The UK‘s National Health Service (NHS) is trialing an AI system that predicts demand for intensive care beds and ventilators during the coronavirus pandemic.
Tests of the COVID 19 Capacity Planning and Analysis System (CPAS) began today at four hospitals in England. If the trials are successful, the tool will be rolled out across the country.
“CPAS allows individual hospitals to plan ahead, ensuring they can give the best care to every patient,” said Professor Jonathan Benger, the Chief Medical Officer of NHS Digital.
“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.
CPAS was built around a machine learning engine called Cambridge Adjutorium, which Cambridge University researchers unveiled last week.
The model was trained on data about existing COVID-19 cases, which was depersonalized but included lab results, hospitalization details, risk factors, and outcomes.
Early tests of the system produced highly accurate predictions about which patients needed ventilators or treatment in intensive care units (ICU). This convinced the NHS to industrialize the method in a capacity planning tool that hospitals across the country can use on a daily basis.
As well as forecasting which resources hospitals need, CPAS will provide demographic and healthcare information about the patients being admitted, which will be used to compare the effects of the coronavirus between different regions.
It also offers a simulation environment, which planners can use to test alternative planning strategies, such as increasing the number of available beds or changing the profile of patients admitted to hospitals.
The NHS claims that several other countries have already expressed an interest in the system, and has high hopes that the system will outlast the pandemic.
“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,” said Professor Benger.