NHS Artificial Intelligence Pilot Program Tracks People’s Eating and Drinking Habits

Google’s DeepMind was given access to every patient’s complete medical history at one of England’s largest hospitals, Royal Free Hospital, which is part of the National Health Service. Ben Stansall/AFP/Getty Images

Artificial intelligence (AI) is increasingly being used by the NHS, in some cases to track people’s eating and drinking habits in their homes, to prevent avoidable hospital admissions.

The NHS unveiled a suite of AI initiatives across England on Tuesday, aiming to stop unnecessary hospitalisations during the busy winter period.

One pilot scheme in Buckinghamshire connects AI technology to electronic sensors placed on kettles and fridges to spot changes in patients.

Sodexo

The scheme is a partnership with the French services giant and major NHS contractor Sodexo, which managed 150 COVID testing sites on behalf of the Department for Health.

In a video demonstrating the technology, Sodexo’s Onward Care team places remote monitoring devices in patient homes, which then flows through data into Sodexo online dashboards, which for example, can tell the company which room patients are in and how long they have been there.

Onward Care project director Adrian McCourt in the video says that the technology “uses artificial intelligence so that we can identify whether someone’s behaviour is changing and if that behaviour is changing, we'll get a notification, that means that we can act proactively to check what is happening with that individual.”

Sensors on fridges and kettles are used as “proxies for hydration and nutrition.”

The Epoch Times understands that the trial is done as part of a patient care plan, with the patient’s full consent.

Leveraging AI

NHS England said it is aiming to leverage AI to “revolutionise healthcare.” Last week it emerged that 7.7 million people are on NHS waiting lists in England, the highest since records began in 2007.

Earlier this year, Dominic Cushnan, director of AI, Imaging and Deployment for NHS England, said that there are now 86 live AI projects.

Other projects include four GP practices in Somerset participating in a trial of an AI system from a company called Bering, which is developing a mathematical model able to predict unplanned emergency hospital admissions.

NHS teams in some areas of Birmingham are also piloting AI which uses an algorithm that predicts the top 5 percent at risk of potential hospital attendance, so staff can offer measures to avoid A&E admissions. Over the next two years, the scheme wants to prevent 4,500 unnecessary A&E attendances and 17,000 overnight hospital stays.

‘Reducing Avoidable A&E Attendances’

Amanda Pritchard, chief executive of NHS England, said: “This suite of tech and data solutions ahead of winter demonstrates how NHS staff across the country are innovating every step of the way, maximising the use of the latest technology and AI to help patients but also significantly reducing the number of avoidable A&E attendances.

“They are identifying the most at-risk or vulnerable patients and wider issues affecting their health, so teams can get to them early and help avoid an unnecessary visit to hospital—not only are these measures better for patients who can be cared for at home where they feel most comfortable but they are good for the NHS too, particularly when we know that this winter is likely to be incredibly challenging.”

Chris Holt, chief transformation officer at Birmingham Community Healthcare NHS FT, said: “Using data more smartly and harnessing the power of AI is now crucial in supporting the highest risk patients who, with the right support, can stay well at home.

“By identifying those complex patients—most likely to attend or be admitted to hospital over winter—it means we can step in much sooner and give them support that’s personalised for them.”

This year, £200 million was made available to establish and develop virtual wards, which allow patients to stay at home while receiving care from clinical staff, who use apps or wearable technology to monitor them remotely.

PA Media contributed to this report.