Chalabala - stock.adobe.com

NHS England deploys pilot AI tool to forecast A&E admissions

The NHS is deploying an AI-based demand forecasting tool to accurately predict activity levels and free up staff, space and resources to tackle post-pandemic treatment backlogs

The NHS is deploying a demand forecasting tool from artificial intelligence (AI) firm Faculty that will predict accident and emergency admissions and help it better accommodate post-pandemic backlogs for elective procedures.

The same firm was involved in building a Covid-19 “early warning system” in the early stages of the coronavirus pandemic. That was also used to forecast hospital admissions.

Faculty delivered the earlier forecasting tool in July 2020 to give the UK Joint Biosecurity Centre (JBC) the ability to give health service providers advanced warning of new upsurges in Covid-19 cases.

According to an NHSX statement at the time, Faculty developed the tool as part of the Covid-19 datastore project, which also involved data analytics supplier Palantir, whose Foundry software was used as a front-end data platform. 

Stephen Powis, NHS national medical director, said in a Faculty statement about the new tool: “NHS staff have been unstoppable in their efforts across what has been an unprecedented two years, treating over 600,000 patients with Covid in hospitals, delivering more than 118 million life-saving vaccinations, managing high levels of A&E arrivals, all while continuing to provide routine care.

“Pressures remain high, 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.”

As NHS attention turns to tackling backlogs for elective procedures, it is said the tool will offer better certainty on when emergency demand levels are likely to be lower, and so support decisions on when elective care delivery should be prioritised.

Admission forecasts are broken down by age in the tool. This potentially allows staff to plan for specific bed needs, such as for paediatric or elderly patients.

It could also be used at NHS trust level, enabling staff in regional and national teams to spot areas with expected demand surges and coordinate proactive support.

Faculty said data about factors such as Covid prevalence and public holidays improved the accuracy of the model behind the tool. Their ambition is to include weather data sources in future iterations.

The tool was co-developed with frontline clinical and operational staff in nine pilot NHS trusts. It is being rolled out to more than 100 NHS trusts.

Myles Kirby, director of health and life sciences at Faculty, said: “Since our work with the NHS began two years ago, Faculty has been driven by one goal – to help improve patient care.

“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.

“As this pilot shows, artificial intelligence is a force for good, and we’ll be working closely with the NHS to make sure the benefits are felt by patients and staff in all the hospitals chosen.”

Chris Moran, national strategic incident director, NHS England and NHS Improvement, added: “This leading technology has been developed to support hospitals by alerting them of potential upcoming surges in A&E admissions, and this will support decision-making and flexible use of resources and capacity, meaning the NHS will be in a better position to prepare for surges in demand.”

Read more about AI in the NHS

Read more on Artificial intelligence, automation and robotics

SearchCIO
SearchSecurity
SearchNetworking
SearchDataCenter
SearchDataManagement
Close