App-based symptom tracking to optimize SARS-CoV-2 testing strategy using machine learning

Abstract

Background Tests are scarce resources, especially in low and middle-income countries, and the optimization of testing programs during a pandemic is critical for the effectiveness of the disease control. Hence, we aim to use the combination of symptoms to build a predictive model as a screening tool to identify people and areas with a higher risk of SARS-CoV-2 infection to be prioritized for testing. Materials and methods We performed a retrospective analysis of individuals registered in "Dados do Bem," a Brazilian app-based symptom tracker. We applied machine learning techniques and provided a SARS-CoV-2 infection risk map of Rio de Janeiro city. Results From April 28 to July 16, 2020, 337,435 individuals registered their symptoms through the app. Of these, 49,721 participants were tested for SARS-CoV-2 infection, being 5,888 (11.8%) positive. Among self-reported symptoms, loss of smell (OR[95%CI]: 4.6 [4.4–4.9]), fever (2.6 [2.5–2.8]), and shortness of breath (2.1 [1.6–2.7]) were independently associated with SARS-CoV-2 infection. Our final model obtained a competitive performance, with only 7% of false-negative users predicted as negatives (NPV = 0.93). The model was incorporated by the "Dados do Bem" app aiming to prioritize users for testing. We developed an external validation in the city of Rio de Janeiro. We found that the proportion of positive results increased significantly from 14.9% (before using our model) to 18.1% (after the model). Conclusions Our results showed that the combination of symptoms might predict SARS-Cov-2 infection and, therefore, can be used as a tool by decision-makers to refine testing and disease control strategies.

Symptoms associated with a COVID-19 infection among a non-hospitalized cohort in Vienna

“…The results also show that the symptoms experienced by C19+ significantly differ, except for dyspnea, to those experienced by C19−. This agrees with other studies that also reported hyposmia, dysgeusia, and fever as significantly increased in C19+ persons [ 6 , 21 , 22 ]. Further, the large relative difference of hyposmia (+155%) and dysgeusia (+101%) frequencies for C19+ in comparison to C19− users suggests that hyposmia and dysgeusia are specific but not sensitive, i.e.…”

How Artificial Intelligence and New Technologies Can Help the Management of the COVID-19 Pandemic

“…The function generates a Health Code associated with different colors (green, yellow, red) based on the risk of being infected [ 22 ].…”

“…The app Dados do Bem was developed in Brazil to track COVID-19 symptoms: applying machine learning techniques, it was possible to provide a SARS-CoV-2 infection risk map of the city of Rio de Janeiro, representing a potential tool for decision-makers to refine disease-control strategies [ 20 , 22 ].…”

Choice of SARS-CoV-2 diagnostic test: challenges and key considerations for the future

“…Digital screening tools are also in development to track COVID-19 symptoms and support the identification of infection. In Brazil, where testing resources are limited, an app-based symptom tracker has been developed to help prioritize those who should be tested [ 89 ]. After implementation of the app, the proportion of positive results increased significantly from 14.9% to 18.1%.…”