This article is more than 1 year old

Hospitals to use startup's AI tech to predict A&E traffic

Software will figure out number of beds needed – up to three weeks ahead

At least 100 NHS trusts in England are to start using machine-learning software to predict the number of patients expected to be admitted to Accident and Emergency departments each day.

The tool, built by British startup Faculty, aims to help managers figure out how best to allocate staff and resources during predicted surges, up to three weeks in advance.

"By better forecasting patient demand, we are helping staff tackle treatment backlogs by showing them who is set to be admitted, what their needs are, and which staff are needed to treat them," Myles Kirby, director of Health and Life Sciences at Faculty, said in a statement to The Register.

The software is said to provide detailed predictions, estimating the number and age of people it expects to arrive at A&E. Guessing people's ages allows the NHS to prepare freeing up beds at different departments to care for children at pediatric units or provide better support for elderly patients when rates of A&E admission are expected to be high. When they're predicted to be low, the tool could help the NHS be better at clearing its backlog of appointments for planned surgeries or other types of non-emergency procedures. 

Faculty trained its model on hospital admissions data, and it takes into account external factors such as public holidays and the progress of the COVID-19 pandemic. The startup said it also plans to incorporate other sources of data that affects A&E predictions, such as the weather. It was piloted at nine NHS trusts, and will be rolled out to at least 100 more, we're told.

NHS England national medical director Stephen Powis told The Register the AI tool will help provide better care for patients during a challenging time when hospitals are strained from the ongoing COVID-19 pandemic.

"NHS staff have been unstoppable in their efforts across what has been an unprecedented two years," he said, "treating over 600,000 patients with COVID in hospitals, delivering more than 118 million lifesaving vaccinations, managing high levels of A&E arrivals, all while continuing to provide routine care."

"Pressures remain high," Powis continued, "but staff are determined to address the COVID-19 backlogs that inevitably built up throughout the pandemic, and while that cannot happen overnight, harnessing new technologies like the A&E forecasting tool, to accurately predict activity levels and free up staff, space and resources will be key to helping deliver more vital tests, checks and procedures for patients."

Faculty also helped build a COVID-19 Early Warning System, another machine learning-powered tool that predicted hospital admissions and number of beds needed for patients, up to three weeks ahead. The system looked at the number of positive COVID-19 cases and calls made to the non-emergency 111 number to make its predictions. It is right now being used 1,000 practitioners in the NHS.

The Register has asked Faculty for comment. ®

More about


Send us news

Other stories you might like