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.
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.
Authors: Pier Carmine Passarelli; Michele Antonio Lopez; Giuseppe Niccolò Mastandrea Bonaviri; Franklin Garcia-Godoy; Antonio D'Addona Journal: Am J Dent Date: 2020-06 Impact factor: 1.522
Authors: Marcelo Freitas do Prado; Bianca Brandão de Paula Antunes; Leonardo Dos Santos Lourenço Bastos; Igor Tona Peres; Amanda de Araújo Batista da Silva; Leila Figueiredo Dantas; Fernanda Araújo Baião; Paula Maçaira; Silvio Hamacher; Fernando Augusto Bozza Journal: Rev Bras Ter Intensiva Date: 2020-06-24
Authors: D Paolotti; A Carnahan; V Colizza; K Eames; J Edmunds; G Gomes; C Koppeschaar; M Rehn; R Smallenburg; C Turbelin; S Van Noort; A Vespignani Journal: Clin Microbiol Infect Date: 2014-01 Impact factor: 8.067
Authors: I T Peres; L S L Bastos; J G M Gelli; J F Marchesi; L F Dantas; B B P Antunes; P M Maçaira; F A Baião; S Hamacher; F A Bozza Journal: Public Health Date: 2021-01-15 Impact factor: 2.427
Authors: Cristina Menni; Ana M Valdes; Claire J Steves; Tim D Spector; Maxim B Freidin; Carole H Sudre; Long H Nguyen; David A Drew; Sajaysurya Ganesh; Thomas Varsavsky; M Jorge Cardoso; Julia S El-Sayed Moustafa; Alessia Visconti; Pirro Hysi; Ruth C E Bowyer; Massimo Mangino; Mario Falchi; Jonathan Wolf; Sebastien Ourselin; Andrew T Chan Journal: Nat Med Date: 2020-05-11 Impact factor: 53.440
Authors: David A Drew; Long H Nguyen; Tim D Spector; Andrew T Chan; Claire J Steves; Cristina Menni; Maxim Freydin; Thomas Varsavsky; Carole H Sudre; M Jorge Cardoso; Sebastien Ourselin; Jonathan Wolf Journal: Science Date: 2020-05-05 Impact factor: 47.728
Authors: Otavio T Ranzani; Amanda A B Silva; Igor T Peres; Bianca B P Antunes; Thiago W Gonzaga-da-Silva; Daniel R Soranz; José Cerbino-Neto; Silvio Hamacher; Fernando A Bozza Journal: Clin Microbiol Infect Date: 2022-02-09 Impact factor: 13.310
Authors: Fausto Baldanti; Nirmal K Ganguly; Guiqiang Wang; Martin Möckel; Luke A O'Neill; Harald Renz; Carlos Eduardo Dos Santos Ferreira; Kazuhiro Tateda; Barbara Van Der Pol Journal: Crit Rev Clin Lab Sci Date: 2022-03-15 Impact factor: 6.250
Authors: Nicolas Munsch; Stefanie Gruarin; Jama Nateqi; Thomas Lutz; Michael Binder; Judith H Aberle; Alistair Martin; Bernhard Knapp Journal: Wien Klin Wochenschr Date: 2022-04-13 Impact factor: 2.275