Epilepsy Unit - Neurology Dept. Hospital del Mar - Parc de Salut Mar, Barcelona, Spain; IMIM - Hospital del Mar Medical Research Institute, Barcelona, Spain.
Epilepsy Unit - Neurology Dept. Hospital del Mar - Parc de Salut Mar, Barcelona, Spain.
Neuroimage. 2019 Mar;188:261-273. doi: 10.1016/j.neuroimage.2018.11.052. Epub 2018 Dec 1.
Several models have been proposed to explain brain regional and interregional communication, the majority of them using methods that tap the frequency domain, like spectral coherence. Considering brain interareal communication as binary interactions, we describe a novel method devised to predict dynamics and thus highlight abrupt changes marked by unpredictability. Based on a variable-order Markov model algorithm developed in-house for data compression, the prediction error connectivity (PEC) estimates network transitions by calculating error matrices (EMs). We analysed 20 h of EEG signals of virtual networks generated with a neural mass model. Subnetworks changed through time (2 of 5 signals), from normal to normal or pathological states. PEC was superior to spectral coherence in detecting all considered transitions, especially in broad and ripple bands. Subsequently, EMs of real data were classified using a support vector machine in order to capture the transition from interictal to preictal state and calculate seizure risk. A single seizure was randomly selected for training. Through this approach it was possible to establish a threshold that the calculated risk consistently overcame minutes before the events. Using either spectral coherence or PEC we created 1000 models that successfully predicted 6 seizures (100% sensibility), a whole cluster recorded in a patient with hippocampal epilepsy. However, PEC resulted superior to coherence in terms of true seizure free time and amount of false warnings. Indeed, the best PEC model predicted 96% of interictal time (vs. 83% of coherence) of about 20 h of stereo-EEG. This analysis was extended to patients with neo/mesocortical temporal, neocortical frontal, parietal and occipital lobe epilepsy. Again PEC showed high performance, allowing the prediction of 31 events distributed across 10 days with ROC AUCs that reached 98% (average 93 ± 5%) in 6 different patients. Moreover, considering another state transition, PEC could classify and forecast up to 88% (average 85 ± 3%) of the REM phase both in deep and scalp EEG. In conclusion, PEC is a novel approach that relies on pattern analysis in the time-domain. We believe that this method can be successfully employed both for the study of brain connectivity, and also implemented in real-life solutions for seizure detection and prediction.
已经提出了几种模型来解释大脑区域和区域间的通讯，其中大多数使用的方法都是挖掘频域，如频谱相干性。我们将大脑区域间通讯视为二进制交互，描述了一种新的方法来预测动态，从而突出由不可预测性标记的突然变化。基于为数据压缩开发的内部变量阶马尔可夫模型算法，预测误差连接（PEC）通过计算误差矩阵（EM）来估计网络转换。我们分析了用神经质量模型生成的虚拟网络 20 小时的 EEG 信号。子网络随时间变化（5 个信号中的 2 个），从正常状态变为正常或病理状态。PEC 在检测所有考虑的转换方面优于频谱相干性，特别是在宽带和波纹频段。随后，使用支持向量机对真实数据的 EM 进行分类，以捕捉从间发性到预发性的转换，并计算癫痫发作的风险。随机选择一次癫痫发作进行训练。通过这种方法，可以建立一个阈值，该阈值在事件发生前几分钟内持续超过计算出的风险。使用频谱相干性或 PEC，我们创建了 1000 个模型，这些模型成功地预测了 6 次癫痫发作（100%的敏感性），这是在一名患有海马癫痫的患者中记录的整个集群。然而，PEC 在真无癫痫发作时间和假警告数量方面优于相干性。事实上，最佳 PEC 模型预测了大约 20 小时的立体 EEG 中 96%的间发性时间（而相干性为 83%）。该分析扩展到新皮质颞叶、新皮质额叶、顶叶和枕叶癫痫的患者。再次，PEC 表现出很高的性能，允许在 10 天内分布 31 个事件的预测，在 6 个不同的患者中达到 98%（平均 93±5%）的 ROC AUC。此外，考虑到另一种状态转换，PEC 可以对深度和头皮 EEG 中的 REM 阶段进行分类和预测，达到 88%（平均 85±3%）。总之，PEC 是一种依赖于时域中模式分析的新方法。我们相信，这种方法既可以成功地用于大脑连接性的研究，也可以应用于癫痫发作检测和预测的实际解决方案中。
