In order to realize the early prediction of refractory epilepsy in children, data preprocessing technology was adopted to improve data quality, and then convolutional neural network (CNN) was employed to perform predictions. The results showed that the early prediction accuracy of this algorithm for refractory epilepsy in children was 0.941, the sensitivity was 0.918, the specificity was 0.905, the precision was 0.881, the recall was 0.877, and the F1 score was 0.879. The above six indicators were remarkably superior to those of other algorithms, suggesting that the early prediction of refractory epilepsy in children under this algorithm was accurate. Analysis of the electroencephalography (EEG) characteristics and magnetic resonance imaging (MRI) images of refractory epilepsy in children suggested that the MRI images of patients’ brains under this algorithm had obvious characteristics. The reason for the prediction error of the algorithm was that the duration of epilepsy was too short or the EEG of the patient didn’t change notably during the epileptic seizure. In summary, the prediction method of refractory epilepsy in children based on CNN was accurate, which had broad adoption prospects in assisting clinicians in the examination and diagnosis of refractory epilepsy in children.

中文翻译：

---

人工智能神经网络对儿童难治性癫痫的早期预测

为了实现儿童难治性癫痫的早期预测，采用数据预处理技术提高数据质量，然后利用卷积神经网络（CNN）进行预测。结果表明，该算法对儿童难治性癫痫的早期预测准确率为0.941，灵敏度为0.918，特异度为0.905，精密度为0.881，召回率为0.877，F1评分为0.879。上述六项指标均明显优于其他算法，表明该算法对儿童难治性癫痫的早期预测是准确的。通过对儿童难治性癫痫的脑电图（EEG）特征和磁共振成像（MRI）图像的分析表明，该算法下患者大脑的MRI图像具有明显的特征。算法预测误差的原因是癫痫持续时间太短或者癫痫发作期间患者脑电图没有明显变化。综上所述，基于CNN的儿童难治性癫痫预测方法准确，在辅助临床医生对儿童难治性癫痫的检查和诊断方面具有广阔的应用前景。