Transmission electron micrograph of SARS-CoV-2 virus particles captured by NIAID
The AI model uses data from the COVID Symptom Study app to predict COVID-19 infection.
Researchers at King’s College London, Massachusetts General Hospital and health science company ZOE have developed an artificial intelligence diagnostic that can predict whether someone is likely to have COVID-19 based on their symptoms. Their findings are published today in Nature Medicine.
The AI model uses data from the COVID Symptom Study app to predict COVID-19 infection, by comparing people’s symptoms and the results of traditional COVID tests. Researchers say this may provide help for populations where access to testing is limited. Two clinical trials in the UK and the US are due to start shortly.
More than 3.3 million people globally have downloaded the app and are using it 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 this study, the researchers analysed data gathered from just under 2.5 million people in the UK and US who had been regularly logging their health status in the app, around a third of whom had logged symptoms associated with COVID-19. Of these, 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. They found a wide range of symptoms compared to cold and flu, and warn against focusing only on fever and cough. Indeed, they found 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.
Researchers suggest that combining this AI prediction with widespread adoption of the 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.
Our results suggest that loss of taste or smell is a key early warning sign of COVID-19 infection and should be included in routine screening for the disease. We strongly urge governments and health authorities everywhere to make this information more widely known, and advise anyone experiencing sudden loss of smell or taste to assume that they are infected and follow local self-isolation guidelines.– Professor Tim Spector, King’s College London
The Latest Updates from Bing News & Google News
Go deeper with Bing News on:
AI prediction
- How COVID-19 Broke AI, And Why AI May Break Againon February 28, 2021 at 2:40 pm
The unprecedented circumstances caused by COVID-19 caused many AIs to break. How did these AIs break and what can your business do to ensure that future AIs do not suffer from the same vulnerabilities ...
- Zorroa Launches Boon AI; No-code Machine Learning for Media-driven Organizationson February 27, 2021 at 6:06 am
Zorroa Corp., a leading provider of accessible machine learning (ML) integration solutions backed by Gradient Ventures, Google’s AI-focused venture fund, today officially launched a first-of-its-kind ...
- Blockshipping and 2021.AI Join Forces to Drive Efficiencies in the Global Container Shipping Industry with Artificial Intelligenceon February 27, 2021 at 12:01 am
The partnership between Blockshipping and 2021.AI will help overcome a 40-year old industry challenge. Using AI, the two companies will materially improve operational efficiency for marine container ...
- Edge AI Market Size, Share & Trends Analysis Report With Growth Forecast 2020-2027on February 26, 2021 at 4:37 pm
The global Edge AI market report scope includes detailed study covering underlying factors influencing the industry ...
- AI in Fashion Market Projected To Grow 38.20% During the Forecast Periodon February 26, 2021 at 8:28 am
Whipsmartmi com announces a new report AI in fashion Market added to its research database AI in fashion Market is projected to growing at a CAGR of 38 20 during the forecasting period 2021 2027 View ...
Go deeper with Google Headlines on:
AI prediction
Go deeper with Bing News on:
AI predicting COVID-19 infection
- VinBrain reaches final round of global competition “COVID-19 Pandemic Response Challenge”on February 24, 2021 at 5:05 am
The VinBrain team in the US has reached the final round of the Pandemic Response Challenge held by XPRIZE and Cognizant. This competition, which has prize money of $500,000, aims to harness the power ...
- Analyzing electronic health records can be a fast and accurate way to predict risk of death from COVID-19on February 17, 2021 at 2:30 pm
Hossein Estiri, PhD, is lead author on a study that utilized artificial intelligence to leverage the data compiled in electronic health records to compute individual-level risk scores for death ...
- Vocalis Health's COVID-19 Screening Tool Successfully Validated in Large Clinical Studyon February 17, 2021 at 6:15 am
Vocalis Health, a company pioneering AI-based vocal biomarkers in healthcare, today announced results of a clinical study conducted in collaboration with the Municipal Corporation of Greater Mumbai ...
- Artificial Intelligence for Drug Discovery and Development in the era of Covid-19on February 11, 2021 at 4:00 pm
It takes $2.6 billion for developing a new drug that gains market approval as per the research conducted by Tufts Center for the Study of Drug Development.
- Could AI Help Predict How Ill a COVID-19 Patient Could Become?on February 10, 2021 at 4:00 pm
to study epigenetic biomarkers that could predict patient response to SARS-CoV2 (COVID-19) infection, the company reported in a news release. The goal is to develop an on-site, clinical test that ...