Longitudinal, EEG-based assessment of sleep in people with epilepsy: An automated sleep staging algorithm non-inferior to human raters

IF 2 Q3 NEUROSCIENCES

Clinical Neurophysiology Practice Pub Date : 2025-01-01 DOI:10.1016/j.cnp.2025.01.001

Asbjoern W. Helge , Federico G. Arguissain , Lukas Lechner , Gerhard Gritsch , Jonas Duun-Henriksen , Esben Ahrens , Tilmann Kluge , Manfred Hartmann

{"title":"Longitudinal, EEG-based assessment of sleep in people with epilepsy: An automated sleep staging algorithm non-inferior to human raters","authors":"Asbjoern W. Helge , Federico G. Arguissain , Lukas Lechner , Gerhard Gritsch , Jonas Duun-Henriksen , Esben Ahrens , Tilmann Kluge , Manfred Hartmann","doi":"10.1016/j.cnp.2025.01.001","DOIUrl":null,"url":null,"abstract":"<div><h3>Objective</h3><div>There is an unmet need in epilepsy management for tools that measure sleep objectively over long timespans. Subcutaneous EEG is well-suited for the task, but it requires a reliable automatic algorithm. Here, we present and evaluate such an algorithm, and we show clinical examples of how it produces important information.</div></div><div><h3>Methods</h3><div>A mix of scalp EEG and subcutaneous EEG was used to develop an algorithm to output sleep stages and common sleep parameters. The algorithm was tested on unseen data from 11 healthy subject and 12 people with epilepsy (PwE). Lastly, data (>3months) from three exemplary PwE were analyzed for sleep.</div></div><div><h3>Results</h3><div>The algorithm proved non-inferior at sleep stage segmentation on data from PwE compared to human raters using scalp EEG. It reached a Cohen’s kappa score of 0.8 [CI 0.78 – 0.83] on healthy subjects and on data from PwE it got to 0.705 [CI 0.663–––0.744] against rater D and 0.686 [CI 0.632–––0.739] against rater E. The three examples showed that useful information can be gained from longitudinal sleep analysis.</div></div><div><h3>Conclusion</h3><div>Subcutaneous EEG and a sleep algorithm can be employed to effectively review sleep in PwE at a level that is non-inferior compared to human raters.</div></div><div><h3>Significance</h3><div>This has the potential to make objective sleep parameters available in the clinic as a valuable addition to subjective sleep assessments.</div></div>","PeriodicalId":45697,"journal":{"name":"Clinical Neurophysiology Practice","volume":"10 ","pages":"Pages 30-39"},"PeriodicalIF":2.0000,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Clinical Neurophysiology Practice","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2467981X25000010","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"NEUROSCIENCES","Score":null,"Total":0}

引用次数: 0

Abstract

Objective

There is an unmet need in epilepsy management for tools that measure sleep objectively over long timespans. Subcutaneous EEG is well-suited for the task, but it requires a reliable automatic algorithm. Here, we present and evaluate such an algorithm, and we show clinical examples of how it produces important information.

Methods

A mix of scalp EEG and subcutaneous EEG was used to develop an algorithm to output sleep stages and common sleep parameters. The algorithm was tested on unseen data from 11 healthy subject and 12 people with epilepsy (PwE). Lastly, data (>3months) from three exemplary PwE were analyzed for sleep.

Results

The algorithm proved non-inferior at sleep stage segmentation on data from PwE compared to human raters using scalp EEG. It reached a Cohen’s kappa score of 0.8 [CI 0.78 – 0.83] on healthy subjects and on data from PwE it got to 0.705 [CI 0.663–––0.744] against rater D and 0.686 [CI 0.632–––0.739] against rater E. The three examples showed that useful information can be gained from longitudinal sleep analysis.

Conclusion

Subcutaneous EEG and a sleep algorithm can be employed to effectively review sleep in PwE at a level that is non-inferior compared to human raters.

Significance

This has the potential to make objective sleep parameters available in the clinic as a valuable addition to subjective sleep assessments.

查看原文本刊更多论文

癫痫患者睡眠的纵向、基于脑电图的评估：一种不逊于人类评分者的自动睡眠分期算法

目的在癫痫管理中，对长时间客观测量睡眠的工具的需求尚未得到满足。皮下脑电图很适合这项任务，但需要可靠的自动算法。在这里，我们提出并评估了这样的算法，并展示了它如何产生重要信息的临床例子。方法采用头皮脑电图和皮下脑电图的混合方法，开发一种输出睡眠阶段和常见睡眠参数的算法。该算法在11名健康受试者和12名癫痫患者（PwE）的未见数据上进行了测试。最后，对三个典型PwE的数据（3个月）进行睡眠分析。结果该算法对PwE数据的睡眠阶段分割效果优于头皮脑电图的人类评分者。健康受试者的Cohen 's kappa评分为0.8 [CI 0.78 - 0.83]， PwE的数据与评分者D的对比为0.705 [CI 0.663 - 0.744]，与评分者e的对比为0.686 [CI 0.632 - 0.739]。这三个例子表明，纵向睡眠分析可以获得有用的信息。结论皮下脑电图和睡眠算法可以有效地评价PwE的睡眠水平，且睡眠水平不低于人类评分者。这有可能使客观睡眠参数在临床中可用，作为主观睡眠评估的有价值的补充。

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分钟内获得全文求助全文

来源期刊

Clinical Neurophysiology Practice NEUROSCIENCES-

CiteScore

3.90

自引率

0.00%

发文量

审稿时长

71 days

期刊介绍： Clinical Neurophysiology Practice (CNP) is a new Open Access journal that focuses on clinical practice issues in clinical neurophysiology including relevant new research, case reports or clinical series, normal values and didactic reviews. It is an official journal of the International Federation of Clinical Neurophysiology and complements Clinical Neurophysiology which focuses on innovative research in the specialty. It has a role in supporting established clinical practice, and an educational role for trainees, technicians and practitioners.