Design and Implementation of a Machine Learning Based EEG Processor for Accurate Estimation of Depth of Anesthesia
- 10 June 2019
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biomedical Circuits and Systems
- Vol. 13 (4) , 658-669
Abstract
Accurate monitoring of the depth of anesthesia (DoA) is essential for intraoperative and postoperative patient's health. Commercially available electroencephalograph (EEG)-based DoA monitors are recommended only for certain anesthetic drugs and specific age-group patients. This paper presents a machine learning classification processor for accurate DoA estimation irrespective of the patient's age and anesthetic drug. The classification is solely based on six features extracted from EEG signal, i.e. spectral edge frequency (SEF), beta ratio, and four bands of spectral energy (FBSE). A machine learning fine decision tree classifier is adopted to achieve a four-class DoA classification (deep, moderate, and light DoA versus awake state). The feature selection and the classification processor are optimized to achieve the highest classification accuracy for the state of moderate anesthesia required for the surgical operations. The proposed 256-point Fast Fourier Transform (FFT) accelerator is implemented to realize SEF, beta ratio and FBSE that enables minimal latency and high accuracy feature extraction. The proposed DoA processor is implemented using a 65nm CMOS technology and experimentally verified using FPGA based on the EEG recordings of 75 patients undergoing elective surgery with different types of anesthetic agents. The processor achieves an average accuracy of 92.2% for all DoA states, with a latency of 1 sec. The 0.09mm $^2$ DoA processor consumes 140nJ/classification.
Keywords
Funding Information
- Lahore University of Management Sciences (STG-EED-1216)
- Faculty Initiative Fund (FIF-359-1718-EED)
This publication has 27 references indexed in Scilit:
- A Patient-Specific Machine Learning based EEG Processor for Accurate Estimation of Depth of Anesthesia2018
- A multimodal headpatch system for patient brain monitoring in OR and PACU2017
- Monitoring the Depth of Anesthesia Using a New Adaptive Neurofuzzy SystemIEEE Journal of Biomedical and Health Informatics, 2017
- Clinical Electroencephalography for AnesthesiologistsAnesthesiology, 2015
- General Anesthesia, Sleep, and ComaNew England Journal of Medicine, 2010
- Monitoring consciousness: the current status of EEG-based depth of anaesthesia monitorsBest Practice & Research Clinical Anaesthesiology, 2007
- Prevention of awareness during anaesthesiaBest Practice & Research Clinical Anaesthesiology, 2007
- Cerebral State Index during Propofol AnesthesiaAnesthesiology, 2006
- Development and Clinical Application of Electroencephalographic Bispectrum MonitoringAnesthesiology, 2000
- Anesthetic Drug InteractionsAnesthesiology, 1998