Karl Landsteiner Institute for Clinical Epilepsy Research and Cognitive Neurology, Vienna, Austria.
Department of Neurology, Clinic Hietzing, Vienna, Austria.
Epilepsia. 2021 Feb;62(2):426-438. doi: 10.1111/epi.16812. Epub 2021 Jan 19.
To determine if three different commercially available seizure-detection software packages (Besa 2.0, Encevis 1.7, and Persyst 13) accurately detect seizures with high sensitivity, high specificity, and short detection delay in epilepsy patients undergoing long-term video-electroencephalography (EEG) monitoring (VEM).
Comparison of sensitivity (detection rate), specificity (false alarm rate), and detection delay of three commercially available seizure-detection software packages in 81 randomly selected patients with epilepsy undergoing long-term VEM.
Detection rates on a per-patient basis were not significantly different between Besa (mean 67.6%, range 0-100%), Encevis (77.8%, 0-100%) and Persyst (81%, 0-100%; P = .059). False alarm rate (per hour) was significantly different between Besa (mean 0.7/h, range 0.01-6.2/h), Encevis (0.2/h, 0.01-0.5/h), and Persyst (0.9/h, 0.04-6.5/h; P < .001). Detection delay was significantly different between Besa (mean 30 s, range 0-431 s), Encevis (25 s, 2-163 s), and Persyst (20 s, 0-167 s; P = .007). Kappa statistics showed moderate to substantial agreement between the reference standard and each seizure-detection software (Besa: 0.47, 95% confidence interval [CI] 0.36-0.59; Encevis: 0.59, 95% CI 0.47-0.7; Persyst: 0.63, 95% CI 0.51-0.74).
Three commercially available seizure-detection software packages showed similar, reasonable sensitivities on the same data set, but differed in false alarm rates and detection delay. Persyst 13 showed the highest detection rate and false alarm rate with the shortest detection delay, whereas Encevis 1.7 had a slightly lower sensitivity, the lowest false alarm rate, and longer detection delay.
在接受长期视频-脑电图（VEM）监测的癫痫患者中，确定三种不同的市售癫痫发作检测软件包（Besa 2.0、Encevis 1.7 和 Persyst 13）是否能够以高灵敏度、高特异性和短检测延迟准确检测发作。
比较三种市售癫痫发作检测软件包在 81 例随机选择的接受长期 VEM 的癫痫患者中的灵敏度（检测率）、特异性（假警报率）和检测延迟。
基于患者的检测率在 Besa（平均 67.6%，范围 0-100%）、Encevis（77.8%，0-100%）和 Persyst（81%，0-100%；P=0.059）之间无显著差异。假警报率（每小时）在 Besa（平均 0.7/h，范围 0.01-6.2/h）、Encevis（0.2/h，0.01-0.5/h）和 Persyst（0.9/h，0.04-6.5/h；P<0.001）之间有显著差异。检测延迟在 Besa（平均 30s，范围 0-431s）、Encevis（25s，2-163s）和 Persyst（20s，0-167s；P=0.007）之间有显著差异。Kappa 统计显示，参考标准与每种癫痫发作检测软件之间存在中度到高度一致（Besa：0.47，95%置信区间 [CI] 0.36-0.59；Encevis：0.59，95% CI 0.47-0.7；Persyst：0.63，95% CI 0.51-0.74）。
三种市售癫痫发作检测软件包在同一数据集上表现出相似的、合理的敏感性，但在假警报率和检测延迟方面存在差异。Persyst 13 显示出最高的检测率和假警报率，且检测延迟最短，而 Encevis 1.7 的灵敏度略低，假警报率最低，检测延迟最长。
