Anosmia, ageusia, and other COVID-19-like symptoms in association with a positive SARS-CoV-2 test, across six national digital surveillance platforms: an observational study

Abstract

Background: Multiple voluntary surveillance platforms were developed across the world in response to the COVID-19 pandemic, providing a real-time understanding of population-based COVID-19 epidemiology. During this time, testing criteria broadened and health-care policies matured. We aimed to test whether there were consistent associations of symptoms with SARS-CoV-2 test status across three surveillance platforms in three countries (two platforms per country), during periods of testing and policy changes.

Methods: For this observational study, we used data of observations from three volunteer COVID-19 digital surveillance platforms (Carnegie Mellon University and University of Maryland Facebook COVID-19 Symptom Survey, ZOE COVID Symptom Study app, and the Corona Israel study) targeting communities in three countries (Israel, the UK, and the USA; two platforms per country). The study population included adult respondents (age 18-100 years at baseline) who were not health-care workers. We did logistic regression of self-reported symptoms on self-reported SARS-CoV-2 test status (positive or negative), adjusted for age and sex, in each of the study cohorts. We compared odds ratios (ORs) across platforms and countries, and we did meta-analyses assuming a random effects model. We also evaluated testing policy changes, COVID-19 incidence, and time scales of duration of symptoms and symptom-to-test time.

Findings: Between April 1 and July 31, 2020, 514 459 tests from over 10 million respondents were recorded in the six surveillance platform datasets. Anosmia-ageusia was the strongest, most consistent symptom associated with a positive COVID-19 test (robust aggregated rank one, meta-analysed random effects OR 16·96, 95% CI 13·13-21·92). Fever (rank two, 6·45, 4·25-9·81), shortness of breath (rank three, 4·69, 3·14-7·01), and cough (rank four, 4·29, 3·13-5·88) were also highly associated with test positivity. The association of symptoms with test status varied by duration of illness, timing of the test, and broader test criteria, as well as over time, by country, and by platform.

Interpretation: The strong association of anosmia-ageusia with self-reported positive SARS-CoV-2 test was consistently observed, supporting its validity as a reliable COVID-19 signal, regardless of the participatory surveillance platform, country, phase of illness, or testing policy. These findings show that associations between COVID-19 symptoms and test positivity ranked similarly in a wide range of scenarios. Anosmia, fever, and respiratory symptoms consistently had the strongest effect estimates and were the most appropriate empirical signals for symptom-based public health surveillance in areas with insufficient testing or benchmarking capacity. Collaborative syndromic surveillance could enhance real-time epidemiological investigations and public health utility globally.

Funding: National Institutes of Health, National Institute for Health Research, Alzheimer's Society, Wellcome Trust, and Massachusetts Consortium on Pathogen Readiness.

Figure 1

Weekly tests per person by country (A), cases per person by country (B), test results by platform (C), and proportion of positive tests by country (D) and platform (E) Data reported by platform during the study period in Israel (blue), the UK (purple), and the USA (red). National data shown as solid lines while surveillance platform data shown as dashed lines. The transition from thin to thick lines represents when testing policies were considered open. CMU/UMD=Carnegie Mellon University and University of Maryland Facebook COVID-19 Symptom Survey. Israel-Corona=Corona Israel study. ZOE=ZOE COVID Symptom Study app.

Figure 2

Comparison of odds ratios by country and platform for the outcome of test result (positive vs negative) for symptoms (facets) Sensitivity analyses, mapping, and survey language are shown in the appendix (pp 1–15). Odds ratio scale is log-linear to enable comparisons across a wide range of effect estimates. CMU/UMD=Carnegie Mellon University and University of Maryland Facebook COVID-19 Symptom Survey. Israel-Corona=Corona Israel study. ZOE=ZOE COVID Symptom Study app.

Figure 3

Longitudinal ZOE data stratified by country, time from symptom onset to test, and testing-qualifying symptom era Time from symptom onset to test was stratified as early (<3 days) versus late (≥3 days). Stratifications show the impact on effect estimates (y-axis) for the three canonical symptoms of anosmia–ageusia, fever, and cough. The x-axis gives the effect estimates when censoring symptoms 0–14 days after the reported COVID-19 test, which might include later-onset symptoms, as well as measurement bias resulting from the knowledge of the test result. ZOE=ZOE COVID Symptom Study app.