Neuro-fuzzy models to predict the required propofol amount for loss of consciousness during general anesthesia: a preliminary study

Ferreira, Ana Isabel Leitão; Mendes, Joaquim; Amorim, Pedro; Nunes, Catarina S.

http://hdl.handle.net/10400.2/10736

Use this identifier to reference this record.

Name:	Description:	Size:	Format:
fuzzy_paper_publicado.pdf		2.67 MB	Adobe PDF	Download

Send Feedback

Authors

Ferreira, Ana Isabel Leitão

Mendes, Joaquim

Amorim, Pedro

Nunes, Catarina S.

Abstract(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.

Keywords

Personalized anesthesia Loss of consciousness Fuzzy logic ANFIS

URI

http://hdl.handle.net/10400.2/10736

Citation

A. L. Ferreira, J. Mendes, P. Amorim and C. S. Nunes, "Neuro-fuzzy models to predict the required propofol amount for loss of consciousness during general anesthesia: a preliminary study," 2018 IEEE International Symposium on Medical Measurements and Applications (MeMeA), Rome, 2018, pp. 1-5. (ISBN: 978-1-5386-3392-2)