AI helping NHS tackle patient backlog

The forecasting tool utilises modelling techniques and machine learning to predict pressures from emergency demand, allowing NHS workers to make informed decisions and plan. It takes advantage of AI software that analyses data, including the number of 111 calls, COVID-19 cases and public holidays. There are aspirations to include other data sources such as the weather as severe spells of weather are a key factor in A&E admissions.

Trials of the tool in nine NHS trusts, demonstrated an “impressive” ability to forecast daily admissions, broken down by age, up to three weeks in advance.

The A&E admissions forecasting tool will support allocation of staff and resources, to help staff make decisions on what elective care delivery should be prioritised. Ultimately, it will give hospitals a daily forecast of expected admisisons to assist in efforts to bring down the record high waiting lists.

Prior to the pandemic there were 4.43 million people on the NHS waiting list for care. Latest figures show a record breaking six million people waiting for treatment.

When the tool predicts a quieter day, managers will be encouraged to free up A&E staff to prioritise elective care and deliver more routine tests and operations to tackle the backlog. Quieter hospitals can also ‘lend’ staff to a neighbouring trust with higher forecast admissions that day.

On days forecast to be busier, hospital managers can increase bed capacity or the number of staff on call. Breaking down admission forecasts by age also allows medical staff to plan for specific bed needs, such as for paediatric of elderly patients.

Professor Stephen Powis, NHS National Medical Director, said: “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.”

Myles Kirby, Director of Health and Life Sciences at Faculty said: “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, AI 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.”

At the beginning of the pandemic, Faculty worked with NHSX to build a COVID-19 Early Warning System to, capable of forecasting hospital admissions and life-saving equipment up to three weeks in advance. Daily predictions became available on a national, regional and hospital level. The Early Warning System was key to driving increased efficiencies, lower costs and supporting life-saving decisions in real time.

On the 24^th March 2022, the HSJ Partnership Awards awarded Faculty and NHS England Best Healthcare Analytics Project for the NHS.

The award recognises their innovative and collaborative partnership.