Cargando…

Predicting intraoperative hypotension using deep learning with waveforms of arterial blood pressure, electroencephalogram, and electrocardiogram: Retrospective study

To develop deep learning models for predicting Interoperative hypotension (IOH) using waveforms from arterial blood pressure (ABP), electrocardiogram (ECG), and electroencephalogram (EEG), and to determine whether combination ABP with EEG or CG improves model performance. Data were retrieved from Vi...

Descripción completa

Detalles Bibliográficos
Autores principales: Jo, Yong-Yeon, Jang, Jong-Hwan, Kwon, Joon-myoung, Lee, Hyung-Chul, Jung, Chul-Woo, Byun, Seonjeong, Jeong, Han‐Gil
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9362925/
https://www.ncbi.nlm.nih.gov/pubmed/35944013
http://dx.doi.org/10.1371/journal.pone.0272055
_version_ 1784764815831465984
author Jo, Yong-Yeon
Jang, Jong-Hwan
Kwon, Joon-myoung
Lee, Hyung-Chul
Jung, Chul-Woo
Byun, Seonjeong
Jeong, Han‐Gil
author_facet Jo, Yong-Yeon
Jang, Jong-Hwan
Kwon, Joon-myoung
Lee, Hyung-Chul
Jung, Chul-Woo
Byun, Seonjeong
Jeong, Han‐Gil
author_sort Jo, Yong-Yeon
collection PubMed
description To develop deep learning models for predicting Interoperative hypotension (IOH) using waveforms from arterial blood pressure (ABP), electrocardiogram (ECG), and electroencephalogram (EEG), and to determine whether combination ABP with EEG or CG improves model performance. Data were retrieved from VitalDB, a public data repository of vital signs taken during surgeries in 10 operating rooms at Seoul National University Hospital from January 6, 2005, to March 1, 2014. Retrospective data from 14,140 adult patients undergoing non-cardiac surgery with general anaesthesia were used. The predictive performances of models trained with different combinations of waveforms were evaluated and compared at time points at 3, 5, 10, 15 minutes before the event. The performance was calculated by area under the receiver operating characteristic (AUROC), area under the precision-recall curve (AUPRC), sensitivity and specificity. The model performance was better in the model using both ABP and EEG waveforms than in all other models at all time points (3, 5, 10, and 15 minutes before an event) Using high-fidelity ABP and EEG waveforms, the model predicted IOH with a AUROC and AUPRC of 0.935 [0.932 to 0.938] and 0.882 [0.876 to 0.887] at 5 minutes before an IOH event. The output of both ABP and EEG was more calibrated than that using other combinations or ABP alone. The results demonstrate that a predictive deep neural network can be trained using ABP, ECG, and EEG waveforms, and the combination of ABP and EEG improves model performance and calibration.
format Online
Article
Text
id pubmed-9362925
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-93629252022-08-10 Predicting intraoperative hypotension using deep learning with waveforms of arterial blood pressure, electroencephalogram, and electrocardiogram: Retrospective study Jo, Yong-Yeon Jang, Jong-Hwan Kwon, Joon-myoung Lee, Hyung-Chul Jung, Chul-Woo Byun, Seonjeong Jeong, Han‐Gil PLoS One Research Article To develop deep learning models for predicting Interoperative hypotension (IOH) using waveforms from arterial blood pressure (ABP), electrocardiogram (ECG), and electroencephalogram (EEG), and to determine whether combination ABP with EEG or CG improves model performance. Data were retrieved from VitalDB, a public data repository of vital signs taken during surgeries in 10 operating rooms at Seoul National University Hospital from January 6, 2005, to March 1, 2014. Retrospective data from 14,140 adult patients undergoing non-cardiac surgery with general anaesthesia were used. The predictive performances of models trained with different combinations of waveforms were evaluated and compared at time points at 3, 5, 10, 15 minutes before the event. The performance was calculated by area under the receiver operating characteristic (AUROC), area under the precision-recall curve (AUPRC), sensitivity and specificity. The model performance was better in the model using both ABP and EEG waveforms than in all other models at all time points (3, 5, 10, and 15 minutes before an event) Using high-fidelity ABP and EEG waveforms, the model predicted IOH with a AUROC and AUPRC of 0.935 [0.932 to 0.938] and 0.882 [0.876 to 0.887] at 5 minutes before an IOH event. The output of both ABP and EEG was more calibrated than that using other combinations or ABP alone. The results demonstrate that a predictive deep neural network can be trained using ABP, ECG, and EEG waveforms, and the combination of ABP and EEG improves model performance and calibration. Public Library of Science 2022-08-09 /pmc/articles/PMC9362925/ /pubmed/35944013 http://dx.doi.org/10.1371/journal.pone.0272055 Text en © 2022 Jo et al https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
spellingShingle Research Article
Jo, Yong-Yeon
Jang, Jong-Hwan
Kwon, Joon-myoung
Lee, Hyung-Chul
Jung, Chul-Woo
Byun, Seonjeong
Jeong, Han‐Gil
Predicting intraoperative hypotension using deep learning with waveforms of arterial blood pressure, electroencephalogram, and electrocardiogram: Retrospective study
title Predicting intraoperative hypotension using deep learning with waveforms of arterial blood pressure, electroencephalogram, and electrocardiogram: Retrospective study
title_full Predicting intraoperative hypotension using deep learning with waveforms of arterial blood pressure, electroencephalogram, and electrocardiogram: Retrospective study
title_fullStr Predicting intraoperative hypotension using deep learning with waveforms of arterial blood pressure, electroencephalogram, and electrocardiogram: Retrospective study
title_full_unstemmed Predicting intraoperative hypotension using deep learning with waveforms of arterial blood pressure, electroencephalogram, and electrocardiogram: Retrospective study
title_short Predicting intraoperative hypotension using deep learning with waveforms of arterial blood pressure, electroencephalogram, and electrocardiogram: Retrospective study
title_sort predicting intraoperative hypotension using deep learning with waveforms of arterial blood pressure, electroencephalogram, and electrocardiogram: retrospective study
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9362925/
https://www.ncbi.nlm.nih.gov/pubmed/35944013
http://dx.doi.org/10.1371/journal.pone.0272055
work_keys_str_mv AT joyongyeon predictingintraoperativehypotensionusingdeeplearningwithwaveformsofarterialbloodpressureelectroencephalogramandelectrocardiogramretrospectivestudy
AT jangjonghwan predictingintraoperativehypotensionusingdeeplearningwithwaveformsofarterialbloodpressureelectroencephalogramandelectrocardiogramretrospectivestudy
AT kwonjoonmyoung predictingintraoperativehypotensionusingdeeplearningwithwaveformsofarterialbloodpressureelectroencephalogramandelectrocardiogramretrospectivestudy
AT leehyungchul predictingintraoperativehypotensionusingdeeplearningwithwaveformsofarterialbloodpressureelectroencephalogramandelectrocardiogramretrospectivestudy
AT jungchulwoo predictingintraoperativehypotensionusingdeeplearningwithwaveformsofarterialbloodpressureelectroencephalogramandelectrocardiogramretrospectivestudy
AT byunseonjeong predictingintraoperativehypotensionusingdeeplearningwithwaveformsofarterialbloodpressureelectroencephalogramandelectrocardiogramretrospectivestudy
AT jeonghangil predictingintraoperativehypotensionusingdeeplearningwithwaveformsofarterialbloodpressureelectroencephalogramandelectrocardiogramretrospectivestudy