The NHS has started trialling a machine learning system that aims to predict the upcoming demand for intensive care resources needed to treat patients suffering from the COVID-19 virus.
The COVID-19 Capacity Planning and Analysis System (CPAS) was developed by data scientists from NHS Digital and a team of researchers from the University of Cambridge. It uses data from Public Health England in order to help hospitals plan and manage the deployment of life-saving resources, such as ventilators, across the NHS.
The first stage alpha trials began this week at four hospitals across England in order to demonstrate the accuracy of the system and to see if it needs altered in order to cater to the needs of hospitals.
NHS Trusts keen on AI but are limited by poor access to data The NHS teams up with Apple and Google on coronavirus tracking app Amazon and Microsoft join NHS project battling pandemic Critical NHS cyber security checks suspended due to coronavirus response NHSX urged to “follow ethical best practice” in developing coronavirus app
NHS Digital Chief Medical Officer Professor Jonathan Benger said that being able “to predict demand for critical care beds, equipment and staff” is “essential”.
“CPAS allows individual hospitals to plan ahead, ensuring they can give the best care to every patient. At the same time, the wider NHS can ensure that the ventilators, other equipment and drugs that each intensive care unit will need are in place at exactly the time they are required.
"In the longer term, it is hoped that CPAS can be used to predict hospital length of hospital stay, discharge planning and wider intensive care demand in the time that will come after the pandemic.”
CPAS is based on a machine learning engine called Cambridge Adjutorium, which was developed by University of Cambridge engineer Professor Mihaela van der Schaar with the assistance of her multidisciplinary team.
Building a strong foundation for AI
How a Data-Train-Inference AI model positions your enterprise for long-term success
Cambridge Adjutorium is said to be a “highly flexible machine learning system” which was developed with medical researchers in mind. It was previously used to develop insights into cardiovascular disease and cystic fibrosis.
“Two weeks ago, the team shared a method with the world that showed it was possible to do capacity planning for COVID-19 patients,” said Dr Jem Rashbass, executive director for Master Registries and Data at NHS Digital.
“We recognised that there was an opportunity to industrialise the methods and deploy this as a service through the national infrastructure managed by NHSD and deliver a real data-driven planning tool to hospitals.”
If CPAS proves successful in the trial, the system will be launched nationwide across the NHS.
