2019, Number 1
<< Back Next >>
Revista Cubana de Informática Médica 2019; 11 (1)
Automatic monitoring of sedation states in electroencephalographic signals
González RT, Rodríguez AY, Drullet FJL, Marañon REJ, Montoya PA
Language: Spanish
References: 20
Page: 18-32
PDF size: 621.69 Kb.
ABSTRACT
General anesthesia provide the patient states of unconsciousness, amnesia and analgesia, however, cases of intraoperative awareness are reported. Due to the incidence of this phenomenon and the psychosomatic effects it causes, the Neuroscience Studies Center, Images and Signals Processing at the University of Oriente, and the General Hospital "Juan Bruno Zayas Alfonso" both in Santiago de Cuba, Cuba, implement a methodology that allows the automatic detection of anesthetic sedation states applying Artificial Intelligence. For this, the signals recorded by the electroencephalographic channel F4, nine spectral parameters, the Support Vector Machines and the Neuro-Fuzzy Systems were used. In the automatic recognition of the Sedation States: Profound, Moderate and Mild an Accuracy of 96.12%, 90.06% and 90.24% respectively was achieved with the Support Vector Machines, so the use of the electroencephalographic channel F4 is proposed in the detection of anesthetic states.
REFERENCES
Niedermeyer E, Lopes da Silva F. Electroencephalography, Basic Principles, Clinical Applications, and Related Fields. Lippincott: Williams & Wilkins. 6 ed. 2011.
Williams A, Ruddock Y. BET 1: The use of bispectral index monitoring (BIS) in conscious sedation. Emergency Medicine Journal. 2015; 32(5):662.
John ER, Prichep LS, Kox W, Valdés Sosa P, Bosch-Bayard J, Aubert E, et Al. Invariant Reversible QEEG Effects of Anesthetics. Consciousness and Cognition. 2001; 10(2):165-83.
Kazuko H, Nobuhiro M, Teiji S. Simultaneous Bicoherence Analysis of Cccipital and Frontal Electroencephalograms in Awake and Anesthetized Subjects. Clinical Neurophysiology. 2014; 125(1):194-201.
Hashemi M, Hutt A, Sleigh J. How the Cortico-thalamic Feedback Affects the EEG Power Spectrum Over Frontal and Occipital Regions During Propofol-induced Sedation. Journal of Computational Neuroscience. 2015; 39(2):155-179.
Mohammed EAL, Nesma S, Mostafa EHD. An SVM Intelligent System for Pre-anesthetic Examination. Complex Systems (WCCS). Second World Conference on IEEE. 2014; 73-78.
Nagaraj SB, McClain LM, Zhou DW, Biswal S, Rosenthal ES, Purdon PL et Al. Automatic Classification of Sedation Levels in ICU Patients Using Heart Rate Variability. Crit Care Med. 2016; 44(9): e782–9.
Hernandez-Meza G, Izzetoglu M, Osbakken M, Green M. Investigation of Optical Neuro-monitoring Technique for Detection of Maintenance and Emergence States During General Anesthesia. Journal of Clinical Monitoring and Computing. 2017.
Chang JJ, Syafiie S, Ahmad RKR, Lim TA. ANFIS Based Model for Bispectral Index Prediction. En: Herawan T, Ghazali R, Deris M, eds. Recent Advances on Soft Computing and Data Mining. Advances in Intelligent Systems and Computing. Springer, 2014:287.
Mansour E, Ali RAM, et Al. Analyzing the EEG Signals in Order to Estimate the Depth of Anesthesia Using Wavelet and Fuzzy Neural Networks. International Journal of Interactive Multimedia and Artificial Intelligence. 2016; 4(2).
Shalbaf A, Saffar M, Sleigh J, Shalbaf R. Monitoring the Depth of Anesthesia Using a New Adaptive Neuro-fuzzy System. IEEE Journal of Biomedical and Health Informatics. 2017; PP(99).
Kaier W, Steyn-Ross ML, Steyn-Ross DA, Wilson MT, Sleigh JW. EEG Slow-wave Coherence Changes in Propofol Induced General Anesthesia: Experiment and Theory. Frontiers in Systems Neuroscience. 2014; 8:1-16.
Montoya Pedrón A, Marañón Reyes EA, Rodríguez Aldana Y, Álvarez RuffoI CM, Salgado Castillo A. Evaluación de la eficacia de los parámetros del Electroencefalograma Cuantitativo en la medición del nivel de profundidad anestésico. Revista MEDISAN. 2014; 18(3). ISSN 1029-3019.
Tan ZB, Wang LY, Mckelvey G, et Al. Evaluation of EEG [beta]^sub 2^/[theta]-ratio and channel locations in measuring anesthesia depth. Journal of Biomedical Science and Engineering. 2010; 3(1):39-46.
Rodríguez Aldana Y, González Rubio T, Marañón Reyes E, Montoya Pedrón A, Sanabria Macías F. Aplicación de la corrección de artefactos en el electroencefalograma para monitoreo anestésico. Revista Cubana de Neurología y Neurocirugía. 2015; 5 Suppl 1:S9–14.
Webb AR, Copsey KD. Statistical Pattern Recognition. 3 ed. John Wiley&Sons, Ltd. 2011.
Chao C, John R, Jamie T, Jonathan G. An Extended ANFIS Architecture and Its Learning Properties for Type-1 and Interval type-2 Models. School of Computer Science University of Nottingham, Vancouver. 2016.
Schneider G, Gelb AW, Schmeller B, Tschakert R, Kochs E. Detection of Awareness in Surgical Patients With EEG-based Indices Bispectral Index and Patient State Index. British Journal of Anaesthesia. 2003; 91(3):329-35.
Espí C, Vila P, Muñoz S, Monerris M, Mazo V, Canet J. Estudio comparativo del índice biespectral y la entropía espectral en cirugía ginecológica. Revista Española de Anestesiología y Reanimación. 2005; 52(8):459-65.
Loria AB. Awareness o despertar intraoperatorio generalidades acerca de este fenómeno. Revista Médica de Costa Rica y Centroamérica. 2012; 69(600):15-9.