QCovid was developed using data from more than 8 million adults in 1205 GP practices.
The model uses a number of factors such as a person’s age, ethnicity and existing medical conditions to predict their risk of catching COVID-19 and then dying or being admitted to hospital.
Researchers at Oxford University and collaborators across the UK have used anonymous data from primary care, hospitals, COVID-19 test results and death registries to determine which factors were associated with poor outcomes during the first wave of the virus.
Other factors incorporated in the model include level of deprivation, obesity, whether someone lived in residential care or was homeless, and a range of existing medical conditions, such as cardiovascular disease, diabetes, respiratory disease and cancer.
The Oxford-led team looked at data from January to April 2020 and from May 2020 to June 2020, to find out whether the tool accurately predicted severe outcomes due to COVID-19.
The results, published in the BMJ, showed it performed well in predicting outcomes. People in the dataset whose calculated risk put them in the top 20% of risk of death accounted for 94% of deaths from coronavirus.
Lead researcher Professor Julia Hippisley-Cox, a general practitioner and Professor of Clinical Epidemiology and General Practice at Oxford, said:
“Risk assessments to date have been based on the best evidence and clinical expertise, but have focused largely on single factors. The QCovid risk model provides a much more nuanced assessment of risk by taking into account a number of different factors that are cumulatively used to estimate risk.”
“This model will help inform clinical advice so that people can take proportionate precautions to protect themselves from COVID-19.”
Reacting to the research, Derek Hill, Professor of medical imaging science at UCL, said data collected during the first wave was 'out of date'.
He said: “Despite the very impressive amount of data and sophisticated data science that has gone into building QCovid, it has a fundamental flaw that dramatically reduces its practical usefulness.
"Your chance of being hospitalised or dying from COVID-19 is critically dependent on factors that the authors did not include in their model. The model does not know who actually was exposed to or was infected by the virus that causes COVID-19. The model has no information about individuals’ behaviour, such as whether they self-isolated, or worked in a high risk job, washed their hands properly, or wore a mask, nor of whether there was lots of COVID-19 infections in an individual’s neighbourhood.
"These missing data are arguably more important than the data included in the model at predicting who will get serious COVID-19. And we are already seeing in the second wave different patterns of spread and infection, as well as big differences in behaviour (such as widespread mask wearing)."
The Oxford-led team of researchers say they plan to regularly update their model as levels of immunity change, more data become available and behaviour in the population changes.
The research was funded by the NIHR following a commission by the Chief Medical Officer for England.