Automated Annotation of Epileptiform Burden and Its Association with Outcomes.
Automated Annotation of Epileptiform Burden and Its Association with Outcomes.
复制标题
DOI：
10.1002/ana.26161
复制
发表时间：
2021-08
影响因子：
11.2
通讯作者：
Westover MB
中科院分区：
文献类型：
--
作者：
Zafar SF;Rosenthal ES;Jing J;Ge W;Tabaeizadeh M;Aboul Nour H;Shoukat M;Sun H;Javed F;Kassa S;Edhi M;Bordbar E;Gallagher J;Moura V Jr;Ghanta M;Shao YP;An S;Sun J;Cole AJ;Westover MB
目的：确定急性发作患者癫痫样活动负荷与预后之间的剂量-反应关系。单中心回顾分析了1967名神经科、内科和外科患者，他们在2011-2017年间接受了16小时的连续脑电检查。我们开发了一种人工智能算法来注释11.02TB的脑电，并在记录的72小时内量化癫痫样活动负荷。我们评估了1)最初24小时的负荷，2)负荷最高的12小时时段(峰值负荷)，以及3)通过监测的前72小时累积的负荷。应用机器学习来评估癫痫样负荷对预后的影响。结果采用出院改良Rankin评分，分为良(0-4)和差(5-6)。癫痫样负荷峰值与不良预后独立相关(p<；0.0001)。其他独立关联包括年龄、APACHE II评分、发病时癫痫发作和缺氧缺血性脑病的诊断。根据最后一次脑电测量(最长72小时)到出院之间的时间间隔计算模型校准误差：1)最后一次测量到出院之间的5天：0.0941[CI 0.0706，0.1191]；最后一次测量到出院之间的5-10天：0.0946[CI 0.0631，0.1290]；>；最后一次测量到出院之间的10天：0.0998[CI 0.0698，0.1335]。在调整协变量后，最大癫痫活动负荷从0%增加到100%，不良结局的概率增加35%。癫痫样活动峰值负荷的自动测量为未来研究抑制癫痫样活动是否改善预后的多中心随机试验提供了一个方便、一致和可量化的靶点。
To determine the dose-response relation between epileptiform activity burden and outcomes in acutely ill patients. Single center retrospective analysis of 1967 neurologic, medical and surgical patients who underwent > 16 hours of continuous EEG between 2011–2017. We developed an AI algorithm to annotate 11.02 terabytes of EEG and quantify epileptiform activity burden within 72 hours of recording. We evaluated burden in 1) the first 24 hours of recording, 2) the 12-hr epoch with highest burden (peak burden), and 3) cumulative through the first 72 hours of monitoring. Machine learning was applied to estimate the effect of epileptiform burden on outcome. Outcome measure was discharge modified Rankin Scale, dichotomized as good (0–4) vs. poor (5–6). Peak epileptiform burden was independently associated with poor outcomes (p<0.0001). Other independent associations included age, APACHE II, seizure on presentation, and diagnosis of hypoxic ischemic encephalopathy. Model calibration error was calculated across three strata based on the time interval between last EEG measurement (up to 72 hours of monitoring) and discharge: 1) < 5 days between last measurement and discharge: 0.0941 [CI 0.0706, 0.1191); 5–10 days between last measurement and discharge: 0.0946 [CI 0.0631, 0.1290]; > 10 days between last measurement and discharge: 0.0998 [CI 0.0698, 0.1335]. After adjusting for covariates, increase in peak epileptiform activity burden from 0% to 100% increased the probability of poor outcome by 35%. Automated measurement of peak epileptiform activity burden affords a convenient, consistent, and quantifiable target for future multi-center randomized trials investigating whether suppressing epileptiform activity improves outcomes.
登录
查看更多内容
影响因子：
8.8
作者：
Lee, Hyunjo;Mizrahi, Moshe A.;Foreman, Brandon
通讯作者：
Foreman, Brandon
影响因子：
9.9
作者：
Claassen, J.;Jette, N.;Hirsch, L. J.
通讯作者：
Hirsch, L. J.
影响因子：
2.6
作者：
Ribeiro, A.;Singh, R.;Brunnhuber, F.
通讯作者：
Brunnhuber, F.
影响因子：
4.7
作者：
Zafar, Sahar F.;Postma, Eva N.;Westover, M. Brandon
通讯作者：
Westover, M. Brandon
DOI：
10.1007/978-1-4614-7138-7_4
发表时间：
2013-01-01
期刊：
INTRODUCTION TO STATISTICAL LEARNING: WITH APPLICATIONS IN R
影响因子：
--
作者：
James, Gareth;Witten, Daniela;Tibshirani, Robert
通讯作者：
Tibshirani, Robert