Importance The hippocampus is a highly epileptogenic brain region, yet over 90% of hippocampal epileptiform activity (HEA) cannot be identified on scalp electroencephalogram (EEG) by human experts. Currently, detection of HEA requires intracranial electrodes, which limits our understanding of the role of HEA in brain diseases. Objective To develop and validate a machine learning algorithm that accurately detects HEA from a standard scalp EEG, without the need for intracranial electrodes. Design, Setting, and Participants In this diagnostic study, conducted from 2008 to 2021, EEG data were used from patients with temporal lobe epilepsy (TLE) and healthy controls (HCs) to train and validate a deep neural network, HEAnet, to detect HEA on scalp EEG. Participants were evaluated at tertiary-level epilepsy centers at 2 academic hospitals: Massachusetts General Hospital (MGH) or Brigham and Women's Hospital (BWH). Included in the study were patients aged 12 to 78 years with a clinical diagnosis of TLE and HCs without epilepsy. Patients with TLE and HCs with a history of intracranial surgery were excluded from the study. Exposures Simultaneous intracranial EEG and/or scalp EEG. Main Outcomes and Measures Performance was assessed using cross-validated areas under the receiver operating characteristic curve (AUC ROC) and precision-recall curve (AUC PR) and additional clinically relevant metrics. Results HEAnet was trained and validated using data sets that were derived from a convenience sample of 141 eligible participants (97 with TLE and 44 HCs without epilepsy) whose retrospective EEG data were readily available. Data set 1 included the simultaneous scalp EEG and intracranial electrode recordings of 51 patients with TLE (mean [SD] age, 40.7 [15.9] years; 30 men [59%]) at MGH. An automatically generated training data set with 972 095 positive HEA examples was created, in addition to a held-out expert-annotated testing data set with 22 762 positive HEA examples. HEAnet's performance was validated on 2 independent scalp EEG data sets: (1) data set 2 (at MGH; 24 patients with TLE and 20 HCs; mean [SD] age, 42.3 [16.2] years; 17 men [39%]) and (2) data set 3 (at BWH; 22 patients with TLE and 24 HCs; mean [SD] age, 43.0 [14.4] years; 20 men [43%]). For single-event detection of HEA on data set 1, HEAnet achieved a mean (SD) AUC ROC of 0.89 (0.01) and a mean (SD) AUC PR of 0.39 (0.03). On external validation with data sets 2 and 3, HEAnet accurately distinguished TLE from HC (AUC ROC of 0.88 and 0.95, respectively) and predicted epilepsy lateralization with 100% and 92% accuracy, respectively. HEAnet tracked dynamic changes in HEA in response to seizure medication adjustments and performed comparably with human experts in diagnosing TLE from 1-hour scalp EEG recordings, diagnosing TLE in several individuals that experts missed. Without reducing specificity, addition of HEAnet to human expert EEG review increased sensitivity for diagnosing TLE in humans from 50% to 58% to 63% to 67%. Conclusions and Relevance Results of this diagnostic study suggest that HEAnet provides a novel, noninvasive, quantitative, and clinically relevant biomarker of hippocampal hyperexcitability in humans.

中文翻译：

---

头皮脑电图上海马癫痫样活动的无创检测。


重要性 海马体是一个高度致癫痫的大脑区域，但人类专家无法通过头皮脑电图 (EEG) 识别出超过 90% 的海马癫痫样活动 (HEA)。目前，HEA的检测需要颅内电极，这限制了我们对HEA在脑部疾病中作用的理解。目的 开发并验证一种机器学习算法，无需颅内电极，即可从标准头皮脑电图准确检测 HEA。设计、设置和参与者 在这项 2008 年至 2021 年进行的诊断研究中，使用颞叶癫痫 (TLE) 患者和健康对照 (HC) 患者的脑电图数据来训练和验证深度神经网络 HEAnet，以检测 HEA头皮脑电图。参与者在 2 家学术医院的三级癫痫中心接受评估：马萨诸塞州总医院 (MGH) 或布莱根妇女医院 (BWH)。该研究包括年龄在 12 岁至 78 岁之间、临床诊断为 TLE 和 HCs 但不伴有癫痫的患者。有颅内手术史的 TLE 和 HC 患者被排除在研究之外。暴露同步颅内脑电图和/或头皮脑电图。主要结果和措施 使用受试者工作特征曲线 (AUC ROC) 和精确回忆曲线 (AUC PR) 下的交叉验证面积以及其他临床相关指标来评估绩效。结果 HEAnet 使用数据集进行训练和验证，这些数据集来自 141 名符合条件的参与者（97 名患有 TLE 和 44 名 HC 没有癫痫）的方便样本，这些参与者的回顾性脑电图数据很容易获得。数据集 1 包括 MGH 51 名 TLE 患者（平均 [SD] 年龄，40.7 [15.9] 岁；30 名男性 [59%]）的同步头皮脑电图和颅内电极记录。 除了包含 22,762 个 HEA 正面示例的专家注释测试数据集之外，还创建了包含 972,095 个正面 HEA 示例的自动生成的训练数据集。 HEAnet 的性能在 2 个独立的头皮 EEG 数据集上得到验证：(1) 数据集 2（在 MGH；24 名 TLE 患者和 20 名 HC；平均 [SD] 年龄，42.3 [16.2] 岁；17 名男性 [39%]）和(2) 数据集 3（BWH；22 名 TLE 患者和 24 名 HC；平均 [SD] 年龄，43.0 [14.4] 岁；20 名男性 [43%]）。对于数据集 1 上 HEA 的单事件检测，HEAnet 的平均 (SD) AUC ROC 为 0.89 (0.01)，平均 (SD) AUC PR 为 0.39 (0.03)。在使用数据集 2 和 3 进行外部验证时，HEAnet 准确区分了 TLE 和 HC（AUC ROC 分别为 0.88 和 0.95），并分别以 100% 和 92% 的准确度预测癫痫偏侧化。 HEAnet 跟踪 HEA 响应癫痫药物调整的动态变化，并通过 1 小时头皮脑电图记录诊断 TLE，诊断出 TLE 的表现与人类专家相当，诊断出专家漏掉的几个个体的 TLE。在不降低特异性的情况下，将 HEAnet 添加到人类专家 EEG 审查中，将人类 TLE 诊断的敏感性从 50% 提高到 58% 到 63% 到 67%。这项诊断研究的结论和相关性结果表明，HEAnet 提供了一种新型、无创、定量且具有临床相关性的人类海马过度兴奋性生物标志物。