Bernardo Danilo, Kim Jonathan, Cornet Marie-Coralie, Numis Adam L, Scheffler Aaron, Rao Vikram R, Amorim Edilberto, Glass Hannah C
Department of Neurology and Weill Institute for Neurosciences, University of California, San Francisco, San Francisco, California, USA.
Department of Neurology and Neurological Sciences, Stanford University, Palo Alto, California, USA.
Epilepsia. 2025 Jan;66(1):89-103. doi: 10.1111/epi.18163. Epub 2024 Nov 4.
This study was undertaken to develop a machine learning (ML) model to forecast initial seizure onset in neonatal hypoxic-ischemic encephalopathy (HIE) utilizing clinical and quantitative electroencephalogram (QEEG) features.
We developed a gradient boosting ML model (Neo-GB) that utilizes clinical features and QEEG to forecast time-dependent seizure risk. Clinical variables included cord blood gas values, Apgar scores, gestational age at birth, postmenstrual age (PMA), postnatal age, and birth weight. QEEG features included statistical moments, spectral power, and recurrence quantification analysis (RQA) features. We trained and evaluated Neo-GB on a University of California, San Francisco (UCSF) neonatal HIE dataset, augmenting training with publicly available neonatal electroencephalogram (EEG) datasets from Cork University and Helsinki University Hospitals. We assessed the performance of Neo-GB at providing dynamic and static forecasts with diagnostic performance metrics and incident/dynamic area under the receiver operating characteristic curve (iAUC) analyses. Model explanations were performed to assess contributions of QEEG features and channels to model predictions.
The UCSF dataset included 60 neonates with HIE (30 with seizures). In subject-level static forecasting at 30 min after EEG initiation, baseline Neo-GB without time-dependent features had an area under the receiver operating characteristic curve (AUROC) of .76 and Neo-GB with time-dependent features had an AUROC of .89. In time-dependent evaluation of the initial seizure onset within a 24-h seizure occurrence period, dynamic forecast with Neo-GB demonstrated median iAUC = .79 (interquartile range [IQR] .75-.82) and concordance index (C-index) = .82, whereas baseline static forecast at 30 min demonstrated median iAUC = .75 (IQR .72-.76) and C-index = .69. Model explanation analysis revealed that spectral power, PMA, RQA, and cord blood gas values made the strongest contributions in driving Neo-GB predictions. Within the most influential EEG channels, as the preictal period advanced toward eventual seizure, there was an upward trend in broadband spectral power.
This study demonstrates an ML model that combines QEEG with clinical features to forecast time-dependent risk of initial seizure onset in neonatal HIE. Spectral power evolution is an early EEG marker of seizure risk in neonatal HIE.
本研究旨在开发一种机器学习（ML）模型，利用临床和定量脑电图（QEEG）特征预测新生儿缺氧缺血性脑病（HIE）的首次癫痫发作。
我们开发了一种梯度提升ML模型（Neo-GB），利用临床特征和QEEG预测随时间变化的癫痫发作风险。临床变量包括脐血气值、阿氏评分、出生孕周、孕龄（PMA）、出生后年龄和出生体重。QEEG特征包括统计矩、频谱功率和递归定量分析（RQA）特征。我们在加利福尼亚大学旧金山分校（UCSF）的新生儿HIE数据集上对Neo-GB进行训练和评估，并使用来自科克大学和赫尔辛基大学医院的公开可用新生儿脑电图（EEG）数据集进行训练增强。我们使用诊断性能指标和接收器操作特征曲线下的事件/动态面积（iAUC）分析来评估Neo-GB在提供动态和静态预测方面的性能。进行模型解释以评估QEEG特征和通道对模型预测的贡献。
UCSF数据集包括60例HIE新生儿（30例有癫痫发作）。在脑电图开始后30分钟的个体水平静态预测中, 没有时间依赖性特征的基线Neo-GB的接收器操作特征曲线下面积（AUROC）为0.76，具有时间依赖性特征的Neo-GB的AUROC为0.89。在24小时癫痫发作期内对首次癫痫发作进行时间依赖性评估时，Neo-GB的动态预测显示中位数iAUC = 0.79（四分位间距[IQR] 0.75 - 0.82）和一致性指数（C-index）= 0.82，而30分钟时的基线静态预测显示中位数iAUC = 0.75（IQR 0.72 - 0.76）和C-index = 0.69。模型解释分析表明，频谱功率、PMA、RQA和脐血气值对驱动Neo-GB预测的贡献最大。在最具影响力的EEG通道中，随着发作前期向最终发作发展，宽带频谱功率呈上升趋势。
本研究展示了一种将QEEG与临床特征相结合的ML模型，用于预测新生儿HIE首次癫痫发作的时间依赖性风险。频谱功率演变是新生儿HIE癫痫发作风险的早期脑电图标志物。
