Accurate Machine Learning-based Monitoring of Anesthesia Depth with EEG Recording

IF 5.9 2区 医学 Q1 NEUROSCIENCES Neuroscience bulletin Pub Date : 2024-09-17 DOI:10.1007/s12264-024-01297-w
Zhiyi Tu, Yuehan Zhang, Xueyang Lv, Yanyan Wang, Tingting Zhang, Juan Wang, Xinren Yu, Pei Chen, Suocheng Pang, Shengtian Li, Xiongjie Yu, Xuan Zhao
{"title":"Accurate Machine Learning-based Monitoring of Anesthesia Depth with EEG Recording","authors":"Zhiyi Tu, Yuehan Zhang, Xueyang Lv, Yanyan Wang, Tingting Zhang, Juan Wang, Xinren Yu, Pei Chen, Suocheng Pang, Shengtian Li, Xiongjie Yu, Xuan Zhao","doi":"10.1007/s12264-024-01297-w","DOIUrl":null,"url":null,"abstract":"<p>General anesthesia, pivotal for surgical procedures, requires precise depth monitoring to mitigate risks ranging from intraoperative awareness to postoperative cognitive impairments. Traditional assessment methods, relying on physiological indicators or behavioral responses, fall short of accurately capturing the nuanced states of unconsciousness. This study introduces a machine learning-based approach to decode anesthesia depth, leveraging EEG data across different anesthesia states induced by propofol and esketamine in rats. Our findings demonstrate the model’s robust predictive accuracy, underscored by a novel intra-subject dataset partitioning and a 5-fold cross-validation method. The research diverges from conventional monitoring by utilizing anesthetic infusion rates as objective indicators of anesthesia states, highlighting distinct EEG patterns and enhancing prediction accuracy. Moreover, the model’s ability to generalize across individuals suggests its potential for broad clinical application, distinguishing between anesthetic agents and their depths. Despite relying on rat EEG data, which poses questions about real-world applicability, our approach marks a significant advance in anesthesia monitoring.</p>","PeriodicalId":19314,"journal":{"name":"Neuroscience bulletin","volume":"57 1","pages":""},"PeriodicalIF":5.9000,"publicationDate":"2024-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Neuroscience bulletin","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1007/s12264-024-01297-w","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"NEUROSCIENCES","Score":null,"Total":0}
引用次数: 0

Abstract

General anesthesia, pivotal for surgical procedures, requires precise depth monitoring to mitigate risks ranging from intraoperative awareness to postoperative cognitive impairments. Traditional assessment methods, relying on physiological indicators or behavioral responses, fall short of accurately capturing the nuanced states of unconsciousness. This study introduces a machine learning-based approach to decode anesthesia depth, leveraging EEG data across different anesthesia states induced by propofol and esketamine in rats. Our findings demonstrate the model’s robust predictive accuracy, underscored by a novel intra-subject dataset partitioning and a 5-fold cross-validation method. The research diverges from conventional monitoring by utilizing anesthetic infusion rates as objective indicators of anesthesia states, highlighting distinct EEG patterns and enhancing prediction accuracy. Moreover, the model’s ability to generalize across individuals suggests its potential for broad clinical application, distinguishing between anesthetic agents and their depths. Despite relying on rat EEG data, which poses questions about real-world applicability, our approach marks a significant advance in anesthesia monitoring.

Abstract Image

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
利用脑电图记录对麻醉深度进行基于机器学习的精确监测
全身麻醉是外科手术的关键,需要进行精确的深度监测,以降低从术中意识到术后认知障碍等各种风险。传统的评估方法依赖于生理指标或行为反应,无法准确捕捉细微的无意识状态。本研究介绍了一种基于机器学习的方法,利用异丙酚和埃斯卡胺诱导大鼠不同麻醉状态下的脑电图数据来解码麻醉深度。我们的研究结果表明,该模型具有很高的预测准确性,新颖的受试者内部数据集划分和 5 倍交叉验证方法也证明了这一点。这项研究有别于传统的监测方法,它利用麻醉剂输注率作为麻醉状态的客观指标,突出了独特的脑电图模式,提高了预测准确性。此外,该模型还具有跨个体的泛化能力,这表明它具有广泛的临床应用潜力,可以区分麻醉剂及其深度。尽管我们的方法依赖于大鼠的脑电图数据,这对现实世界的适用性提出了质疑,但它标志着麻醉监测领域的一大进步。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
Neuroscience bulletin
Neuroscience bulletin NEUROSCIENCES-
CiteScore
7.20
自引率
16.10%
发文量
163
审稿时长
6-12 weeks
期刊介绍: Neuroscience Bulletin (NB), the official journal of the Chinese Neuroscience Society, is published monthly by Shanghai Institutes for Biological Sciences (SIBS), Chinese Academy of Sciences (CAS) and Springer. NB aims to publish research advances in the field of neuroscience and promote exchange of scientific ideas within the community. The journal publishes original papers on various topics in neuroscience and focuses on potential disease implications on the nervous system. NB welcomes research contributions on molecular, cellular, or developmental neuroscience using multidisciplinary approaches and functional strategies. We feature full-length original articles, reviews, methods, letters to the editor, insights, and research highlights. As the official journal of the Chinese Neuroscience Society, which currently has more than 12,000 members in China, NB is devoted to facilitating communications between Chinese neuroscientists and their international colleagues. The journal is recognized as the most influential publication in neuroscience research in China.
期刊最新文献
Neuronal Regulation of Feeding and Energy Metabolism: A Focus on the Hypothalamus and Brainstem. Deciphering the Role of Shank3 in Dendritic Morphology and Synaptic Function Across Postnatal Developmental Stages in the Shank3B KO Mouse. Conditional Tnfaip6-Knockout in Inner Ear Hair Cells Does not Alter Auditory Function. Inhibition of the cGAS‑STING Pathway Reduces Cisplatin-Induced Inner Ear Hair Cell Damage. A New Pathway Mediating Pain Sensitization after Active Sleep Deprivation.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1