Objective. There is an unmet need to develop seizure detection algorithms from brain regions outside the epileptogenic cortex. The study aimed to demonstrate the feasibility of classifying seizures and interictal states from local field potentials (LFPs) recorded from the human thalamus—a subcortical region remote to the epileptogenic cortex. We tested the hypothesis that spectral and entropy-based features extracted from LFPs recorded from the anterior nucleus of the thalamus (ANT) can distinguish its state of ictal recruitment from other interictal states (including awake, sleep). Approach. Two supervised machine learning tools (random forest and the random kitchen sink) were used to evaluate the performance of spectral (discrete wavelet transform—DWT), and time-domain (multiscale entropy—MSE) features in classifying seizures from interictal states in patients undergoing stereo-electroencephalography (EEG) evaluation for epilepsy surgery. Under the supervision of IRB, field potentials were recorded from the ANT in consenting adults with drug-resistant temporal lobe epilepsy. Seizures were confirmed in the ANT using line-length and visual inspection. Wilcoxon rank-sum method was used to test the differences in spectral patterns between seizure and interictal (awake and sleep) states. Main results. 79 seizures (10 patients) and 158 segments (approx. 4 h) of interictal stereo-EEG data were analyzed. The mean seizure detection latencies with line length in the ANT varied between seizure types (range 5–34 s). However, the DWT and MSE in the ANT showed significant changes for all seizure types within the first 20 s after seizure onset. The random forest (accuracy 93.9% and false-positive 4.6%) and the random kitchen sink (accuracy 97.3% and false-positive 1.8%) classified seizures and interictal states. Significance. These results suggest that features extracted from the thalamic LFPs can be trained to detect seizures that can be used for monitoring seizure counts and for closed-loop seizure abortive interventions.

客观的。从致癫痫皮层以外的大脑区域开发癫痫发作检测算法的需求尚未得到满足。该研究旨在证明根据从人类丘脑（远离致癫痫皮层的皮层下区域）记录的局部场电位 (LFP) 对癫痫发作和发作间状态进行分类的可行性。我们检验了这样一个假设，即从丘脑前核 (ANT) 记录的 LFP 中提取的基于光谱和熵的特征可以将其发作期募集状态与其他发作间期状态（包括清醒、睡眠）区分开来。方法. 使用两个监督机器学习工具（随机森林和随机厨房水槽）来评估频谱（离散小波变换 - DWT）和时域（多尺度熵 - MSE）特征在分类患者发作间期癫痫发作中的性能癫痫手术的立体脑电图 (EEG) 评估。在 IRB 的监督下，在同意的患有耐药颞叶癫痫的成年人中记录了 ANT 的场电位。使用线长和目视检查在 ANT 中确认癫痫发作。Wilcoxon 秩和法用于测试癫痫发作和发作间期（清醒和睡眠）状态之间光谱模式的差异。主要结果。分析了 79 次癫痫发作（10 名患者）和 158 段（约 4 小时）的发作间立体脑电图数据。ANT 中线长的平均癫痫检测潜伏期因癫痫类型而异（范围 5-34 秒）。然而，在癫痫发作后的前 20 秒内，ANT 中的 DWT 和 MSE 显示出所有癫痫发作类型的显着变化。随机森林（准确率 93.9% 和假阳性 4.6%）和随机厨房水槽（准确率 97.3% 和假阳性 1.8%）对癫痫发作和发作间期状态进行分类。意义。这些结果表明，可以训练从丘脑 LFP 中提取的特征来检测可用于监测癫痫发作计数和闭环癫痫中止干预的癫痫发作。