Predictive symptoms for COVID-19 in the community: REACT-1 study of over 1 million people

Abstract

Background: Rapid detection, isolation, and contact tracing of community COVID-19 cases are essential measures to limit the community spread of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). We aimed to identify a parsimonious set of symptoms that jointly predict COVID-19 and investigated whether predictive symptoms differ between the B.1.1.7 (Alpha) lineage (predominating as of April 2021 in the US, UK, and elsewhere) and wild type.

Methods and findings: We obtained throat and nose swabs with valid SARS-CoV-2 PCR test results from 1,147,370 volunteers aged 5 years and above (6,450 positive cases) in the REal-time Assessment of Community Transmission-1 (REACT-1) study. This study involved repeated community-based random surveys of prevalence in England (study rounds 2 to 8, June 2020 to January 2021, response rates 22%-27%). Participants were asked about symptoms occurring in the week prior to testing. Viral genome sequencing was carried out for PCR-positive samples with N-gene cycle threshold value < 34 (N = 1,079) in round 8 (January 2021). In univariate analysis, all 26 surveyed symptoms were associated with PCR positivity compared with non-symptomatic people. Stability selection (1,000 penalized logistic regression models with 50% subsampling) among people reporting at least 1 symptom identified 7 symptoms as jointly and positively predictive of PCR positivity in rounds 2-7 (June to December 2020): loss or change of sense of smell, loss or change of sense of taste, fever, new persistent cough, chills, appetite loss, and muscle aches. The resulting model (rounds 2-7) predicted PCR positivity in round 8 with area under the curve (AUC) of 0.77. The same 7 symptoms were selected as jointly predictive of B.1.1.7 infection in round 8, although when comparing B.1.1.7 with wild type, new persistent cough and sore throat were more predictive of B.1.1.7 infection while loss or change of sense of smell was more predictive of the wild type. The main limitations of our study are (i) potential participation bias despite random sampling of named individuals from the National Health Service register and weighting designed to achieve a representative sample of the population of England and (ii) the necessary reliance on self-reported symptoms, which may be prone to recall bias and may therefore lead to biased estimates of symptom prevalence in England.

Conclusions: Where testing capacity is limited, it is important to use tests in the most efficient way possible. We identified a set of 7 symptoms that, when considered together, maximize detection of COVID-19 in the community, including infection with the B.1.1.7 lineage.

Fig 1. Flow chart showing numbers of participants by symptom status and PCR result.

(A) Rounds 2–7 and (B) round 8 of the REACT-1 study.

Fig 2. Results from univariate logistic regression models of PCR positivity for 26 surveyed symptoms.

Effect size estimates are expressed as odds ratios (95% confidence intervals) in rounds 2–7 (left) and round 8 (right).

Fig 3. Selected symptoms predictive of COVID-19.

Results of LASSO stability selection using 1,000 models (with 50% subsamples of training data from rounds 2–7). Mean (penalized) log odds ratios (log ORs) across all models are shown in the top panel. Positive regression coefficients are presented in teal, and negative in red. Only symptoms selected at least once are displayed. The selection proportions (selection prop.; proportion of 1,000 models that included each symptom) are shown in the middle panel; the horizontal dashed line shows the selection threshold of 50%. Symptoms are ordered according to their selection proportions, and selected symptoms are in black. The bottom panel shows the area under the curve (AUC) of models adding each variable in order of selection proportion (from left to right) in both holdout data from rounds 2–7 (grey) and data from round 8 (red).

Fig 4. Symptoms predictive of B.1.1.7 infection.

LASSO stability selection for symptoms predictive of B.1.1.7 (Alpha) lineage infection versus symptomatic people (aged 5+ years) testing PCR negative in round 8. Mean log odds ratio (Log OR) and selection proportion (selection prop.) are represented for each symptom in the top and bottom panels, respectively. Positive regression coefficients are presented in teal, and negative in red.

Fig 5. B.1.1.7 versus wild-type symptoms.

Comparison of symptom profile in B.1.1.7 (Alpha) lineage versus wild-type infection among 1,124 people testing positive in round 8 (other lineages excluded, N = 8). (A) Proportion of people reporting each symptom by lineage (left panel), and the differences in proportions with 95% confidence intervals (right panel). (B) Results of LASSO stability selection (using 1,000 models with 50% subsampling) with B.1.1.7 infection, versus wild-type infection as the outcome, summarized by the mean log odds ratio (Log OR) and selection proportion (selection prop.) for each of the symptoms selected at least once. Positive regression coefficients are presented in teal, and negative in red. The horizontal dashed line represents the selection threshold of 50%.