Skip to main content
  1. Home
  2. Computing
  3. News

AI-powered stethoscope promises heart disease detection in seconds

Three serious heart conditions detected in just 15 seconds, while the results appear on a phone.

Add as a preferred source on Google
Demonstration of AI stethoscope.
Imperial College

The Apple Watch is on the wrist of millions of users across the world. Over the years, Apple has developed algorithms that collect data from the integrated PPG sensor to sense irregular heart rhythms and warn users about risks such as Atrial Fibrillation. Now, a similar approach has been deployed to develop an AI-powered stethoscope that is claimed to detect three serious heart conditions within a matter of seconds.

The device, which is roughly the size of a playing card and looks more like a power bank, has already been deployed by Imperial College London and Imperial College Healthcare NHS Trust as part of a nationwide study called TRICORDER.  The smart stethoscope can detect Heart failure (HF), atrial fibrillation (AF), and valvular heart disease (VHD).

How does it work?

At the heart of the AI stethoscope is a single-lead ECG sensor and a mic array that records phonocardiogram (PCG) waveforms, while algorithms make sense of these heart activity and blood flow readings to detect any abnormalities. The device, which connects to a smartphone app via Bluetooth and sends data to the cloud over Wi-Fi or cellular network, can reportedly detect the aforementioned heart issues in just 15 seconds.

This AI-driven stethoscope is classified as a Class IIa medical device, which means it is already authorized for regular use in healthcare. As such, doctors and healthcare professionals won’t need a written or signed consent from patients for using it either. The most notable aspect is that the trials have produced reliable results. 

Recommended Videos

The device, which has been provided as a replacement stethoscope for routine patient clinical examination to general practitioners (GP) across the country, takes a 15-second recording after placing it over the upper left sternal border area on the chest. The real magic happens courtesy of the algorithms, which are governed by the UK Medicines and Healthcare Products Regulatory Agency (MHRA) and have shown promising results. 

“The statistical performance of these three AI algorithms has been shown to be high and consistent against international external validation studies,” the team says in a research paper published in the BMJ Open journal. As part of the initial study, which spanned over 200 GP surgeries covering over 1.5 million patients, doctors examined patients who came in with complaints of fatigue and breathlessness. 

According to the British Heart Foundation, which partly funded the studies, patients who got themselves examined by the AI-powered stethoscope were roughly 3.5 times more likely to be diagnosed with atrial fibrillation. “They were almost twice as likely to receive a diagnosis of heart valve disease, which is where one or more heart valves do not work properly,” the institution adds.

A bright future

The core objective behind the development of this smart stethoscope is to detect heart problems in the early stages, so that patients can get the required life-saving medications and treatment in time. Heart failure, which affects as many as a million patients in the UK alone, is detected in 70 percent of cases only after an individual is rushed in for emergency care. 

Professor Nicholas Peters, senior investigator from Imperial College London and consultant cardiologist at Imperial College Healthcare NHS Trust, notes that the smart stethoscope allows the detection of three serious heart conditions in one sitting. As for the device itself, it is manufactured by a California-based company named Eko Health. 

“It is estimated that implementing this tool in primary care could save the NHS £2,400 per patient by eliminating the potential need for an unplanned A&E visit,” claims the UK’s National Health Service (NHS). It notes that over three million patients have already been enrolled as part of the TRICORDER trial program, and down the road, it could potentially enable healthcare savings worth over a hundred million pounds to the government. 

Nadeem Sarwar
Nadeem is the Managing Editor at Digital Trends.
The maker of ChatGPT wants to make open-source projects less of a security bargain
OpenAI launches Patch the Planet for open-source security, with over 30 open-source projects on board.
openai-chatgpt-os

OpenAI has launched Patch the Planet, a new initiative aimed at fixing one of the internet's quietest problems – the chronically underfunded security of open-source software.

Patch the Planet pairs OpenAI's most security-capable AI models with Trail of Bits, a security firm that has committed its entire research organization to the effort, alongside support from HackerOne and Calif.

Read more
I sifted through the Prime Day chaos to find the best Apple deals actually worth buying
Apple's about to hike prices. Prime Day 2026 is your last chance to save up to $150 on MacBooks, AirPods, and iPads.
Prime Day Deals on Apple Products

Apple is set to increase the prices for its upcoming iPhones and MacBooks, as the company can no longer offset the rising RAM and storage costs. That means, if you are looking to upgrade your aging device, you should buy the current-generation Apple products rather than wait for the new ones.

And since Amazon Prime Day is offering good discounts on the latest iPhones, iPads, MacBooks, and other Apple accessories, this is the perfect time to buy them. Here are my favorite Amazon Prime Day deals for Apple products. 

Read more
This sneaky photo trick gets AI chatbots to ignore their safety rules
Florida International University researchers built a method that nearly doubled the rate of harmful responses from a tested AI model using nothing but pixel-level edits in an image.
JaiLIP AI chatbot exploit image

A photo that looks completely ordinary to you could carry a hidden instruction to trick an AI chatbot into ignoring its safety rules, according to new research out of Florida International University. The study found that pixel-level alterations in an image that are invisible to the human eye can be enough to confuse the model reading the image and lead it to generate responses it would normally block.

Hacking what the AI sees

Read more