• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利:CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法,用中文像聊天一样搜索,搜遍4000万医学文献。AI智能推荐,让科研检索更轻松。

立即免费搜索

文件翻译

保留排版,准确专业,支持PDF/Word/PPT等文件格式,支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述,25分钟生成高质量综述,智能提取关键信息,辅助科研写作。

立即免费体验

自动尖峰检测:哪个软件包?

Automated spike detection: Which software package?

机构信息

Department of Clinical Neurophysiology, Stichting Epilepsie Instellingen Nederland.

Department of Clinical Neurophysiology, Stichting Epilepsie Instellingen Nederland.

出版信息

Seizure. 2022 Feb;95:33-37. doi: 10.1016/j.seizure.2021.12.012. Epub 2021 Dec 26.

DOI:10.1016/j.seizure.2021.12.012
PMID:34974231
Abstract

PURPOSE

We assessed three commercial automated spike detection software packages (Persyst, Encevis and BESA) to see which had the best performance.

METHODS

Thirty prolonged EEG records from people aged at least 16 years were collected and 30-minute representative epochs were selected. Interictal epileptiform discharges (IEDs) were marked by three human experts and by all three software packages. For each 30-minutes selection and for each 10-second epoch we measured whether or not IEDs had occurred. We defined the gold standard as the combined detections of the experts. Kappa scores, sensitivity and specificity were estimated for each software package.

RESULTS

Sensitivity for Persyst in the default setting was 95% for 30-minute selections and 82% for 10-second epochs. Sensitivity for Encevis was 86% (30-minute selections) and 61% (10-second epochs). The specificity for both packages was 88% for 30-minute selections and 96%-99% for the 10-second epochs. Interrater agreement between Persyst and Encevis and the experts was similar than between experts (0.67-0.83 versus 0.63-0.67). Sensitivity for BESA was 40% and specificity 100%. Interrater agreement (0.25) was low.

CONCLUSIONS

IED detection by the Persyst automated software is better than the Encevis and BESA packages, and similar to human review, when reviewing 30-minute selections and 10-second epochs. This findings may help prospective users choose a software package.

摘要

目的

我们评估了三种商业自动化尖峰检测软件包(Persyst、Encevis 和 BESA),以了解哪种软件包性能最佳。

方法

收集了至少 16 岁的 30 份长时间脑电图记录,并选择了 30 分钟的代表性时段。由三位人类专家和所有三个软件包标记发作间期癫痫样放电(IEDs)。对于每个 30 分钟的选择和每个 10 秒的时段,我们都测量了是否发生了 IEDs。我们将专家的联合检测定义为金标准。为每个软件包估计了 Kappa 评分、灵敏度和特异性。

结果

在默认设置下,Persyst 的灵敏度为 95%,用于 30 分钟的选择,82%用于 10 秒的时段。Encevis 的灵敏度为 86%(30 分钟的选择)和 61%(10 秒的时段)。这两个软件包的特异性均为 88%,用于 30 分钟的选择,96%-99%用于 10 秒的时段。Persyst 和 Encevis 与专家之间的组内一致性与专家之间的相似(0.67-0.83 与 0.63-0.67)。BESA 的灵敏度为 40%,特异性为 100%。组内一致性(0.25)较低。

结论

在审查 30 分钟的选择和 10 秒的时段时,Persyst 自动化软件检测 IED 的性能优于 Encevis 和 BESA 软件包,与人工审查相似。这些发现可能有助于潜在用户选择软件包。

