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 regression 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 applied machine learning techniques and provided a visualization of potential regions with high densities of COVID-19 as a risk map. We performed a retrospective analysis of individuals registered in "Dados do Bem", an app-based symptom tracker in use in Brazil. 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 associated with SARS-CoV-2 infection. Our final model obtained a competitive performance, with only 7% of false-negative users among the predicted as negatives (NPV = 0.93). From the 287,714 users still not tested, our model estimated that only 34.5% are potentially infected, thus reducing the need for extensive testing of all registered users. The model was incorporated by the "Dados do Bem" app aiming to prioritize users for testing. We developed an external validation in the state of Goias and found that of the 465 users selected, 52% tested positive. 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 in the general population of 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 [6,22,23]. Further, the large relative difference of hyposmia and dysgeusia frequencies for C19+ users suggests that hyposmia and dysgeusia are specific but not sensitive, i.e.…”

“…The AUC of our predictor (0.74) is in the range of the performance of the symptom-based COVID-19 predictor described in the literature. Other reported AUCs were as 0.68 [22], 0.74 [2] and 0.90 [4]. The considerably higher AUC of the latter predictor is explained by the inclusion of many asymptomatic patients who did not report any contact with a COVID-19 infected person.…”

Vaccine effectiveness of ChAdOx1 nCoV-19 against COVID-19 in a socially vulnerable community in Rio de Janeiro, Brazil: a test-negative design study

“…From the beginning of the pandemic until Nov 27, 2021, the region presented high rates of positive cases (7,852/100,000) and deaths (271/100,000)[ 9 ]. Since July 2020, a community broad testing strategy became available at the “Complexo da Maré” after an effort of civil society, non-governmental organizations (NGOs) and local community[ 10 ]. The testing was free of any charge and available on tents located in three different regions in Maré.…”

Modern Machine-Learning Predictive Models for Diagnosing Infectious Diseases

“…Dataset Specification. The most retrieved ML diagnosis models are based on signs and symptoms [19][20][21][22][23][24], followed by models based on laboratory tests [25,26]. Moreover, we found ML models based on clinical and electronic health records (EHRs) [27,28], ML models based on clinical reports [29], ML models based on image processing with other techniques [30,31], and ML models based on a combination of predictors including abnormal lab test results, the incidence rates, and signs and symptoms, as well as epidemiological features [32].…”