Register Now


Lost Password

Lost your password? Please enter your email address. You will receive a link and will create a new password via email.

Add post

You must login to add post .

Add question

You must login to ask a question.


Register Now

Welcome to! Your registration will grant you access to using more features of this platform. You can ask questions, make contributions or provide answers, view profiles of other users and lots more. Register now!

Clinical trials begin of Cambridge Heartwear’s AI-powered monitor that identifies those at risk of stroke

Clinical trials are under way of a Cambridge start-up’s new low-cost wearable heart monitor that uses artificial intelligence to identify those at risk of a stroke. Cambridge Heartwear’s sensor-packed wireless device picks up on dangerous and irregular heart rhythms, which often go undetected until after a stroke has taken place.

Cambridge Heartwear's Prof Roberto Cipolla, Dr Rameen Shakur and James Charles, a post-doc in Prof Cipolla's group

Cambridge Heartwear’s Prof Roberto Cipolla, Dr Rameen Shakur and James Charles, a post-doc in Prof Cipolla’s group

The concept was born out of a personal loss.

In 2015, a year after his father died of a stroke, Professor Roberto Cipolla, from the University of Cambridge’s Department of Engineering, met cardiologist and clinical academic Dr Rameen Shakur and began a research collaboration that led the company being formed in 2017.

Cambridge Heartwear has created a sensor-packed wireless device
Cambridge Heartwear has created a sensor-packed wireless device

Stroke and stroke-related mortality and morbidity affects 120,000 people in the UK each year. It is the country’s fourth biggest killer, with more than 23,000 deaths last year, and the NHS spends £2.5billion annually on neurological treatment and rehabilitation for stroke patients.

The most common heart rhythm disturbance, which affects more than one million people across the UK, is atrial fibrillation (AF).

National and international data suggests more than 80 per cent of those who die or who are left with severe neurological deficits following a stroke had an irregular heartbeat as the underlying cause, meaning early diagnosis could make a real difference.

Dr Shakur, who was formerly a Wellcome Trust Clinical Fellow at Cambridge and is now based at MIT in America, said: “It makes sense to pick up AF before someone has a stroke and put preventative treatment in place. Unfortunately, the technology and clinical care systems we currently have in place aren’t really doing this.”

Electrocardiograms (ECGs) are used to monitor heart rhythms. But to use one outside of a GP surgery or hospital, a cumbersome £2,000 device called a Holter monitor is attached to a patient’s chest via 12 leads, and is carried around for 24 hours.

It can then take four to six weeks from the date of referral by a GP to the anaylsis of the data from the Holter monitor.

“If you’re wearing an ECG over a long period of time, you’re collecting a huge amount of data,” said Dr Shakur. “Finding an irregularity among all the normal rhythms can be like looking for a needle in a haystack. I wanted to automate this process, helping the patient to get a diagnosis and start on treatment.”

Working with Prof Cipolla, a world leader in computer vision and real-world applications, and students from the Department of Engineering, the unique Heartsense monitor was developed along with powerful algorithms that can automatically interpret ECG data to an accuracy above 95 per cent.

The Cambridge Science Park company secured funding last year to build and test 100 prototypes and extend the device’s AI capability.

Heartsense includes a multiple lead ECG, oxygen sensing, a temperature and tracking device, which can be comfortably worn by patients, while its multiple, independent sensors, which produce specific and sensitive data, are enclosed in a robust waterproof casing.

The development team used knowledge of clinical anatomy and electrophysiology ensure maximal signal output and the data produced is far more sensitive than that from current single lead wearable devices.

This data is wirelessly streamed in real time to the cloud, where adaptive AI algorithms identify clinically relevant irregular and dangerous rhythms.

The aim was to create algorithms that could learn from a limited amount of supervision from the cardiologist.

“Our aim was not to replace the cardiologist, but to give them diagnostic support in real time,” said Prof Cipolla.

To aid the adoption by clinicians, the team also ensured that the output of the AI algorithms included the information commonly used by a cardiologist.

“This was not necessary for the final diagnosis but made the system a little more understandable and explainable than typical deep learning systems, which are still thought of as black boxes,” noted Prof Cipolla.

Costing substantially less than a Holter monitor, the device’s ergonomic design was developed with the help of The Royal College of Art.

Patients are now being enrolled from primary care in Lancashire for clinical trials of the product.


About Marie

Leave a reply