AI foot scanner recognises warning signs of heart failure to keep people out of hospital, researchers say

A foot scanner that uses AI to recognise the warning signs of heart failure could be used at home to keep people out of hospital, researchers have said.

The device takes and analyses almost 2,000 pictures a minute, in a similar manner to facial recognition, to calculate the level of fluid in the feet and ankles.

Such water retention, known as oedema, is one of three major warning signs heart failure is becoming more severe and potentially life threatening.

The AI scanner is roughly the size of a smart speaker and can alert healthcare professionals so they can take action, such as increasing the patient's medication.

The device, developed by Cambridge-based start-up Heartfelt Technologies, is mounted to the wall and typically installed at a patient's bedside.

It automatically takes 1,800 pictures a minute of the foot and lower leg and multiple angles, only scanning the legs to a height of 50cm off the floor, and then uses AI to calculate the level of fluid they contain. It also works without wifi.

The Foot Study, which is being presented at the British Cardiovascular Society annual conference in Manchester, suggests the alerts come 13 days before a person would end up in hospital.

It used the AI device to monitor 26 heart failure patients from five NHS trusts who were enrolled between 2020 and 2022 and asked them to weigh themselves using Bluetooth-enabled scales.

Seven instances of worsening heart failure were detected in six patients, while one death from the condition was recorded.

Researchers found in patients enrolled in the study for at least two weeks before an alert was triggered, the average lead time before hospital admission was 13 days.

The lead time averaged eight days when all five triggers picked up by the device were analysed.

The study also found monitoring using scales failed to predict any heart failure-related hospital admissions, with researchers suggesting this was because patients struggled to stick to tracking their weight, whereas the AI device did not require any action.

The early warning provided by the device could allow specialist staff to react quickly to changes in a patient's condition, potentially allowing them to stay out of hospital.

Dr Philip Keeling, senior author of the study and a consultant cardiologist at Torbay and South Devon NHS Foundation Trust, said: "Only about half of people admitted to hospital with heart failure currently get assigned an early review by a heart failure nurse who can check to see if they are suffering a harmful build-up of fluid because their heart is not working properly.

"Amid a shortage of heart failure nurses, a device like this can be like a virtual nurse, tracking people's health."

Heart failure is a long-term condition where the heart is unable to pump blood around the body properly, typically because it has become too weak or stiff, and is estimated to affect 920,000 people in the UK.

The three main symptoms indicating the condition is getting worse are increased breathlessness, weight gain and swelling in the legs or ankles.

Discussing the findings, Professor Bryan Williams, chief scientific and medical officer at the British Heart Foundation (BHF), said: "This small study suggests a simple device could significantly improve outcomes for at-risk patients with heart failure by keeping them out of hospital.

"This study is a good example of how technology might aid earlier interventions and treatment, by allowing people to track a key sign of their heart health at home."

(c) Sky News 2025: AI foot scanner recognises warning signs of heart failure to keep people out of hospi