文献速递癫痫

基因组与临床数据整合深度学习预测新诊断癫痫治疗反应

Integrative Deep Learning of Genomic and Clinical Data for Predicting Treatment Response in Newly Diagnosed Epilepsy.
PubMed 文献 · Neurology · 2025-10-29

该研究开发并验证了一种多模态深度学习模型,整合临床与基因组特征,预测新诊断癫痫患者初始抗癫痫药物(ASM)治疗1年后的无发作概率。开发队列(澳大利亚,n=286)中,联合转录因子结合相关基因组变异与临床因素后AUC达0.74,显著优于仅临床模型(AUC 0.67);外部验证队列(n=219)中同样组合AUC为0.69,高于仅临床模型(AUC 0.62)。模型提示可辅助个体化选药。

要点

  • 整合临床与基因组特征的多模态深度学习模型可提升ASM反应预测性能。
  • 转录因子结合相关基因组变异联合临床因素在开发与验证队列中均优于仅临床模型。
  • 该模型或可支持新诊断癫痫的个体化初始ASM选择。

核心结论

  • 整合基因组数据与临床特征可增强深度学习模型预测新诊断癫痫患者ASM反应的能力,可能支持个体化治疗选择并改善临床结局。

研究设计与样本

  • 开发队列为澳大利亚新诊断癫痫个体(n=286,中位年龄39岁,47.2%无发作),外部验证队列为Human Epilepsy Project 1参与者(n=219,中位年龄31岁,20.5%无发作)。
  • 所有参与者启动ASM治疗并前瞻性随访至少1年,纳入16项临床因素及4类癫痫与ASM药物基因组学基因组特征(含或不含功能影响注释)。
  • 评估多种机器学习架构与多模态融合策略,预测初始ASM治疗1年时的无发作状态。

主要发现

  • 开发队列中,联合临床因素与影响转录因子结合的基因组变异获得最高AUC 0.74(95%CI 0.70-0.78),显著优于仅临床模型(AUC 0.67,95%CI 0.62-0.72;p<0.05)。
  • 外部验证队列中,相同特征组合AUC为0.69(95%CI 0.67-0.71),高于仅临床模型(AUC 0.62,95%CI 0.60-0.64;p<0.05)。
  • 将模型应用于开发队列,若所有参与者服用排名最高的ASM,平均预测无发作概率为68.05%(95%CI 65.79%-70.35%),而观察到的无发作率为47.2%(95%CI 41.3%-53.2%)。

临床怎么用

  • 该模型可辅助神经科医生在新诊断癫痫患者中个体化选择初始ASM,但需进一步外部验证与临床实施评估。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

BACKGROUND AND OBJECTIVES: Epilepsy is a common neurologic disorder. Although antiseizure medications (ASMs) are the first-line treatment, identifying the most effective ASM for each individual remains a trial-and-error process. Genetic variation may influence treatment response. We aimed to develop and validate a multimodal deep learning model that integrates clinical and genomic features to predict response to the initial ASM in people with newly diagnosed epilepsy. METHODS: We used data from individuals with newly diagnosed epilepsy in Australia as the development cohort and participants from the Human Epilepsy Project 1 (recruited in the United States, Europe, and Australia) as the external validation cohort. All participants initiated ASM treatment and were followed prospectively for at least 1 year. We included 16 clinical factors and constructed 4 genomic feature types related to epilepsy and ASM pharmacogenomics, with and without functional impact annotations. We evaluated various machine learning architectures and multimodal fusion strategies to predict seizure freedom while taking the initial ASM at 1 year. RESULTS: In the development cohort (n = 286, median age 39 years, 47.2% seizure free), combining clinical and genomic features in our proposed multimodal deep learning model improved predictive performance. The highest area under the receiver operating characteristic curve (AUC) of 0.74 (95% CI 0.70-0.78) was achieved using clinical factors and genomic variants affecting transcription factor binding, significantly outperforming the clinical-only model (AUC 0.67, 95% CI 0.62-0.72; p < 0.05). In the external validation cohort (n = 219, median age 31 years, 20.5% seizure free), the same feature combination achieved an AUC of 0.69 (95% CI 0.67-0.71), higher than the clinical-only model (AUC 0.62, 95% CI 0.60-0.64; p < 0.05). Applying this model to the development cohort, if all participants took the highest ranked ASMs, the mean predicted seizure-free probability would be 68.05% (95% CI 65.79%-70.35%) compared with the observed seizure-free rate of 47.2% (95% CI 41.3%-53.2%). DISCUSSION: Integrating genomic data with clinical features enhances the ability of deep learning models in predicting ASM response in newly diagnosed epilepsy. This approach may support personalized treatment selection and improve clinical outcomes.

来源:Neurology,查看原文。版权归原作者所有。

引用

  1. Feng W, Nhu D, Anderson A, et al. Integrative Deep Learning of Genomic and Clinical Data for Predicting Treatment Response in Newly Diagnosed Epilepsy. Neurology. 2025. PMID: 41160788. doi:10.1212/WNL.0000000000214315

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。