The tool utilises sophisticated modelling techniques and innovative machine learning technology, co-developed with Faculty, an artificial intelligence firm. At the start of the pandemic, Faculty also helped build the COVID-19 Early Warning System to forecast hospital admissions and life-saving equipment up to three weeks in advance.
The aspiration is that the insights provided will support local teams with planning their allocation of staff and resources weeks in advance. This includes knowing when to focus on freeing up beds, working with partners in the wider health and care system as needed, to ensure capacity for patients when they need it.
Importantly - as attention turns to tackling elective backlogs - the tool can offer increased certainty on when emergency demand levels are likely to be lower, and support decisions on when elective care delivery should be prioritised.
Admission forecasts are broken down by age, allowing staff to plan for specific bed needs, such as for paediatric patients or for elderly patients – as well as by NHS trust, allowing staff in regional and national teams to spot those areas with expected demand surges and coordinate proactive support.
Data sources on external factors, such as COVID-19 and public holidays, have been incorporated to improve the model’s accuracy, and there are aspirations to expand this to other data sources such as weather in future.
The tool co-developed with frontline clinical and operational staff in nine pilot NHS trusts. Feedback has been positive and the accuracy of the predictions impressive. The tool is being rolled out to over 100 other NHS acute trusts.
Professor Stephen Powis, NHS national medical director, said: “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 lifesaving 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.”
