Artificial intelligence could reduce the number of elderly people who fall at home

Artificial intelligence (AI) could help reduce the number of falls elderly people have at home, leading to fewer people being admitted to hospital.

Social care provider and health technology company Cera said a pilot of its AI platform had led to a 20% reduction in falls, and they were optimistic the rate could continue to fall.

Cera is a private company, but the majority of its activities provide social care on behalf of the NHS and local authorities.

Its staff handle 50,000 appointments a day, according to founder Dr Ben Maruthappu, who started the business in 2016 when he was an A&E doctor.

The Fall Prediction AI platform takes patient information recorded by caregivers in a smartphone app and assesses their fall risk.

Based on the information, the visiting caregiver can then ensure that the patient is hydrated and that pathways to the toilets and kitchen are clear.

No caregiver likes to show up at someone's house and find them on the floor

Dr Ben Maruthappu, Cera

The pilot is currently taking place in locations across the North West, Yorkshire and central Scotland.

Approximately 134 patients who had a total of 29 falls in the fortnight before the trial were included.

After using Cera Fall Prediction AI, the total number of falls decreased to 23, a decrease of 20.69%.

Dr Maruthappu said the reception from staff had been “really positive”.

“No caregiver likes to show up at someone's house and find them on the floor,” she said. “It's a really difficult situation.

“Being able to prevent that changes that person's life and changes our caregivers' ability to really provide great care so they're on the front foot.

“Instead of showing up at someone's house and finding them on the floor, they already know days in advance that something is coming.”

Dr Maruthappu said Cera is able to create the programs thanks to “unprecedented amounts of data on how patients are doing at home in the community”.

He added: “This makes it very easy for us to build AI products, whereas other healthcare companies trying to use AI simply don't have the data set.”

Cera has been building AI products since 2021, starting with a platform that predicts and prevents hospital admissions.

2022 saw the launch of Cera Voice, an automated AI phone call that engages with patients daily to ask them specific health questions and determine their risk of getting sick.

The chatbot adapts to the patient based on the answers it receives and adapts the questions it asks to get relevant information.

“This helps us turn the conversation into data and the risk of someone ending up in hospital or becoming unwell so we can do something about it,” added Dr Maruthappu.

Cera “started with a mission to empower people to live better lives in their own homes,” he said.

Further uses of AI in the company include using ChatGPT to automate paperwork or to help the company schedule its workers.

“Figuring out who is matched with whom for visits is really quite complicated. We have to match them based on language, time, location, caregiver skills, health conditions of the person.

“We use AI to improve it. It means our carers travel around 30% less. They're saving that time because they're taking a more efficient person-to-person route, and it's time to get back to providing care.”

Elsewhere, Cera uses avatars, or digital representations, to train staff.

The platforms, which show images of real-life instructors, can welcome new beginners in multiple languages ​​and teach them various skills.

A pilot using the technology started last month in London and South East Europe.

Dr Maruthappu said he hopes the use of avatars can address pressures in social care in a sustainable way.