Matemática e Estatística | Comunicações em congressos, conferências e seminários / Communications in congresses, conferences
Permanent URI for this collection
Browse
Browsing Matemática e Estatística | Comunicações em congressos, conferências e seminários / Communications in congresses, conferences by Author "Antunes, L."
Now showing 1 - 3 of 3
Results Per Page
Sort Options
- Comparison of neural networks, fuzzy and stochastic prediction models for return of consciousness after general anesthesiaPublication . Nunes, Catarina S.; Mendonca, T. F.; Amorim, Pedro; Ferreira, D. A.; Antunes, L.This paper presents three modeling techniques to predict return of consciousness (ROC) after general anesthesia, considering the effect concentration of the anesthetic drug at awakening. First, several clinical variables were statistically analysed to determine their correlation with the awakening concentration. The anesthetic and the analgesic mean dose during surgery, and the age of the patient, proved to have significantly high correlation coefficients. Variables like the mean bispectral index value during surgery, duration of surgery did not present a statistical relation with ROC. Stochastic regression models were built using the variables with higher correlation. Secondly, fuzzy models were built using an Adaptive Network-Based Fuzzy Inference System (ANFIS) also relating different sets of variables. Thirdly, radial basis function (RBF) neural networks were trained relating different sets of clinical values with the anesthetic drug effect concentration at awakening. Clinical data was used to train and test the models. The stochastic models and the fuzzy models proved to have good prediction properties. The RBF network models were more biased towards the training set. The best balanced performance was achieved with the fuzzy models.
- EMG contributes to improve cerebral state Index modeling in dogs anesthesiaPublication . Brás, S.; Ferreira, D. A.; Antunes, L.; Ribeiro, L.; Nunes, Catarina S.; Gouveia, S.Cerebral State Index (CSI) is a measure of depth of anesthesia (DoA) developed for humans, which is traditionally modeled with the Hill equation and the propofol effect-site concentration (Ce). The CSI has been studied in dogs and showed several limitations related to the interpretation of EEG data. Nevertheless, the CSI has a lot of potential for DoA monitoring in dogs, it just needs to be adjusted for this species. In this work, an adapted CSI model is presented for dogs considering a) both Ce and EMG as inputs and b) a fuzzy logic structure with parameters optimized using the ANFIS method. The new model is compared with traditional Hill model using data from dogs in routine surgery. The results showed no significant impact in the model performance with the change of model structure (Fuzzy instead of Hill). The residuals of the Hill model were significantly correlated with the EMG, indicating that the latter should be considered in the model. In fact, the EMG introduction in CSI model significantly decreased the modeling error: 11.8 [8.6; 15.2] (fuzzy logic) versus 20.9 [16.4; 29.0] (Hill). This work shows that CSI modeling in dogs can be improved using the current human anesthesia set-up, once the EMG signal is acquired simultaneously with the CSI index. However, it does not invalidate the search of new DoA indices more adjusted to use in dog’s anesthesia.
- Modelling the dynamics of depth of anaesthesia: cerebral state index in dogsPublication . Bressan, Nadja; Castro, A.; Bras, S.; Ribeiro, L.; Ferreira, D. A.; Silva, A.; Antunes, L.; Nunes, Catarina S.The goal of this study was to obtain models that described the relation between the anaesthetic drug infusions (propofol) and an electroencephalogram (EEG) derived index (Cerebral State Index - CSI) during general anaesthesia in dogs. The first phase integrated the adaptation of hardware for EEG acquisition and exploration for the best electrodes position in dogs skull. The clinical protocol implementation and data collection were the next steps followed by CSI modeling. CSI showed adequate response to changes in drug infusion, reflecting the changes of depth of anaesthesia in dogs. The models obtained adjusted well to the original CSI data and also predicted the CSI trend during surgery. Using this monitor in current practice might improve quality in the anaesthesia procedure providing a useful tool to administer a correct sedation.