article

New AI diagnostic can predict COVID-19 likelihood without a test

Tuesday, 12 May 2020

Researchers have developed an artificial intelligence diagnostic that can predict whether someone is likely to have COVID-19 based on their symptoms.

The initial phase of the research, which is published in Nature Medicine, is a collaboration between health science company ZOE, Massachusetts General HospitalKing’s College London, and the University of Nottingham.

The AI model uses data from the COVID Symptom Study app, which in just six weeks has grown to over 3 million people reporting their health to help fight the epidemic. The model is able to predict COVID-19 infection without patients having to be tested, by comparing them with people who have used the app to share their symptoms and the results of traditional COVID tests.

Two clinical trials are due to start shortly in both the US and the UK. The diagnostic is a not for profit initiative which cannot completely replace clinical tests, but may have great promise for populations where access to testing is limited. The app also does not present the same privacy concerns that track and trace apps do.

Dr Ana Valdes

Dr Ana Valdes from the School of Medicine at the University of Nottingham, is one of the collaborators on the study. Dr Valdes says: “Scientists in the School of Medicine at Nottingham have been collaborating with groups from London and Harvard in the analysis of data from a COVID-19 symptom tracker app. What this international group of clinicians, computer scientists and biomedical scientists report in Nature Medicine is that loss of smell is a key symptom for predicting the presence of COVID-19.

“We looked at app report data from over 2.6 million people from the US and the UK and focused on those who had already had a test for COVID-19 and reported some symptoms. They find that people who had a test for COVID those who reported a loss of the sense of smell were 3 times more likely to have tested positive for COVID-19 than negative. They then put together a mathematical model to predict likelihood of COVID given the full set of symptoms presented and conclude that 17% of those who reported some symptoms such as fever of cough between March and April were likely to actually have had COVID-19."

More than 3.3 million people globally have used the COVID Symptom Study app to report daily on their health status, whether they feel well or have any new symptoms such as persistent cough, fever, fatigue and loss of taste or smell (anosmia). In the UK, the data is being used to help inform scientific decision making by the National Health Services of England, Wales and Scotland. Following clinical trials, the app may be able to share a diagnosis with study participants, playing a crucial role in aiding the UK to be able to safely lift lockdown and detect a second wave sooner.

In the study published today in Nature Medicine, the researchers analysed data gathered from 2.5 million people in the US and UK who had been regularly logging their health status in the app, around a third of whom had logged symptoms associated with COVID-19. Of participants in the US and the UK, 18,374 reported having had a test for coronavirus, with 7,178 people testing positive.

The research team investigated which symptoms known to be associated with COVID-19 were most likely to be associated with a positive test. The study demonstrates the wide range of symptoms caused by COVID compared to cold and flu, and the danger of focusing only on fever and cough as the world looks to reopen without reigniting the epidemic. Loss of taste and smell (anosmia) was particularly striking, with two thirds of users testing positive for coronavirus infection reporting this symptom compared with just over a fifth of the participants who tested negative. The findings suggest that anosmia is a stronger predictor of COVID-19 than fever, supporting anecdotal reports of loss of smell and taste as a common symptom of the disease.

The researchers then created a mathematical model that predicted with nearly 80% accuracy whether an individual is likely to have COVID-19 based on their age, sex and a combination of four key symptoms: loss of smell or taste, severe or persistent cough, fatigue and skipping meals. Applying this model to the entire group of over 800,000 app users experiencing symptoms predicted that just under a fifth of those who were unwell (17.42%) were likely to have COVID-19 at that time. 

The team is now focused on launching two clinical trials to test more sophisticated AI models to predict COVID based on just two days of symptoms. One trial planned at Massachusetts General Hospital is focused on high risk populations in Boston. Around 5,000 people will be tested for antibodies at the start of the trial, they will use the app daily, and then be retested when showing symptoms. The app will be launched in Spanish as part of this effort. A second trial with King’s College London is due to start shortly in the UK. 

Combining this AI prediction with widespread adoption of the COVID Symptom Study app could help to identify those who are likely to be infectious as soon as the earliest symptoms start to appear, focusing tracking and testing efforts where they are most needed and so helping us to navigate reopening the economy without triggering a resurgence of the virus.‍

A spokesperson from the NHS said, “We are grateful to the innovative developers of the C-19 Symptom Study app. The app is supporting the NHS and Government to manage the COVID-19 crisis.”  

Story credits

More information is available from Dr Ana Valdes from the School of Medicine at the University of Nottingham, at ana.valdes@nottingham.ac.uk ; or Charlotte Anscombe, Media Relations Manager in the Press Office at the University of Nottingham, on +44 (0)115 74 84417, charlotte.anscombe@nottingham.ac.uk

Charlotte Anscombe - Media Relations Manager - Faculty of Medicine and Health Sciences
Email: charlotte.anscombe@nottingham.ac.uk
Phone: 0115 748 4417
Location:

Our academics can now be interviewed for broadcast via our Media Hub, which offers a Quicklink fixed camera and ISDN line facilities at Jubilee campus. For further information please contact a member of the Press Office on +44 (0)115 951 5798, email  pressoffice@nottingham.ac.uk

For up to the minute media alerts, follow us on Twitter

Notes to editors:

The University of Nottingham is a research-intensive university with a proud heritage. Studying at the University of Nottingham is a life-changing experience and we pride ourselves on unlocking the potential of our students. We have a pioneering spirit, expressed in the vision of our founder Sir Jesse Boot, which has seen us lead the way in establishing campuses in China and Malaysia - part of a globally connected network of education, research and industrial engagement. Ranked 103rd out of more than 1,000 institutions globally and 18th in the UK by the QS World University Rankings 2022, the University’s state-of-the-art facilities and inclusive and disability sport provision is reflected in its crowning as The Times and Sunday Times Good University Guide 2021 Sports University of the Year. We are ranked eighth for research power in the UK according to REF 2014. We have six beacons of research excellence helping to transform lives and change the world; we are also a major employer and industry partner - locally and globally. Alongside Nottingham Trent University, we lead the Universities for Nottingham initiative, a pioneering collaboration which brings together the combined strength and civic missions of Nottingham’s two world-class universities and is working with local communities and partners to aid recovery and renewal following the COVID-19 pandemic.

More news…

Media Relations - External Relations

The University of Nottingham
C Floor, Pope Building (Room C4)
University Park
Nottingham, NG7 2RD

telephone: +44 (0) 115 951 5798
email: pressoffice@nottingham.ac.uk