相似文献

1
Automated spike detection: Which software package?自动尖峰检测:哪个软件包?
Seizure. 2022 Feb;95:33-37. doi: 10.1016/j.seizure.2021.12.012. Epub 2021 Dec 26.
2
Automated seizure detection in an EMU setting: Are software packages ready for implementation?在 EMU 环境中自动进行癫痫发作检测:软件包是否已准备好实施?
Seizure. 2022 Mar;96:13-17. doi: 10.1016/j.seizure.2022.01.009. Epub 2022 Jan 13.
3
Systematic analysis and comparison of commercial seizure-detection software.系统分析和比较商业癫痫发作检测软件。
Epilepsia. 2021 Feb;62(2):426-438. doi: 10.1111/epi.16812. Epub 2021 Jan 19.
4
Comparison of Automated Spike Detection Software in Detecting Epileptiform Abnormalities on Scalp-EEG of Genetic Generalized Epilepsy Patients.比较遗传全面性癫痫患者头皮脑电图的自动棘波检测软件在检测棘波异常方面的表现。
J Clin Neurophysiol. 2024 Nov 1;41(7):618-624. doi: 10.1097/WNP.0000000000001039. Epub 2023 Oct 30.
5
Development of Expert-Level Automated Detection of Epileptiform Discharges During Electroencephalogram Interpretation.专家级脑电图解读中癫痫样放电自动检测的发展。
JAMA Neurol. 2020 Jan 1;77(1):103-108. doi: 10.1001/jamaneurol.2019.3485.
6
Accurate identification of EEG recordings with interictal epileptiform discharges using a hybrid approach: Artificial intelligence supervised by human experts.采用人工智能辅助人工专家的混合方法准确识别 EEG 记录中的发作间期癫痫样放电。
Epilepsia. 2022 May;63(5):1064-1073. doi: 10.1111/epi.17206. Epub 2022 Mar 7.
7
Improving staff response to seizures on the epilepsy monitoring unit with online EEG seizure detection algorithms.利用在线脑电图癫痫发作检测算法提高癫痫监测单元工作人员对癫痫发作的反应能力。
Epilepsy Behav. 2018 Jul;84:99-104. doi: 10.1016/j.yebeh.2018.04.026. Epub 2018 May 11.
8
Determining the Spike-Wave Index Using Automated Detection Software.使用自动化检测软件确定棘波指数。
J Clin Neurophysiol. 2021 May 1;38(3):198-201. doi: 10.1097/WNP.0000000000000672.
9
Interrater Reliability of Experts in Identifying Interictal Epileptiform Discharges in Electroencephalograms.专家在脑电图中识别发作间期癫痫样放电的组内信度。
JAMA Neurol. 2020 Jan 1;77(1):49-57. doi: 10.1001/jamaneurol.2019.3531.
10
Using sampled visual EEG review in combination with automated detection software at the EMU.在电休克治疗病房中使用抽样视觉脑电图复查与自动化检测软件相结合。
Seizure. 2020 Aug;80:96-99. doi: 10.1016/j.seizure.2020.06.002. Epub 2020 Jun 4.

引用本文的文献

1
Quantitative EEG signatures in patients with and without epilepsy development after a first seizure.首次发作后有或无癫痫发展患者的定量脑电图特征。
Epilepsia Open. 2025 Apr;10(2):427-440. doi: 10.1002/epi4.13128. Epub 2025 Mar 4.
2
SynchroLINNce: Toolbox for Neural Synchronization and Desynchronization Assessment in Epilepsy Animal Models.同步LINNce:癫痫动物模型中神经同步化与去同步化评估工具箱
Int J Psychol Res (Medellin). 2024 Jul 25;17(2):14-24. doi: 10.21500/20112084.7329. eCollection 2024 Jul-Dec.
3
Discovering EEG biomarkers of Lennox-Gastaut syndrome through unsupervised time-frequency analysis.
通过无监督时频分析发现伦诺克斯-加斯托综合征的脑电图生物标志物。
Epilepsia. 2025 Feb;66(2):541-553. doi: 10.1111/epi.18211. Epub 2024 Dec 12.
4
Spike-spindle coupling during sleep and its mechanism explanation in childhood focal epilepsy.睡眠期间的棘波-纺锤波耦合及其在儿童局灶性癫痫中的机制解释
Cogn Neurodyn. 2024 Oct;18(5):2145-2160. doi: 10.1007/s11571-023-10052-2. Epub 2024 Jan 4.
5
Expert level of detection of interictal discharges with a deep neural network.利用深度神经网络实现发作间期放电的专家级检测。
Epilepsia. 2025 Jan;66(1):184-194. doi: 10.1111/epi.18164. Epub 2024 Nov 12.
6
Evaluation of simplified wireless EEG recordings in the neurological emergency room.神经内科急诊中简化无线脑电图记录的评估。
PLoS One. 2024 Oct 31;19(10):e0310223. doi: 10.1371/journal.pone.0310223. eCollection 2024.
7
Epileptic activity on foramen ovale electrodes is associated with sleep and tau pathology in Alzheimer's disease.卵圆孔电极上的癫痫活动与阿尔茨海默病中的睡眠和tau病理相关。
Brain. 2025 Feb 3;148(2):506-520. doi: 10.1093/brain/awae231.
8
Subclinical epileptiform activity in the Alzheimer continuum: association with disease, cognition and detection method.阿尔茨海默病连续体中的亚临床癫痫样活动:与疾病、认知和检测方法的关联。
Alzheimers Res Ther. 2024 Jan 23;16(1):19. doi: 10.1186/s13195-023-01373-9.
9
Feasibility of high-density electric source imaging in the presurgical workflow: Effect of number of spikes and automated spike detection.高密度电源成像在术前工作流程中的可行性:棘波数量和自动棘波检测的影响。
Epilepsia Open. 2023 Sep;8(3):785-796. doi: 10.1002/epi4.12732. Epub 2023 Jun 1.
10
Moving the field forward: detection of epileptiform abnormalities on scalp electroencephalography using deep learning-clinical application perspectives.推动该领域发展:利用深度学习在头皮脑电图上检测癫痫样异常——临床应用前景
Brain Commun. 2022 Aug 29;4(5):fcac218. doi: 10.1093/braincomms/fcac218. eCollection 2022.