Predicting Global Trends in COVID-19 Cases Via Online Symptom Checkers Self-Assessments

Abstract

Background: During the coronavirus disease 2019 (COVID-19) pandemic, digital health has become increasingly important due to physical distance constraints. Online symptom checkers are digital health solutions which provide a differential diagnosis based on a user’s symptoms. Aggregation of these diagnoses across a population allows for inference about the current trends in overall health.

Methods: In this study, we analyze spatial and temporal data of the symptom checker Symptoma (www.symptoma.com) and correlate these data with the number of newly confirmed COVID-19 cases.

Findings: We find a high correlation between the number of Symptoma users assessed to have a high risk of a COVID-19 infection and the official COVID-19 infection numbers for many countries. Furthermore, we show that for the majority of countries the symptom checker is predictive (median +5 days) of the official infection numbers.

Interpretation: Our findings could help to detect coronavirus hot spots early on and thereby become an interesting tool in fighting against the pandemic.

Note: Funding: This study has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 830017 and by the Austrian Research Promotion Agency under grant agreement No 880939 (supported by the Federal Ministries Republic of Austria for Digital and Economic Affairs and Climate Action, Environment, Energy, Mobility, Innovation and Technology).

Declaration of Interests: All authors are employees of Symptoma GmbH. JN holds shares of Symptoma.

Keywords: COVID-19; Symptom Checker; Multi Lingual; Outbreak Prediction