Transformation Directorate

NHS Harnesses Coronavirus Forecasting Tech To Help Save Lives

NHS teams are being given access to cutting-edge predictive technology to help them save lives by forecasting coronavirus hospitalisations.

As the Government eases lockdown, the new Joint Biosecurity Centre is being asked to give the NHS locally advance warning of any uptick in coronavirus admissions.

This is being complimented by a machine learning-powered tool for the NHS based on Bayesian hierarchical modelling to warn hospitals so they can divert staff, beds and other equipment such as oxygen or ventilators needed to tackle COVID-19 cases.

Despite many predictions to the contrary, the NHS was not overwhelmed by 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.

Now the country is through the first phase of the virus, the NHS is working to increase routine services that had to pause during the peak of the epidemic, while also remaining ready to deal with smaller localised outbreaks.

The rollout of the new technology, built and developed by artificial intelligence firm Faculty, 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.

It works by learning from the data from previous outbreaks such as bed use and early warning indicators such as 111 call volumes, to model what might happen in the future.

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 said: “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.

This technology has already helped provide the NHS at a national level a clear understanding of bed capacity and availability across the country, and has helped ensure ventilators and oxygen supply has been targeted where it is needed so no hospital has run out.

Now local hospitals have been given access to the new forecasting tool that will help them to plan how to use their available capacity for both Covid-19 patients and routine care and operations, with the benefit of advance knowledge of how the need to care for more or less patients with the virus might change in the coming one to three weeks.

The data store is also helping with important new NHS research projects.

World-first research into how the virus impacted on some patients living with diabetes, led by Professor Jonathan Valabhji, the NHS National Clinical Director for diabetes and obesity, was only possible because of the datastore, and has enabled the health service to provide new advice for millions of people to help keep them safe.

The data store also enabled Professor Ben Goldacre, of the University of Oxford, and his team to undertake one of the largest studies to date on risk factors associated with COVID-19 death.

To protect patient confidentiality all data used is either pseudonymised, anonymised or aggregated and therefore does not identify any individual, with strict processes in place to ensure the data, which is owned by the NHS, is only used and viewed by those who need to see it, and only for as long as it is needed. 

The NHS is currently using Palantir, a private technology firm, to support the work of the NHS COVID-19 datastore. The NHS has signed a new four month contract with Palantir, which includes requirements to package up the work they’ve been doing so the service can go out to tender in an open procurement process.


The new Palantir contract will be published on Contracts Finder in due course:

  • The contract was a direct award using the GCloud framework
  • The contract contains the standard GCloud terms where relevant – any intellectual property rights derived from the work are reserved to the NHS.
  • The NHS is the data controller at all times – Palantir is a data processor and is only permitted to use the data as directed by the NHS
  • All data is de-identified or anonymised prior to loading into Palantir’s platform.