Mortality Risk Assessment Using Deep Learning-Based Frequency Analysis of EEG and EOG in Sleep.

IF 5.6 2区 医学 Q1 Medicine Sleep Pub Date : 2024-09-20 DOI:10.1093/sleep/zsae219
Teitur Óli Kristjánsson, Katie L Stone, Helge B D Sorensen, Andreas Brink-Kjaer, Emmanuel Mignot, Poul Jennum
{"title":"Mortality Risk Assessment Using Deep Learning-Based Frequency Analysis of EEG and EOG in Sleep.","authors":"Teitur Óli Kristjánsson, Katie L Stone, Helge B D Sorensen, Andreas Brink-Kjaer, Emmanuel Mignot, Poul Jennum","doi":"10.1093/sleep/zsae219","DOIUrl":null,"url":null,"abstract":"<p><strong>Study objectives: </strong>To assess whether the frequency content of electroencephalography (EEG) and electrooculography (EOG) during nocturnal polysomnography (PSG) can predict all-cause mortality.</p><p><strong>Methods: </strong>Power spectra from PSGs of 8,716 participants, included from the MrOS Sleep Study and the Sleep Heart Health Study (SHHS), were analyzed in deep learning-based survival models. The best-performing model was further examined using SHapley Additive Explanation (SHAP) for data-driven sleep-stage specific definitions of power bands, which were evaluated in predicting mortality using Cox Proportional Hazards models.</p><p><strong>Results: </strong>Survival analyses, adjusted for known covariates, identified multiple EEG frequency bands across all sleep stages predicting all-cause mortality. For EEG, we found an all-cause mortality hazard ratio (HR) of 0.90 (CI95% 0.85-0.96) for 12-15 Hz in N2, 0.86 (CI95% 0.82-0.91) for 0.75-1.5 Hz in N3, and 0.87 (CI95% 0.83-0.92) for 14.75-33.5 Hz in REM sleep. For EOG, we found several low-frequency effects including an all-cause mortality HR of 1.19 (CI95% 1.11-1.28) for 0.25 Hz in N3, 1.11 (CI95% 1.03-1.21) for 0.75 Hz in N1, and 1.11 (CI95% 1.03-1.20) for 1.25-1.75 Hz in Wake. The gain in the concordance index (C-index) for all-cause mortality is minimal, with only a 0.24% increase: The best single mortality predictor was EEG N3 (0-0.5 Hz) with C-index of 77.78% compared to 77.54% for confounders alone.</p><p><strong>Conclusion: </strong>Spectral power features, possibly reflecting abnormal sleep microstructure, are associated with mortality risk. These findings add to a growing literature suggesting that sleep contains incipient predictors of health and mortality.</p>","PeriodicalId":22018,"journal":{"name":"Sleep","volume":null,"pages":null},"PeriodicalIF":5.6000,"publicationDate":"2024-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Sleep","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1093/sleep/zsae219","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"Medicine","Score":null,"Total":0}
引用次数: 0

Abstract

Study objectives: To assess whether the frequency content of electroencephalography (EEG) and electrooculography (EOG) during nocturnal polysomnography (PSG) can predict all-cause mortality.

Methods: Power spectra from PSGs of 8,716 participants, included from the MrOS Sleep Study and the Sleep Heart Health Study (SHHS), were analyzed in deep learning-based survival models. The best-performing model was further examined using SHapley Additive Explanation (SHAP) for data-driven sleep-stage specific definitions of power bands, which were evaluated in predicting mortality using Cox Proportional Hazards models.

Results: Survival analyses, adjusted for known covariates, identified multiple EEG frequency bands across all sleep stages predicting all-cause mortality. For EEG, we found an all-cause mortality hazard ratio (HR) of 0.90 (CI95% 0.85-0.96) for 12-15 Hz in N2, 0.86 (CI95% 0.82-0.91) for 0.75-1.5 Hz in N3, and 0.87 (CI95% 0.83-0.92) for 14.75-33.5 Hz in REM sleep. For EOG, we found several low-frequency effects including an all-cause mortality HR of 1.19 (CI95% 1.11-1.28) for 0.25 Hz in N3, 1.11 (CI95% 1.03-1.21) for 0.75 Hz in N1, and 1.11 (CI95% 1.03-1.20) for 1.25-1.75 Hz in Wake. The gain in the concordance index (C-index) for all-cause mortality is minimal, with only a 0.24% increase: The best single mortality predictor was EEG N3 (0-0.5 Hz) with C-index of 77.78% compared to 77.54% for confounders alone.

