Literature DB >> 33558051

Deep learning models for the prediction of intraoperative hypotension.

Solam Lee1, Hyung-Chul Lee2, Yu Seong Chu3, Seung Woo Song4, Gyo Jin Ahn5, Hunju Lee6, Sejung Yang7, Sang Baek Koh8.   

Abstract

BACKGROUND: Intraoperative hypotension is associated with a risk of postoperative organ dysfunction. In this study, we aimed to present deep learning algorithms for real-time predictions 5, 10, and 15 min before a hypotensive event.
METHODS: In this retrospective observational study, deep learning algorithms were developed and validated using biosignal waveforms acquired from patient monitoring of noncardiac surgery. The classification model was a binary classifier of a hypotensive event (MAP <65 mm Hg) or a non-hypotensive event by analysing biosignal waveforms. The regression model was developed to directly estimate the MAP. The primary outcome was area under the receiver operating characteristic (AUROC) curve and the mean absolute error (MAE).
RESULTS: In total, 3301 patients were included. For invasive models, the multichannel model with an arterial pressure waveform, electrocardiography, photoplethysmography, and capnography showed greater AUROC than the arterial-pressure-only models (AUROC15-min, 0.897 [95% confidence interval {CI}: 0.894-0.900] vs 0.891 [95% CI: 0.888-0.894]) and lesser MAE (MAE15-min, 7.76 mm Hg [95% CI: 7.64-7.87 mm Hg] vs 8.12 mm Hg [95% CI: 8.02-8.21 mm Hg]). For the noninvasive models, the multichannel model showed greater AUROCs than that of the photoplethysmography-only models (AUROC15-min, 0.762 [95% CI: 0.756-0.767] vs 0.694 [95% CI: 0.686-0.702]) and lesser MAEs (MAE15-min, 11.68 mm Hg [95% CI: 11.57-11.80 mm Hg] vs 12.67 [95% CI: 12.56-12.79 mm Hg]).
CONCLUSIONS: Deep learning models can predict hypotensive events based on biosignals acquired using invasive and noninvasive patient monitoring. In addition, the model shows better performance when using combined rather than single signals.
Copyright © 2021 British Journal of Anaesthesia. Published by Elsevier Ltd. All rights reserved.

Entities:  

Keywords:  artificial intelligence; biosignals; deep learning; digital medicine; hypotension; intraoperative hypotension; perioperative medicine

Mesh:

Year:  2021        PMID: 33558051     DOI: 10.1016/j.bja.2020.12.035

Source DB:  PubMed          Journal:  Br J Anaesth        ISSN: 0007-0912            Impact factor:   9.166


  6 in total

1.  Intraoperative prediction of postanaesthesia care unit hypotension.

Authors:  Konstantina Palla; Stephanie L Hyland; Karen Posner; Pratik Ghosh; Bala Nair; Melissa Bristow; Yoana Paleva; Ben Williams; Christine Fong; Wil Van Cleve; Dustin R Long; Ronald Pauldine; Kenton O'Hara; Kenji Takeda; Monica S Vavilala
Journal:  Br J Anaesth       Date:  2021-12-17       Impact factor: 11.719

2.  VitalDB, a high-fidelity multi-parameter vital signs database in surgical patients.

Authors:  Hyung-Chul Lee; Yoonsang Park; Soo Bin Yoon; Seong Mi Yang; Dongnyeok Park; Chul-Woo Jung
Journal:  Sci Data       Date:  2022-06-08       Impact factor: 8.501

3.  Intraoperative Hypotension Prediction Model Based on Systematic Feature Engineering and Machine Learning.

Authors:  Subin Lee; Misoon Lee; Sang-Hyun Kim; Jiyoung Woo
Journal:  Sensors (Basel)       Date:  2022-04-19       Impact factor: 3.847

Review 4.  Artificial intelligence in perioperative medicine: a narrative review.

Authors:  Hyun-Kyu Yoon; Hyun-Lim Yang; Chul-Woo Jung; Hyung-Chul Lee
Journal:  Korean J Anesthesiol       Date:  2022-03-29

5.  Machine learning for predicting acute hypotension: A systematic review.

Authors:  Anxing Zhao; Mohamed Elgendi; Carlo Menon
Journal:  Front Cardiovasc Med       Date:  2022-08-23

6.  Artificial Intelligence for Detection of Cardiovascular-Related Diseases from Wearable Devices: A Systematic Review and Meta-Analysis.

Authors:  Solam Lee; Yuseong Chu; Jiseung Ryu; Young Jun Park; Sejung Yang; Sang Baek Koh
Journal:  Yonsei Med J       Date:  2022-01       Impact factor: 2.759

  6 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.