15.07.20
NHS harnessing predictive tech to help coronavirus forecasting
As lockdown restrictions continue to be eased, NHS teams are being given access to cutting-edge predictive technology to help forecast coronavirus hospitalisations to warn hospitals of local upticks and potential risks.
Using a machine learning-powered tool for the NHS based on Bayesian hierarchical modelling designed to warn hospitals so they can divert staff, beds and other equipment such as oxygen or ventilators necessary for tackling Covid-19 cases, the technology should help NHS teams save lives by being better prepared.
Alongside the technology, as government eases lockdown, the new Joint Biosecurity Centre is being asked to give the NHS advanced warning of any local uptick in coronavirus admissions.
Despite predictions to the contrary, the NHS avoided becoming overwhelmed during the first wave of Covid-19 – in which over 100,000 emergency coronavirus patients have been cared for in hospital – while also providing urgent services such as A&E, cancer and mental health as extensively as possible.
Now, as the country seeks to increase routine services which it had to pause during the peak of the epidemic, it is attempting to ensure it still has the necessary information, technology and protocols in place to handle smaller, localised outbreaks.
To assist this, the rollout of the new technology, built and developed by artificial intelligence specialists, will help local teams balance these priorities on a day to day basis, helping clinicians and scientists to model and predict hospitalisations up to three weeks in advance. Learning from data from previous outbreaks, such as bed use and early warning indicators such as NHS 111 call volumes, it will model potential future outcomes.
Indra Joshi, director of AI at NHSX, said: “As we continue to deal with the greatest public health emergency in a century, the NHS continues to rise to the challenge, and by using this leading technology, we will help support frontline staff in their ongoing mission to save as many lives as they can.
“This tool helps services plan the bringing back on of services for other patients safely, while flexing capacity locally for Covid-19 care."
Health Secretary Matt Hancock added: “The Covid-19 pandemic has shown the power of technology to improve patient care.
“These innovative tools will help arm the NHS with the insight it needs to predict hospitalisations, weeks in advance and ensure hospitals are prepared.
“This is good news for patients and staff that puts the NHS at the forefront of cutting-edge coronavirus care - and demonstrates the power that data has to protect the public and save lives.”
The forecasting tool is one part of a wider project known as the NHS Covid-19 Data Store, an effort by NHS England and NHS Improvement and NHSX to give local and national health leaders the information they need to help tackle the virus and direct resources to where they are needed most.