TY - GEN
T1 - Predicting postoperative delirium in patients undergoing deep hypothermia circulatory arrest
AU - Ma, Owen
AU - Dutta, Arindam
AU - Bliss, Daniel
AU - Crepeau, Amy Z.
N1 - Funding Information:
This work was sponsored by the ASU Mayo Seed Grant Program. The authors would like to thank Alex Chiriyath, Christian Chapman, Andrew Herschfelt, Bryan Paul, and Sha-ranya Srinivas of BLISS Lab for their help in revising this article. They would also like to thank Gene Brewer and Visar Berisha of Arizona State University for their feedback on this study’s methodology. Additionally, they would like to thank Yonas E. Geda, Gregory A. Worrell, and William J. Mauermann of Mayo Clinic for their initial analysis on this data. Lastly, they would like to thank Daniel Crepeau of Mayo Clinic for his technical assistance with transferring and accessing the data.
Publisher Copyright:
© 2017 IEEE.
Copyright:
Copyright 2018 Elsevier B.V., All rights reserved.
PY - 2018/4/10
Y1 - 2018/4/10
N2 - Cardiac surgeries involving deep hypothermia circulatory arrest present a risk of cognitive impairment. This study attempts to uncover intraoperative electroencephalogram (EEG) biomarkers predictive of postoperative delirium, which is associated with long term health complications. We predict postoperative delirium diagnoses by examining changes in ensemble neural activity during surgeries through spatiotemporal eigenspectra extracted from patient EEG data. Artifact detection and feature normalization schemes are developed to facilitate this. At most 14 of 16 cases were correctly predicted with a p-value of 0.0015. An area under the receiver operating characteristics (ROC) curve of 0.8364 was achieved-0.9091 when considering the convex hull.
AB - Cardiac surgeries involving deep hypothermia circulatory arrest present a risk of cognitive impairment. This study attempts to uncover intraoperative electroencephalogram (EEG) biomarkers predictive of postoperative delirium, which is associated with long term health complications. We predict postoperative delirium diagnoses by examining changes in ensemble neural activity during surgeries through spatiotemporal eigenspectra extracted from patient EEG data. Artifact detection and feature normalization schemes are developed to facilitate this. At most 14 of 16 cases were correctly predicted with a p-value of 0.0015. An area under the receiver operating characteristics (ROC) curve of 0.8364 was achieved-0.9091 when considering the convex hull.
KW - Deep Hypothermia Circulatory Arrest
KW - Electroencephalography
KW - Intra-operative Monitoring
KW - Neurophysiology
KW - Signal Processing
UR - http://www.scopus.com/inward/record.url?scp=85050966239&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85050966239&partnerID=8YFLogxK
U2 - 10.1109/ACSSC.2017.8335566
DO - 10.1109/ACSSC.2017.8335566
M3 - Conference contribution
AN - SCOPUS:85050966239
T3 - Conference Record of 51st Asilomar Conference on Signals, Systems and Computers, ACSSC 2017
SP - 1313
EP - 1317
BT - Conference Record of 51st Asilomar Conference on Signals, Systems and Computers, ACSSC 2017
A2 - Matthews, Michael B.
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 51st Asilomar Conference on Signals, Systems and Computers, ACSSC 2017
Y2 - 29 October 2017 through 1 November 2017
ER -