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

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%.

[1]  Matthias Görges,et al.  University of Queensland Vital Signs Dataset: Development of an Accessible Repository of Anesthesia Patient Monitoring Data for Research , 2012, Anesthesia and analgesia.

[2]  Jerald Yoo,et al.  A 1.1mW hybrid OFDM ground effect-resilient body coupled communication transceiver for head and body area network , 2016, 2016 IEEE Asian Solid-State Circuits Conference (A-SSCC).

[3]  Samo Ribaric,et al.  Monitoring the Depth of Anaesthesia , 2010, Sensors.

[4]  R. Sandin.  Outcome after awareness with explicit recall. , 2006, Acta anaesthesiologica Belgica.

[5]  P. Myles,et al.  Prevention of awareness during anaesthesia. , 2007, Best practice & research. Clinical anaesthesiology.

[6]  Emery N Brown,et al.  Age-dependent electroencephalogram (EEG) patterns during sevoflurane general anesthesia in infants , 2015, eLife.

[7]  Muhammad Bin Altaf,et al.  A high accuracy and low latency patient-specific wearable fall detection system , 2017, 2017 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI).

[8]  Satoshi Hagihira,et al.  The Relationship Between Bispectral Index and Electroencephalographic Parameters During Isoflurane Anesthesia , 2004, Anesthesia and analgesia.

[9]  E. Brown,et al.  Effects of Sevoflurane and Propofol on Frontal Electroencephalogram Power and Coherence , 2014, Anesthesiology.

[10]  Jerald Yoo,et al.  A Pseudo OFDM With Miniaturized FSK Demodulation Body-Coupled Communication Transceiver for Binaural Hearing Aids in 65 nm CMOS , 2017, IEEE Journal of Solid-State Circuits.

[11]  Medical Advisory Secretariat.  Bispectral index monitor: an evidence-based analysis. , 2004, Ontario health technology assessment series.

[12]  Hoi-Jun Yoo,et al.  An EEG-NIRS Multimodal SoC for Accurate Anesthesia Depth Monitoring , 2018, IEEE Journal of Solid-State Circuits.

[13]  Muhammad Bin Altaf,et al.  A 0.21 μJ patient-specific REM/Non-REM sleep classifier for Alzheimer patients , 2017, 2017 IEEE Biomedical Circuits and Systems Conference (BioCAS).

[14]  Michael J. Prerau,et al.  Characterizing EEG Brain States During General Anesthesia in Children: Insights for Improved Brain Monitoring , 2016 .

[15]  E. Brown,et al.  Clinical Electroencephalography for Anesthesiologists: Part I Background and Basic Signatures , 2015, Anesthesiology.

[16]  E. Brown,et al.  General anesthesia, sleep, and coma. , 2010, The New England journal of medicine.