Alim-Marvasti Ali, Pérez-García Fernando, Dahele Karan, Romagnoli Gloria, Diehl Beate, Sparks Rachel, Ourselin Sebastien, Clarkson Matthew J, Duncan John S
Department of Clinical and Experimental Epilepsy, UCL Queen Square Institute of Neurology, University College London, London, United Kingdom.
Department of Medical Physics and Biomedical Engineering, University College London, London, United Kingdom.
Front Digit Health. 2021 Feb 10;3:559103. doi: 10.3389/fdgth.2021.559103. eCollection 2021.
Epilepsy affects 50 million people worldwide and a third are refractory to medication. If a discrete cerebral focus or network can be identified, neurosurgical resection can be curative. Most excisions are in the temporal-lobe, and are more likely to result in seizure-freedom than extra-temporal resections. However, less than half of patients undergoing surgery become entirely seizure-free. Localizing the epileptogenic-zone and individualized outcome predictions are difficult, requiring detailed evaluations at specialist centers. We used bespoke natural language processing to text-mine 3,800 electronic health records, from 309 epilepsy surgery patients, evaluated over a decade, of whom 126 remained entirely seizure-free. We investigated the diagnostic performances of machine learning models using set-of-semiology (SoS) with and without hippocampal sclerosis (HS) on MRI as features, using STARD criteria. Support Vector Classifiers (SVC) and Gradient Boosted (GB) decision trees were the best performing algorithms for temporal-lobe epileptogenic zone localization (cross-validated Matthews correlation coefficient (MCC) SVC 0.73 ± 0.25, balanced accuracy 0.81 ± 0.14, AUC 0.95 ± 0.05). Models that only used seizure semiology were not always better than internal benchmarks. The combination of multimodal features, however, enhanced performance metrics including MCC and normalized mutual information (NMI) compared to either alone ( < 0.0001). This combination of semiology and HS on MRI increased both cross-validated MCC and NMI by over 25% (NMI, SVC SoS: 0.35 ± 0.28 vs. SVC SoS+HS: 0.61 ± 0.27). Machine learning models using only the set of seizure semiology (SoS) cannot unequivocally perform better than benchmarks in temporal epileptogenic-zone localization. However, the combination of SoS with an imaging feature (HS) enhance epileptogenic lobe localization. We quantified this added NMI value to be 25% in absolute terms. Despite good performance in localization, no model was able to predict seizure-freedom better than benchmarks. The methods used are widely applicable, and the performance enhancements by combining other clinical, imaging and neurophysiological features could be similarly quantified. Multicenter studies are required to confirm generalizability. Wellcome/EPSRC Center for Interventional and Surgical Sciences (WEISS) (203145Z/16/Z).
癫痫影响着全球5000万人，其中三分之一的患者对药物治疗无效。如果能够确定离散的脑病灶或网络，神经外科手术切除可能会治愈疾病。大多数切除手术在颞叶进行，相比颞叶外切除，颞叶切除更有可能实现无癫痫发作。然而，接受手术的患者中不到一半能完全摆脱癫痫发作。定位致痫区和进行个体化预后预测很困难，需要在专科中心进行详细评估。我们使用定制的自然语言处理技术对3800份电子健康记录进行文本挖掘，这些记录来自309例接受癫痫手术的患者，评估时间超过十年，其中126例患者完全摆脱了癫痫发作。我们使用STARD标准，研究了以癫痫发作症状学集合（SoS）为特征、有无海马硬化（HS）的机器学习模型在磁共振成像（MRI）上的诊断性能。支持向量分类器（SVC）和梯度提升（GB）决策树是颞叶致痫区定位表现最佳的算法（交叉验证马修斯相关系数（MCC），SVC为0.73±0.25，平衡准确率为0.81±（0.14，曲线下面积（AUC）为0.95±0.05）。仅使用癫痫发作症状学的模型并不总是优于内部基准。然而与单独使用相比，多模态特征的组合提高了包括MCC和归一化互信息（NMI）在内的性能指标（<0.0001）。癫痫发作症状学和MRI上的HS相结合，使交叉验证的MCC和NMI均提高了25%以上（NMI，SVC SoS：0.35±0.28 对比 SVC SoS+HS：0.61±0.27）。仅使用癫痫发作症状学集合（SoS）的机器学习模型在颞叶致痫区定位中，表现不一定比基准更好。然而，SoS与成像特征（HS）的组合增强了致痫叶的定位。我们将这种增加的NMI值绝对量化为25%。尽管在定位方面表现良好，但没有模型在预测无癫痫发作方面比基准更好。所使用的方法具有广泛适用性，通过结合其他临床、成像和神经生理学特征实现的性能提升也可以类似地进行量化。需要进行多中心研究以确认其普遍性。惠康/工程和物理科学研究委员会介入与外科科学中心（WEISS）（203145Z/16/Z）
Brain Commun. 2022-5-19
J Clin Neurol. 2012-12-21
Epilepsia. 2012-9
No To Hattatsu. 2001-3
NPJ Digit Med. 2022-11-7
Brain Commun. 2022-5-19
World Neurosurg. 2017-10-3
Epilepsy Res. 2016-11
Epilepsy Behav. 2016-1
Zotero 插件
