Researchers in the US have developed a new technology that can identify heart attacks faster and more accurately than traditional methods.
The team used AI and advanced mathematics to design a chip that can analyze electrocardiograms, known as ECGs – graphs of the heart’s electrical signals – and detect a heart attack in real-time.
The resulting technology is lightweight and energy efficient enough to be embedded in wearable devices while still being 92.4 per cent accurate – higher than many current methods.
University of Mississippi electrical and computer engineering assistant professor Kasem Khalil led the research.
Khalil said: “For this issue, a few minutes or even a few extra seconds is going to give this person the care they need before it becomes worse.
“Compared to traditional methods, our technology is up to two times faster, while still highly accurate.
“Our target was not only to increase performance for classifying heart attacks. We are also focusing on the design.
If we want to make this device a usable machine for any person, that means it has to be something lightweight and economic.”
Around 1.4 million people in the UK have survived a heart attack, according to the British Heart Foundation.
Heart disease – a collection of underlying conditions that can lead to a heart attack – is the leading cause of death to men in the UK.
Tamador Mohaidat is a doctoral student in Khalil’s lab and co-author of the publication.
The researcher said: “We wanted to be able to implement this in a way that is real. This is portable hardware that can be in wearable or monitoring devices.
“This method will save lives because we can monitor the heart in real time.”
Mohaidat, from Irbid, Jordan, focused on creating the artificial neural network, while Md. Rahat Kader Khan focused on building the software for the device.
Khan, a second-year computer engineering graduate student from Dhaka, Bangladesh, said the Khalil lab is unique in that it focuses on all aspects of the technology they hope to create.
Khan saidL “Some labs only focus on the software part, and they don’t think about the hardware that’s needed.
“But in our lab, we focus on the whole product. Each of us has a responsibility, but we work together.
“That’s how we optimise the whole system, by focusing on the overall architecture.”
Current methods of heart attack detection often must happen in a medical facility.
A patient experiencing chest pain or who suspects they’re having a heart attack must first go through an electrocardiogram or blood tests to diagnose their condition.
All of that takes time that a patient might not have, the researchers said. If a wearable device such as a watch or a phone can cut down on diagnosis time, patients could get faster treatment.
Khalil said: “When a patient is having a heart attack, the sooner you can treat them, the less likely they are to have permanent damage.
“There’s a huge time-sensitive element to heart attacks.”
While Khalil and his team continue developing the technology, he said he sees other healthcare applications for these devices.
He said: “We want to be able to predict or identify many problems using technology like this.
“Whether that’s heart attacks or seizures or dementia. The detection of a disease or condition depends on the disease itself, but we’re working to find faster, more efficient ways of doing that.”
Graphic by John McCustion/University Marketing and Communications
