Browsing by Issue Date, starting with "2021-11-10"
Now showing 1 - 3 of 3
Results Per Page
Sort Options
- Monitorização da mortalidade: Outubro 2021Publication . Torres, Ana Rita; Silva, Susana Pereira; Rodrigues, Ana PaulaEste relatório tem como objetivo descrever e interpretar o padrão de mortalidade observado durante o mês de outubro, em Portugal, entre as semanas 39/2021 e 43/2021 (27 de setembro a 31 de outubro).
- The importance of smoking cessation during pregnancy and its association with perinatal outcomesPublication . Silva, Ana Inês; Camelo, Alexandra; Madureira, Joana; Reis, Ana Teresa; Barbosa Jr, Fernando; Teixeira, João Paulo; Costa, CarlaIn utero exposure to tobacco smoke is associated with an increased risk of multiple adverse perinatal outcomes. Smoking cessation during pregnancy has been related to the improvement of these outcomes, but often relies on self-reporting, impairing an accurate assessment of smoking cessation impact on newborńs health. Building on data obtained in the frame of the NEOGENE project, this work aimed to estimate the association between smoking cessation among pregnant women, confirmed by maternal urinary cotinine concentrations, and perinatal outcomes. The study population included 595 pregnant women who sought prenatal care in a public hospital in Porto (Portugal), from April 2017 to July 2018. Data on tobacco consumption and cessation was obtained in a face-to-face interview, during the hospital stay. Perinatal outcomes, namely birth weight (BW), length (BL) and head circumference (HC) were retrieved from the hospital medical records. Maternal self-reported tobacco use was validated by urinary cotinine concentrations, using the solid-phase competitive ELISA technique. Maternal active smoking was associated with a significant decrease in BW, BL and HC of 157.66 g (p < 0.001), 0.78 cm (p = 0.001) and 0.39 cm (p = 0.016). Notably, maternal smoking cessation led to a significant increase in BW of approximately 172 g (p = 0.006), when compared to mothers who have not ceased. Increases in BL and HC did not reach significance. This study upholds that tobacco consumption is still an important public health threat in Portugal and that smoking cessation during pregnancy reverses smoking-associated deficits in perinatal outcomes, emphasizing the crucial need for awareness campaigns to promote smoking cessation during pregnancy.
- Classification of microcytic anaemias using machine learning methodsPublication . Leitão, Beatriz; Vinga, Susana; Faustino, PaulaThe prevalence of anaemia in the world population is 24.8%. Proper discrimination between microcytic anaemias is essential to provide the right treatment and genetic counselling.A s the most reliable methods to diagnose thalassemias and IDA (iron deficiency anaemia), some of the most common microcytic anaemias are expensive and time-consuming, many indexes have been developed through the years. These indexes, however, have not been revealed to be 100% accurate. In this thesis, haematological data from a sample of the Portuguese population constituted by 390 individuals and their diagnosis was used to train and test different machine learning algorithms. The objective was to develop a binary classifier, specifically adapted to the Portuguese population, to dis criminate β-thalassemia carriers from IDA patients. Beyond that, a multi-class classifier capable of dis tinguishing between β-thalassemia carriers, α-thalassemia carriers, IDA patients, and healthy subjects was also developed. In order not to compromise the main objective, to obtain a quick and accessible diagnosis, the classifiers developed were only based on information obtained through a complete blood count test, one of the most common laboratory tests in medicine. Although it was not possible to surpass the performance with the binary classifiers created of the most reliable index for the Portuguese population, RDWI (red cell distribution width index), which presented a median accuracy of 95.4%, it was possible to match it with the random forest algorithm. This algorithm showed an excellent performance in the binary and in the multi-class classification, where it achieved promising results, revelling a median accuracy of 93.0%.