Donate to Science & Enterprise

S&E on Mastodon

S&E on LinkedIn

S&E on Flipboard

Please share Science & Enterprise

Univ. Spin-Off Developing A.I.-Boosted Heart Monitor

Heartbeat graphic


13 September 2018. A new enterprise in the U.K. is developing a wearable heart monitor that diagnoses irregular heart rhythms with artificial intelligence using cloud-based algorithms. The company, Cambridge Heartware, was founded in 2017 by medical and engineering researchers at University of Cambridge.

Cambridge Heartware’s product, known as Heartsense, is a system that monitors and analyzes heart rhythms and other vital signs for signs of atrial fibrillation, a disorder where the atria, or upper chambers of the heart, beat irregularly instead of the normal, smooth regular beats that move blood effectively through the blood stream. Because of these irregular heart rhythms, blood can pool in the atria and form clots. If a clot should break off and flow to the brain, it can cause a stroke. According to American Heart Association, 15 to 20 percent of people who have a stroke also have atrial fibrillation.

The university cites data showing more than 1 million people in the U.K. have atrial fibrillation, with more than 100,000 people suffering a stroke each year, resulting in some 23,000 deaths in the U.K. last year. The country’s National Health Service says it spends £2.5 billion ($US 4 billion) each year on treatment and care of stroke patients.

The current system used most often for day-to-day atrial fibrillation monitoring is the Holter monitor, a non-invasive device with 12 wires pasted on the torso, leading to a controller worn by the patient for an entire day. Data from the monitor are later downloaded to a separate system for analysis and interpretation.

The Heartsense system includes a wearable heart and vital signs monitor worn around the chest that measures heart rhythms like an electrocardiogram or ECG, but also core body temperature and oxygen levels in the blood. The ECG module in Heartsense measures heart rhythms at 3 points, but the entire monitoring hardware is packaged in a small waterproof plastic container that its developers say was ergonomically designed by colleagues at the Royal College of Art in London.

Data from the Heartsense monitor are sent to a cloud-based repository where they are analyzed with deep-learning algorithms that adapt and adjust to new data added to the knowledge base. The results are then sent back to the user, displayed on a smartphone app in near real-time. The company reports that tests of the Heartsense algorithms show they accurately detect more than 95 percent of atrial fibrillation incidents. The company also says using 3 monitoring points makes its device more accurate than similar wearable devices using only a single monitoring point.

Cambridge Heartware started up last year, founded by Cambridge information engineering professor Roberto Cipolla and cardiology clinical fellow Rameen Shakur, now at MIT. Initial funding for the company, located in Cambridge Science Park, is supporting 100 prototypes for testing as well as refining the A.I. algorithms. The company says clinical trials of Heartsense are underway in Lancashire, a county in northwest England.

Cambridge Heartware’s goal is to give cardiologists better data than currently available from Holter monitors. “Our aim was not to replace the cardiologist,” says Cipolla in a university statement, “but to give them diagnostic support in real time.” The following video shows data collected by the Heartsense device, as seen on the accompanying smartphone app.

More from Science & Enterprise:

*     *     *

1 comment to Univ. Spin-Off Developing A.I.-Boosted Heart Monitor