Using artificial intelligence as an aid to predict the risk of hospital readmission in patients with COVID-19
The successfully awarded research project through a funding call by Health Data Research UK and the Alan Turing Institute is led by Ewen M Harrison (University of Edinburgh). The research project will work to use national data to answer this key COVID-19 research question.
Share this page
Up to one third of patients hospitalised with COVID-19 are readmitted to hospital within 4 months. This figure is higher than what should be expected. These patients are more likely to have poorer long-term health, and some will die.
We don’t know why some patients are more likely to be readmitted, but it might be because they are:
living with other illnesses
living in lower income areas
recovering from severe COVID-19
receiving medical treatment that lowers their immune system
from an ethnic minority
We will use our data from 220,000 hospital patients within the UK. Our team have already securely linked these data to general practice and hospital NHS data in England and Scotland, vaccination data, and data about virus variants.
These datasets are necessary to provide information on patients’ hospital stay. The NHS data will outline the details of readmission.
We will use artificial intelligence (AI) methods to look at the risk of readmission, using information about a patient’s disease, treatment, and status at discharge. A risk calculator will be built, tested, and made available to healthcare staff, while undergoing regulatory approval. We will also work with the public to understand whether this tool would be useful if available to them.
Identifying those at risk of hospital readmission is important and is of public benefit for three reasons:
It will help identify patients most likely to have long-term health problems after COVID19.
It will allow safer discharge decisions.
It may enable targeted programmes to support patients at home and reduce the chance of readmission.