Conclusion: Spectral power features, possibly reflecting abnormal sleep microstructure, are associated with mortality risk. These findings add to a growing literature suggesting that sleep contains incipient predictors of health and mortality.

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
利用基于深度学习的睡眠脑电图和眼电图频率分析进行死亡率风险评估。
研究目的评估夜间多导睡眠图(PSG)中脑电图(EEG)和脑电图(EOG)的频率内容能否预测全因死亡率:基于深度学习的生存模型分析了8716名参与者的PSG功率谱,这些参与者来自MrOS睡眠研究和睡眠心脏健康研究(SHHS)。使用 SHapley Additive Explanation(SHAP)对表现最佳的模型进行了进一步检查,以获得数据驱动的睡眠阶段特定功率带定义,并使用 Cox Proportional Hazards 模型对其预测死亡率进行了评估:结果:经已知协变量调整后的生存分析发现,所有睡眠阶段的多个脑电图频段均可预测全因死亡率。就脑电图而言,我们发现在 N2 阶段,12-15 Hz 的全因死亡率危险比 (HR) 为 0.90(CI95% 0.85-0.96);在 N3 阶段,0.75-1.5 Hz 的全因死亡率危险比 (HR) 为 0.86(CI95% 0.82-0.91);在快速动眼期睡眠阶段,14.75-33.5 Hz 的全因死亡率危险比 (HR) 为 0.87(CI95% 0.83-0.92)。对于 EOG,我们发现了一些低频效应,包括 N3 中 0.25 Hz 的全因死亡率 HR 为 1.19(CI95% 为 1.11-1.28),N1 中 0.75 Hz 的全因死亡率 HR 为 1.11(CI95% 为 1.03-1.21),Wake 中 1.25-1.75 Hz 的全因死亡率 HR 为 1.11(CI95% 为 1.03-1.20)。全因死亡率的一致性指数(C-指数)增幅很小,仅增加了 0.24%:脑电图 N3(0-0.5 Hz)是预测死亡率的最佳单项指标,其 C 指数为 77.78%,而单独预测混杂因素的 C 指数为 77.54%:结论:可能反映睡眠微观结构异常的频谱功率特征与死亡风险有关。越来越多的文献表明,睡眠中含有预测健康和死亡率的雏形,这些发现为这一观点增添了新的内容。
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
Sleep
Sleep Medicine-Neurology (clinical)
CiteScore
8.70
自引率
10.70%
发文量
0
期刊介绍: SLEEP® publishes findings from studies conducted at any level of analysis, including: Genes Molecules Cells Physiology Neural systems and circuits Behavior and cognition Self-report SLEEP® publishes articles that use a wide variety of scientific approaches and address a broad range of topics. These may include, but are not limited to: Basic and neuroscience studies of sleep and circadian mechanisms In vitro and animal models of sleep, circadian rhythms, and human disorders Pre-clinical human investigations, including the measurement and manipulation of sleep and circadian rhythms Studies in clinical or population samples. These may address factors influencing sleep and circadian rhythms (e.g., development and aging, and social and environmental influences) and relationships between sleep, circadian rhythms, health, and disease Clinical trials, epidemiology studies, implementation, and dissemination research.
期刊最新文献
What is cataplexy? Wireless wearable sensors can facilitate rapid detection of sleep apnea in hospitalized stroke patients. Device-measured weekend catch-up sleep, mortality, and cardiovascular disease incidence in adults. A circadian-informed lighting intervention accelerates circadian adjustment to a night work schedule in a submarine lighting environment. Associations of accelerometer-measured sleep duration with incident cardiovascular disease and cardiovascular mortality.
×
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