No abstract

a b s t r a c tThe aim of this work is to present the practical applications of an integrated use of soft and hard methodologies applied in a case study of the Surgical Centre of the University Hospital Clementino Fraga Filho, where the low volume of surgeries is of major concern. The proposed approach is particularly appropriate in situations where there is limited time, financial resources, and institutional cooperation. Cognitive maps were used to elicit the perspectives of health professionals, which supported simulation experiments and guided the model's execution. Human-resource, patient-related, room-schedule, material, and structural constraints were found to affect the number of surgeries performed. The major contribution of this paper is the proposal of a multi-methodological approach with a committed focus on problem solving that incorporates specialists' views in simulation experiments; these specialists' collaborative work highlights actions that can lead to the resolution (or improvement) of real-world problems.

No abstract

ABSTRACT. Despite medical advances, mortality due to acute coronary syndrome remains high. For this reason, it is important to identify the most critical factors for predicting the risk of death in patients hospitalized with this disease. To improve medical decisions, it is also helpful to construct models that enable us to represent how the main driving factors relate to patient outcomes. In this study, we compare the capability of Artificial Neural Network (ANN) and Support Vector Machine (SVM) models to distinguish between patients hospitalized with acute coronary syndrome who have low or high risk of death. Input variables are selected using the wrapper approach associated with a mutual information filter and two new proposed filters based on Euclidean distance. Because of missing data, the use of a filter is an important step in increasing the size of the usable data set and maximizing the performance of the classification models. The computational results indicate that the SVM model performs better. The most relevant input variables are age, any previous revascularization, and creatinine, regardless of the classification algorithms and filters used. However, the Euclidean filters also identify a second important group of input variables: age, creatinine and systemic arterial hypertension.

No abstract