Classification Models for COVID-19 Test Prioritization in Brazil: Machine Learning Approach

Abstract

Background Controlling the COVID-19 outbreak in Brazil is a challenge due to the population’s size and urban density, inefficient maintenance of social distancing and testing strategies, and limited availability of testing resources. Objective The purpose of this study is to effectively prioritize patients who are symptomatic for testing to assist early COVID-19 detection in Brazil, addressing problems related to inefficient testing and control strategies. Methods Raw data from 55,676 Brazilians were preprocessed, and the chi-square test was used to confirm the relevance of the following features: gender, health professional, fever, sore throat, dyspnea, olfactory disorders, cough, coryza, taste disorders, and headache. Classification models were implemented relying on preprocessed data sets; supervised learning; and the algorithms multilayer perceptron (MLP), gradient boosting machine (GBM), decision tree (DT), random forest (RF), extreme gradient boosting (XGBoost), k-nearest neighbors (KNN), support vector machine (SVM), and logistic regression (LR). The models’ performances were analyzed using 10-fold cross-validation, classification metrics, and the Friedman and Nemenyi statistical tests. The permutation feature importance method was applied for ranking the features used by the classification models with the highest performances. Results Gender, fever, and dyspnea were among the highest-ranked features used by the classification models. The comparative analysis presents MLP, GBM, DT, RF, XGBoost, and SVM as the highest performance models with similar results. KNN and LR were outperformed by the other algorithms. Applying the easy interpretability as an additional comparison criterion, the DT was considered the most suitable model. Conclusions The DT classification model can effectively (with a mean accuracy≥89.12%) assist COVID-19 test prioritization in Brazil. The model can be applied to recommend the prioritizing of a patient who is symptomatic for COVID-19 testing.

Creating symptom-based criteria for diagnostic testing: a case study based on a multivariate analysis of data collected during the first wave of the COVID-19 pandemic in New Zealand

“…The symptom analyses presented here were performed on observational data routinely collected from patients presenting with acute respiratory infections during the first wave of COVID-19 in New Zealand. Similar analyses using machine learning algorithms for test prioritisation based on symptoms have been conducted using data from other countries including Israel and Brazil [ 22 – 24 ]. Given New Zealand’s current elimination strategy [ 3 ], high sensitivity in the targeting of testing to clinically compatible COVID-19 presentations is favoured over specificity during this initial phase of the pandemic, but this balance is likely to change with the implementation of the vaccination programme, opening of borders and increasing prevalence of seasonal acute respiratory illness.…”

Web-Based Skin Cancer Assessment and Classification Using Machine Learning and Mobile Computerized Adaptive Testing in a Rasch Model: Development Study

“…Three models of machine learning—naïve Bayes (NB) [ 25 ], k-nearest neighbors (KNN) [ 26 ], and logistic regression (LR) [ 27 - 31 ]—were applied to compare the model accuracy of classifying SC in the 1000×30 rectangle data set. The 2 training (70%) and testing (30%) sets (ie, the hold-out validation) were separated to examine the model’s accuracy with a proportion of 70:30, where the former was used to predict the latter.…”

Detecting dengue fever in children using online Rasch analysis to develop algorithms for parents: An APP development and usability study

“…In general, Sens is lower than Spec in DF prediction. [1,12,52] It is necessary to investigate whether alternative methods, such as CNN, [30][31][32][33] ANN, [34,35] KNN, [36] and/or LR, [37][38][39][40][41] can enhance the ACC of DF prediction.…”

“…However, despite the prevalence of DF, [22–27] there is a lack of developed applications that can effectively examine symptoms and predict the presence of the disease. Although the nonparametric HT fit statistic [28,29] has been used to develop algorithms for parents in 1 study on DF in children, [1] alternative diagnostic methods are needed for comparison, such as convolutional neural networks (CNN), [30–33] artificial neural networks (ANN), [34,35] K-nearest neighbors algorithms (KNN), [36] and/or logistic regression algorithms (LR). [37–41]…”