NHS QCovid risk prediction algorithm accuracy

Occurred: March 2021

Can you improve this page?
Share your insights with us

The reliability of QCovid, an algorithm developed by the University of Oxford to predict the risk of someone catching, being admitted to hospital, or dying from COVID-19 in England, UK, is in the spotlight for wrongly identifying some patients as high risk.

Based on data from 'the first few months of the pandemic', the model took into account various socio-economic indicators, underlying health conditions such as diabetes and heart disease, body-mass index, and postcode (within Britain), among other factors, to return an 'absolute risk of a covid-19 associated death' or hospitalisation.

Following the launch of the tool, an additional 1.7 million people were instructed to shield, with around 800,000 people moved up the priority list to be vaccinated. These include women with previous gestational diabetes but who were healthy and could not understand why it was being recommended that they shield.

Some General Practitioners also described seeing healthy young men on the list. Young, healthy people who are less likely to have measurements such as body weight recorded in their health records, Irene Petersen, professor of epidemiology and health informatics at University College London, told The Guardian.

An updated version of the system was released in November 2021.

Operator: National Health Service (NHS)
Developer: University of Oxford; NHS Digital

Country: UK

Sector: Govt - health

Purpose: Predict COVID-19 risk

Technology: Prediction algorithm
Issue: Accuracy/reliability



News, commentary, analysis

Page info
Type: Incident
Published: January 2023
Last updated: June 2023