1. Business
  2. Medical marvels
September 10, 2019

AI tool accurately detects heart failure from a single heartbeat

By Ellen Daniel

A new artificial intelligence (AI) neutral network can successfully detect heart failure from just one heartbeat.

This is according to researchers from the University of Surrey, whose findings could drastically improve on existing detection methods for congestive heart failure (CHF).

CHF is a chronic condition that affects the heart’s ability to pump blood around the body due to fluid buildup around the heart. The condition is progressive and has high mortality rates.

Along with researchers from the University of Warwick and the University of Florence, the team used a convolutional neutral network, particularly effective at recognising patterns in data, and used it to analyse electrocardiogram (ECG) signals from publicly available ECG datasets.

From analysing a single heartbeat from the ECGs, they were able to predict with 100% accuracy whether or not the person was experiencing heart failure using advanced signal processing and machine learning tools.

How AI could improve heart failure diagnosis

Current detection methods for CHF look at heart rate variability. While this can be effective, the method is time consuming and is often prone to errors.

The new detection method improves on this, while also identifying certain features of the ECG that indicate the severity of the condition.

Dr Pecchia, President of the European Alliance for Medical and Biological Engineering, explains what the findings could mean for those with the condition:

“With approximately 26 million people worldwide affected by a form of heart failure, our research presents a major advancement on the current methodology.

“Enabling clinical practitioners to access an accurate CHF detection tool can make a significant societal impact, with patients benefitting from early and more efficient diagnosis and easing pressures on NHS resources.”

AI as a medical tool

The use of AI and machine learning in the detection of medical conditions is a growing area in the field of diagnostics.

Recently, Cognetivity Neurosciences announced that it had developed an AI-based test to detect very early signs of dementia.

Earlier this week, the UK government announced that it was investing over £130m in new tech to tackle cancer and other debilitating illnesses, with £50m being invested in diagnostics, including the use of AI.

Read more: Artificial intelligence is making tech companies the new healthcare giants