Benchmark methodological approach for the application of artificial intelligence to lung ultrasound data from COVID-19 patients: From frame to prognostic-level.

Automated ultrasound imaging assessment of the effect of CoronaVirus disease 2019 (COVID-19) on lungs has been investigated in various studies using artificial intelligence-based (AI) methods. However, an extensive analysis of state-of-the-art Convolutional Neural Network-based (CNN) models for frame-level scoring, a comparative analysis of aggregation techniques for video-level scoring, together with a thorough evaluation of the capability of these methodologies to provide a clinically valuable prognostic-level score is yet missing within the literature. In addition to that, the impact on the analysis of the posterior probability assigned by the network to the predicted frames as well as the impact of temporal downsampling of LUS data are topics not yet extensively investigated. This paper takes on these challenges by providing a benchmark analysis of methods from frame to prognostic level. For frame-level scoring, state-of-the-art deep learning models are evaluated with additional analysis of best performing model in transfer-learning settings. A novel cross-correlation based aggregation technique is proposed for video and exam-level scoring. Results showed that ResNet-18, when trained from scratch, outperformed the existing methods with an F1-Score of 0.659. The proposed aggregation method resulted in 59.51%, 63.29%, and 84.90% agreement with clinicians at the video, exam, and prognostic levels, respectively; thus, demonstrating improved performances over the state of the art. It was also found that filtering frames based on the posterior probability shows higher impact on the LUS analysis in comparison to temporal downsampling. All of these analysis were conducted over the largest standardized and clinically validated LUS dataset from COVID-19 patients.

Multi-objective automatic analysis of lung ultrasound data from COVID-19 patients by means of deep learning and decision trees.

COVID-19 raised the need for automatic medical diagnosis, to increase the physicians' efficiency in managing the pandemic. Among all the techniques for evaluating the status of the lungs of a patient with COVID-19, lung ultrasound (LUS) offers several advantages: portability, cost-effectiveness, safety. Several works approached the automatic detection of LUS imaging patterns related COVID-19 by using deep neural networks (DNNs). However, the decision processes based on DNNs are not fully explainable, which generally results in a lack of trust from physicians. This, in turn, slows down the adoption of such systems. In this work, we use two previously built DNNs as feature extractors at the frame level, and automatically synthesize, by means of an evolutionary algorithm, a decision tree (DT) that aggregates in an interpretable way the predictions made by the DNNs, returning the severity of the patients' conditions according to a LUS score of prognostic value. Our results show that our approach performs comparably or better than previously reported aggregation techniques based on an empiric combination of frame-level predictions made by DNNs. Furthermore, when we analyze the evolved DTs, we discover properties about the DNNs used as feature extractors. We make our data publicly available for further development and reproducibility.

Knowledge, Attitudes and Practices of Mozambican Public Employees in relation to the Prevention of COVID-19 / Conhecimentos, Atitudes e Práticas dos Funcionários Públicos de Moçambique em relação à Prevenção da COVID-19

In the middle of December 2019, COVID-19 appeared in the Chinese City of Wuhan. It is a pathology that quickly spread around the world, counting, until the completion of the present study, with more than 2 million infected and about 140 thousand dead. The aim of the present study was to analyze knowledge, attitudes and practices of public workers from Mozambique on the prevention of COVID-19. To this end, 126 public workers in Mozambique (79 men, 43 women and 4 who chose not to disclose their gender) answered a closed questionnaire applied to the Google Form online platform. The questionnaire was open for 5 days (two weekend days and three business days). The results revealed that most employees have basic knowledge and appropriate measures for the prevention of COVID-19, more than half adopt behaviors conducive to disease prevention and less than half effectively comply with preventive actions guided by governmental and the health sector. The results suggest that public officials are knowledgeable, however efforts should be made to carry out educational actions to improve attitudes and change practices related to the prevention of COVID-19.

Nos meados do mês de Dezembro do ano 2019, surgiu a COVID-19, na Cidade Chinesa de Wuhan. Trata-se de uma patologia que rapidamente se espalhou pelo mundo, contando, até a realização do presente estudo, com mais de 2 milhões de infectados e cerca de 140 mil mortos. O objectivo do presente estudo foi de analisar o grau de conhecimentos, atitudes e práticas dos funcionários públicos de Moçambique sobre a prevenção da COVID-19. Para tal, 126 funcionários públicos de Moçambique (79 homens, 43 mulheres e 4 que preferiram não revelar o sexo) responderam a um questionário fechado aplicado na plataforma online Google Form. Refira-se que o questionário esteve aberto durante 5 dias (dois de final de semana e três dias úteis). Os resultados revelaram que a maior parte dos funcionários tem conhecimentos básicos e de medidas apropriadas para a prevenção da COVID-19, mais que a metade assume comportamentos conducentes à prevenção da doença e menos que a metade cumpre eficazmente com acções preventivas orientadas pelas entidades governamentais e de saúde. Os resultados sugerem que os funcionários públicos têm conhecimentos, contudo devem ser envidados esforços no sentido de serem realizadas acções educativas para o melhoramento das atitudes e mudança das práticas relativas à prevenção da COVID-19.

Assessment of atmospheric pollution in the vicinity of a tin and lead industry using lichen species Canoparmelia texana.

This paper examines the viability of using Canoparmelia texana lichen species as a bioindicator of air pollution by radionuclides and rare earth elements (REEs) in the vicinity of a tin and lead industry. The lichen and soil samples were analyzed for uranium, thorium and REEs by instrumental neutron activation analysis. The radionuclides (226)Ra, (228)Ra and (210)Pb were determined either by Gamma-ray spectrometry (GRS) (soils) or by radiochemical separation followed by gross alpha and beta counting using a gas flow proportional counter (lichens). The lichens samples concentrate radionuclides (on the average 25-fold higher than the background for this species) and REEs (on the average 10-fold higher), therefore they can be used as a fingerprint of contamination by the operation of the tin industry.