Repository logo

Matemática e Estatística | Comunicações em congressos, conferências e seminários / Communications in congresses, conferences

Permanent URI for this collection

http://hdl.handle.net/10400.2/1638

Browse

Browsing Matemática e Estatística | Comunicações em congressos, conferências e seminários / Communications in congresses, conferences by Subject "ANFIS"

Now showing 1 - 2 of 2
  • Neuro-fuzzy models to predict the required propofol amount for loss of consciousness during general anesthesia: a preliminary study
    Publication . Ferreira, Ana Isabel Leitão; Mendes, Joaquim; Amorim, Pedro; Nunes, Catarina S.
    This study presents several models to predict the total amount of the anesthetic drug propofol required to achieve loss of consciousness during the induction phase of anesthesia, considering different clinical variables. The data from 49 patients under anesthesia for neurosurgical procedures, were used in this study. Takagi-Sugeno-Kang (TSK) fuzzy models were used to describe the effect of clinical variables on the amount of propofol required for loss of consciousness. The parameters of the TSK models were optimized using an Adaptive Network-Fuzzy Interference System. All models were trained with the data of 35 patients and tested with the data of 14 patients. These models proved to have reasonable prediction properties. The fuzzy model with the best balanced performance used only two inputs: the systolic arterial pressure and the Bispectral Index of the EEG.
    2018Conference object Restricted access Show more
  • Radial basis function neural networks versus fuzzy models to predict return of consciousness after general anesthesia
    Publication . Nunes, Catarina S.; Mendonca, T. F.; Amorim, Pedro; Ferreira, D. A.; Antunes, L. M.
    This paper presents two modelling techniques to predict return of consciousness (ROC) after general anaesthesia, considering the effect concentration of the anaesthetic drug at awakening. First, several clinical variables were statistically analysed to determine their correlation with the awakening concentration. The anaesthetic 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. Radial basis function (RBF) neural networks were trained relating different sets of clinical values with the anaesthetic drug effect concentration at awakening. Secondly, fuzzy models were built using an Adaptive Network-Based Fuzzy Inference System (ANFIS) also relating different sets of variables. Clinical data was used to train and test the models. The fuzzy models and RBF neural networks proved to have good prediction properties and balanced results.
    2004Conference object Restricted access Show more