A Patient-Specific Machine Learning based EEG Processor for Accurate Estimation of Depth of Anesthesia

Fatima Khan Hameed; Usman Ashraf; Muhammad Awais Bin Altaf; Wala Saadeh

doi:10.1109/BIOCAS.2018.8584828

A Patient-Specific Machine Learning based EEG Processor for Accurate Estimation of Depth of Anesthesia

Fatima Khan Hameed, Usman Ashraf, Muhammad Awais Bin Altaf, Wala Saadeh

Institute of Software Systems Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference proceedings › peer-review

Abstract

An electroencephalograph (EEG) based classification processor for the depth of Anesthesia (DoA) during the intraoperative procedure is presented. To enable a DoA to monitor the correct estimation across a range of patients, a novel feature extraction along with machine learning processor is utilized. The decisions are solely based on seven features extracted from EEG along with the EMG signal for motion artifacts rejection. To extract the features efficiently on hardware, a 128-point FFT is proposed that achieves an area reduction and energy/FFT-operation by 39% and 58%, respectively, compared to the conventional. A simple decision tree is used to perform a multiclass DoA classification. The system is synthesized using a 65nm process and experimental verification is done using FPGA based on the subset of patients from the University of Queensland Vital Signs. The proposed patient-specific DoA classification processor achieves a classification accuracy of 79%.

Original language	English
Title of host publication	IEEE Biomedical Circuits and Systems Conference, BioCAS 2018
Publisher	IEEE
Pages	1-4
Number of pages	4
DOIs	https://doi.org/10.1109/BIOCAS.2018.8584828
Publication status	Published - Dec 2018

Fields of science

102 Computer Sciences
102022 Software development

JKU Focus areas

Computation in Informatics and Mathematics
Engineering and Natural Sciences (in general)

Access to Document

10.1109/BIOCAS.2018.8584828

Cite this

@inproceedings{3bef36c4cc344b4fadc5b18908a97aed,

title = "A Patient-Specific Machine Learning based EEG Processor for Accurate Estimation of Depth of Anesthesia",

abstract = "An electroencephalograph (EEG) based classification processor for the depth of Anesthesia (DoA) during the intraoperative procedure is presented. To enable a DoA to monitor the correct estimation across a range of patients, a novel feature extraction along with machine learning processor is utilized. The decisions are solely based on seven features extracted from EEG along with the EMG signal for motion artifacts rejection. To extract the features efficiently on hardware, a 128-point FFT is proposed that achieves an area reduction and energy/FFT-operation by 39\% and 58\%, respectively, compared to the conventional. A simple decision tree is used to perform a multiclass DoA classification. The system is synthesized using a 65nm process and experimental verification is done using FPGA based on the subset of patients from the University of Queensland Vital Signs. The proposed patient-specific DoA classification processor achieves a classification accuracy of 79\%.",

author = "\{Khan Hameed\}, Fatima and Usman Ashraf and \{Bin Altaf\}, \{Muhammad Awais\} and Wala Saadeh",

year = "2018",

month = dec,

doi = "10.1109/BIOCAS.2018.8584828",

language = "English",

pages = "1--4",

booktitle = "IEEE Biomedical Circuits and Systems Conference, BioCAS 2018",

publisher = "IEEE",

}

TY - GEN

T1 - A Patient-Specific Machine Learning based EEG Processor for Accurate Estimation of Depth of Anesthesia

AU - Khan Hameed, Fatima

AU - Ashraf, Usman

AU - Bin Altaf, Muhammad Awais

AU - Saadeh, Wala

PY - 2018/12

Y1 - 2018/12

N2 - An electroencephalograph (EEG) based classification processor for the depth of Anesthesia (DoA) during the intraoperative procedure is presented. To enable a DoA to monitor the correct estimation across a range of patients, a novel feature extraction along with machine learning processor is utilized. The decisions are solely based on seven features extracted from EEG along with the EMG signal for motion artifacts rejection. To extract the features efficiently on hardware, a 128-point FFT is proposed that achieves an area reduction and energy/FFT-operation by 39% and 58%, respectively, compared to the conventional. A simple decision tree is used to perform a multiclass DoA classification. The system is synthesized using a 65nm process and experimental verification is done using FPGA based on the subset of patients from the University of Queensland Vital Signs. The proposed patient-specific DoA classification processor achieves a classification accuracy of 79%.

AB - An electroencephalograph (EEG) based classification processor for the depth of Anesthesia (DoA) during the intraoperative procedure is presented. To enable a DoA to monitor the correct estimation across a range of patients, a novel feature extraction along with machine learning processor is utilized. The decisions are solely based on seven features extracted from EEG along with the EMG signal for motion artifacts rejection. To extract the features efficiently on hardware, a 128-point FFT is proposed that achieves an area reduction and energy/FFT-operation by 39% and 58%, respectively, compared to the conventional. A simple decision tree is used to perform a multiclass DoA classification. The system is synthesized using a 65nm process and experimental verification is done using FPGA based on the subset of patients from the University of Queensland Vital Signs. The proposed patient-specific DoA classification processor achieves a classification accuracy of 79%.

U2 - 10.1109/BIOCAS.2018.8584828

DO - 10.1109/BIOCAS.2018.8584828

M3 - Conference proceedings

SP - 1

EP - 4

BT - IEEE Biomedical Circuits and Systems Conference, BioCAS 2018

PB - IEEE

ER -