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.

The Internet of Things (IoT) paradigm allows small and resource constrained devices to send data through complex networks like the Internet. Bringing the IoT paradigm to the healthcare area, we can expand the connected health vision, enabling new Personal Health Devices (PHD) to share health information directly through the Internet. In this paper we explore the use of the MQTT (Message Queue Telemetry Transport) lightweight protocol together with the ISO/IEEE 11073 standard. We present new ways of connecting PHDs in home networks and the Internet by the use of MQTT Brokers, which will reduce the amount of data traffic.

The increasing availability of connected Personal Health Devices (PHDs) enables a new type of information to be available in the Internet: health information. Most of these devices have specific ways to connect and share information to the Internet through gateways or health managers, creating vertical solutions where one device just talks to one health service. In this context, this paper proposes an architecture that considers the use of different types of health managers and gateways, but keeping interoperability by the use of widely adopted standards. The main contribution of this work is the distribution of health managers in different locations, such as mobile devices and cloud applications, enabling the use of a single health service for different types of PHDs. The ISO/IEEE 11073 standard is used as core technology, enabling the transport of PHD information over different technologies and protocols. We also present a new classification of health managers based on requirements of legacy m-health services. In conclusion, the results of the integration with a real cloud-based connected health system are presented and evaluated.