition software, and Snapchat & # 39; s live image-changing filters.

Entering this data can be extremely time-consuming and is limited to one type of knowledge.

Advertisements

A new breed of ANN & # 39; s called Adversarial Neural Networks contrasts the minds of two AI bots, allowing them to learn from each other.

This approach is designed to speed up the learning process and refine the output of AI systems.

. (TagsToTranslate) Dailymail (t) health