Doutorado
URI permanente desta comunidadehttps://repositorioacademico.universidadebrasil.edu.br/handle/123456789/914
Navegar
3 resultados
Resultados da Pesquisa
Item Aplicações de modelos computacionais de análise de dados biomédicos em plataformas de dispositivos móveis(Universidade Brasil, 2020) Sousa, José Vigno Moura; Almeida, Vilson Rosa de; Costa, Mardoqueu Martins daThis work develops CNNPulmona and CNNCardio, implementations of computational models for optimization of analysis of biomedical data from chest radiography (CXR) and electrocardiogram (ECG), respectively, deployable in mobile device platforms, in addition to a comparison of several methods of signal compression. CNNPulmona is an approach for classifying chest Xray images into three classes: bacterial pneumo nia, viral pneumonia (Covid19 or other type) and healthy lung. Convolutional Neural Networks are used, based on pretrained networks in conjunction with a quantization process, by means of the TensorFlow Lite platform method, thereby reducing the com putational cost. The cascade classification method is used, which makes it possible to divide the classifications into different stages; thus, it was possible to obtain 99.16% ac curacy in the classification of images with suspicion of Covid19. The resulting mobile application program also features a simple and intuitive user interface. In CNNCardio, a new method to classify electrocardiogram signals on mobile devices is proposed, which can classify different arrhythmias according to the EC57 standard of the Asso ciation for the Advancement of Medical Instrumentation. A convolutional neural net work was built, trained and validated with the MITBIH arrhythmia dataset, in which this database has 5 different classes: normal beat, premature supraventricular beat, pre mature ventricular contraction, ventricular beat fusion, normal and unclassifiable beat. After being trained and validated, the model is submitted to a posttraining quantization stage using the TensorFlow Lite conversion method.The results obtained were very sat isfactory, before and after quantization; the convolutional neural network obtained an accuracy of 99%. With the quantization technique, it was possible to obtain a significant reduction in the size of the model, thus enabling the development of the mobile applica tion; this reduction was approximately 90% in relation to the size of the original model. Additionally, the behavior of different signals was compared, when applied to different compression techniques, in order to test and find the best compression techniques for distinct types of biomedical signals, also proving that different types of biomedical sig nals behave distinctly in different types compression of biomedical signals, the results of this comparison of signal compression methods were very satisfactory, demonstrating that different types of compression can be used on signals for better results.Item Presença de Anti-SARS-CoV-2 no leite humano pasteurizado após vacinação: Anti-SARS-CoV-2 no leite humano pasteurizado(Universidade Brasil, 2024) Carvalho, Nara Magalhães; Marciano, Fernanda RobertaThis study aimed to investigate the presence of IgA and IgG antibodies, specific for Severe Acute Respiratory Syndrome (SARS-CoV-2), in human milk from 103 lactating women submitted to the Primary Vaccination Scheme (PVS) before or during pregnancy or after delivery. The influence of pasteurization on human milk, the number of vaccine doses received and the economic aspects of the mother were evaluated. The samples were collected and stored in the public milk bank in the city of Teresina/PI, subjected to pasteurization (heated to a temperature of 62.5 ºC and cooled to 5 ºC and analyzed by immunoenzymatic assays. The samples were divided into two groups: observational group (OG) with 83/103 (80.5%) and control group (CG) with 20/103 (19.5%) samples. Results: In the observational group, 52% (43/83) were positive for IgA. It was observed that among the positive ones, 30/43 (70%) were lactating women who had undergone the Primary Vaccination Scheme before pregnancy and 13 (30%) had undergone the Primary Vaccination Scheme during pregnancy or after delivery. No positive samples for IgG were identified in the Observational Group. In the Control Group, 20/103 samples were evaluated before the pasteurization process, that is, Raw Human Milk (RBM), and the same samples were evaluated after pasteurization (PBM). In Raw Human Milk (RBM), 11/20 (55%) were positive for IgA and 3/20 (15%) were inconclusive for IgA and IgG. In the control group, there was no statistical difference between the positive results for specific antibodies in Raw and Pasteurized Human Milk. Conclusion: There was a predominance of the presence of anti-SARS-CoV-2 IgA in human milk among women who underwent the Primary Vaccination Schedule before pregnancy, with a higher level of IgA among those who underwent the Complete Vaccination Schedule with four doses before delivery. No correlations were observed between IgA content and the mother's economic conditions.Item Impacto da vacinação contra a Covid-19: uma análise do território piauiense(Universidade Brasil, 2022) Pereira, Katyane Leite Alves; Marciano, Fernanda RobertaThe behavior of SARS-CoV-2, which causes Covid-19, has challenged world science, however the completion of vaccination against the pathogen has brought the prospect of curbing and controlling the pandemic scenario. The objective was to evaluate the vaccine impact on notifications of Covid-19 in Piauí. This is an exploratory, descriptive and epidemiological study with a quantitative approach, carried out from secondary data available on the public domain website of the state secretary of health of Piauí. The sample comprised all confirmed cases and deaths from Covid-19 notified from January 1 to December 31, 2021. Data collection took place from January to February 2022 and included hospitalizations in clinical, intensive care, stabilization and hospital beds. respirators, new cases, deaths and vaccination records. The results showed stability in the occupation of clinical beds, intensive care units, stabilization units and beds with respirators in the last 14 days of 2021. There was an increase in notifications from January to May 2021 with a greater number of daily cases notified on May 18, indicating 1753 confirmed cases with a decline in cases in June and a downward trend with a variation rate of -39.71%. With regard to deaths resulting from the disease, the highest daily number observed in the state of Piauí occurred on April 11, with 49 deaths. Vaccination recorded a peak of 404,842 vaccine doses dispensed on December 22, with a variation rate of -48.83%. The correlation analysis showed that vaccination is inversely proportional to all hospitalizations and deaths, showing that the higher the vaccination, the lower the hospitalization and deaths from the new Coronavirus, but it did not prevent the transmission of the disease from person to person. Thus, it is necessary that protective measures be maintained and that new studies be carried out in the path of elucidation and genomic surveillance, with a view to persistent immunity and in the immune system escapes to mutations resulting from SARS-CoV-2 infection.