Department of Neurology, Haeundae Paik Hospital, Inje University College of Medicine, Busan, Korea.
Department of Radiology, Haeundae Paik Hospital, Inje University College of Medicine, Busan, Korea.
Acta Neurol Scand. 2021 Jun;143(6):637-645. doi: 10.1111/ane.13407. Epub 2021 Mar 18.
The aim of this study was to evaluate the feasibility of machine learning based on diffusion tensor imaging (DTI) measures to distinguish patients with focal epilepsy versus healthy controls and antiseizure medication (ASM) responsiveness.
This was a retrospective study performed at a tertiary hospital. We enrolled 456 patients with focal epilepsy, who underwent DTI and were taking ASMs. We enrolled 100 healthy subjects as a control. We obtained the conventional DTI measures and structural connectomic profiles from the DTI.
The support vector machine (SVM) classifier based on the conventional DTI measures revealed an accuracy of 76.5% and an area under curve (AUC) of 0.604 (95% Confidence interval (CI), 0.506-0.695). Another SVM classifier combined with structural connectomic profiles demonstrated an accuracy of 82.8% and an AUC of 0.701 (95% CI, 0.606-0.784). Of the 456 patients with epilepsy, 242 patients were ASM good responders, whereas 214 patients were ASM poor responders. In the classification of the ASM responders, an SVM classifier based on the conventional DTI measures revealed an accuracy of 54.9% and an AUC of 0.551 (95% CI, 0.443-0.655). Another SVM classifier combined with structural connectomic profiles demonstrated an accuracy of 59.3% and an AUC of 0.594 (95% CI, 0.485-0.695).
DTI using a machine learning is useful for differentiating patients with focal epilepsy from healthy controls, but it cannot classify ASM responsiveness. Combining structural connectomic profiles results in a better classification performance than the use of conventional DTI measures alone for identifying focal epilepsy and ASM responsiveness.
本研究旨在评估基于弥散张量成像（DTI）指标的机器学习在区分局灶性癫痫患者与健康对照者和抗癫痫药物（ASM）反应性方面的可行性。
这是一项在三级医院进行的回顾性研究。我们纳入了 456 名接受 DTI 检查并正在服用 ASM 的局灶性癫痫患者，同时纳入了 100 名健康受试者作为对照。我们从 DTI 中获得了常规 DTI 指标和结构连接组学图谱。
基于常规 DTI 指标的支持向量机（SVM）分类器显示出 76.5%的准确率和 0.604 的 AUC（95%置信区间（CI），0.506-0.695）。另一个结合结构连接组学图谱的 SVM 分类器显示出 82.8%的准确率和 0.701 的 AUC（95% CI，0.606-0.784）。在 456 名癫痫患者中，242 名患者为 ASM 良好反应者，214 名患者为 ASM 不良反应者。在 ASM 反应者的分类中，基于常规 DTI 指标的 SVM 分类器显示出 54.9%的准确率和 0.551 的 AUC（95% CI，0.443-0.655）。另一个结合结构连接组学图谱的 SVM 分类器显示出 59.3%的准确率和 0.594 的 AUC（95% CI，0.485-0.695）。
使用机器学习的 DTI 有助于区分局灶性癫痫患者与健康对照者，但无法对 ASM 反应性进行分类。与单独使用常规 DTI 指标相比，结合结构连接组学图谱可提高识别局灶性癫痫和 ASM 反应性的分类性能。
