Papers by eleonora oliveira
Archives of Neurology, 1996
Introduction: The societal and economic impact of ischemic stroke in young adults is considerable... more Introduction: The societal and economic impact of ischemic stroke in young adults is considerable. The etiological investigation of ischemic stroke in this population is also challenging. Objective: To describe the characteristics of young patients with ischemic stroke admitted to a neurological rehabilitation program in Brazil. Methods: This transversal retrospective study analyzed data from the electronic health records of 134 patients aged 18 to 45 years with ischemic stroke admitted from 2008 to 2012. Results: The average patient age at the time of ictus was 33 years; 56% of the subjects were female, and 29.3% had undetermined etiologies of stroke, on the basis of both TOAST and SSS TOAST criteria. Further, 48.7% of the subjects had a known vascular risk factor, which was arterial hypertension in most cases. The results of thrombophilia testing were positive in 13.7% of patients, but in only 3.7% of patients, thrombophilia was determined to be the causal mechanism of the stroke. There was a significant association between thrombophilia and patent foramen ovale, but no significant association was found between thrombophilia and arterial dissection. Among the patients with artery dissections, 46% had a history of trauma, which was statistically significant. Conclusions: Etiological diagnosis of stroke in the young is challenging for clinicians. Hence, a more effective classification scheme, better investigative mechanisms, and correct determination of causal associations in ischemic stroke are needed. Thrombophilia screening should be performed in the presence of relevant clinical signs and/or family history.
IEEE International Conference on Neural Networks - Conference Proceedings, 2004
This work describes the use of direct supervised multi layer perceptron network (MLP) with one hi... more This work describes the use of direct supervised multi layer perceptron network (MLP) with one hidden layer. Its weights are adjusted by the backpropagation algorithm. In an artificial neural network (ANN), the knowledge of the domain specialists is represented by the topology of the ANN and by the values of the weights used. Thus, it is considerably difficult to explain
Nowadays there are several data mining algorithms applied to the resolution of many different pro... more Nowadays there are several data mining algorithms applied to the resolution of many different problems, such as the classification of patterns. However, when these algorithms are used separately to classify they usually present an inferior performance compared to the performance obtained by combined models. The bagging and boosting techniques combine models of the same kind in a competitive form, in
Uploads
Papers by eleonora oliveira