文献速递癫痫

利用电子日记开发并验证癫痫发作预测模型

Development and Validation of Forecasting Next Reported Seizure Using e-Diaries.
PubMed 文献 · Ann Neurol · 2020-07-09

研究基于SeizureTracker.com的5,419例患者电子日记数据,训练深度学习模型预测未来24小时自我报告癫痫发作风险,并在独立测试集验证。AI模型AUC为0.86,优于随机预测的0.83,Brier技能评分为0.27,提示预测有效且优于随机水平,但临床价值尚待进一步研究。

要点

  • 深度学习模型可基于3个月电子日记预测未来24小时癫痫发作风险。
  • 测试集AUC 0.86优于随机预测AUC 0.83,校准指标BSS为0.27。
  • 预测有效性在多数患者中具有意义,临床价值仍需前瞻性验证。

核心结论

  • AI模型能有效预测未来24小时自我报告癫痫发作,性能优于随机预测。

研究设计与样本

  • 回顾性研究,使用SeizureTracker.com的5,419例患者电子日记数据。
  • 训练集3,806例患者共1,665,215患者日,测试集1,613例患者共549,588患者日,无患者重叠。
  • 采用循环网络加多层感知机的深度学习模型,基于3个月滑动窗口日记历史进行预测。

主要发现

  • AI模型AUC为0.86(95%CI 0.85-0.88),随机预测AUC为0.83(95%CI 0.81-0.85),差异有统计学意义(p<0.001)。
  • 总体Brier技能评分为0.27(95%CI 0.23-0.31),优于随机预测(p<0.001)。

关键数值与推荐

  • AI模型AUC 0.86(95%CI 0.85-0.88),随机预测AUC 0.83(95%CI 0.81-0.85)。
  • Brier技能评分0.27(95%CI 0.23-0.31),表示AI预测校准优于随机基准。

临床怎么用

  • 该模型可为癫痫患者提供未来24小时发作风险的个体化预测,辅助日常管理。
  • 预测结果需结合临床判断,其临床价值尚待进一步研究量化。

局限性

  • 研究为回顾性设计,基于自我报告日记数据,可能存在报告偏倚。
  • 预测的临床价值尚未在前瞻性研究中验证。

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

OBJECTIVE: There are no validated methods for predicting the timing of seizures. Using machine learning, we sought to forecast 24-hour risk of self-reported seizure from e-diaries. METHODS: Data from 5,419 patients on SeizureTracker.com (including seizure count, type, and duration) were split into training (3,806 patients/1,665,215 patient-days) and testing (1,613 patients/549,588 patient-days) sets with no overlapping patients. An artificial intelligence (AI) program, consisting of recurrent networks followed by a multilayer perceptron ("deep learning" model), was trained to produce risk forecasts. Forecasts were made from a sliding window of 3-month diary history for each day of each patient's diary. After training, the model parameters were held constant and the testing set was scored. A rate-matched random (RMR) forecast was compared to the AI. Comparisons were made using the area under the receiver operating characteristic curve (AUC), a measure of binary discrimination performance, and the Brier score, a measure of forecast calibration. The Brier skill score (BSS) measured the improvement of the AI Brier score compared to the benchmark RMR Brier score. Confidence intervals (CIs) on performance statistics were obtained via bootstrapping. RESULTS: The AUC was 0.86 (95% CI = 0.85-0.88) for AI and 0.83 (95% CI = 0.81-0.85) for RMR, favoring AI (p < 0.001). Overall (all patients combined), BSS was 0.27 (95% CI = 0.23-0.31), also favoring AI (p < 0.001). INTERPRETATION: The AI produced a valid forecast superior to a chance forecaster, and provided meaningful forecasts in the majority of patients. Future studies will be needed to quantify the clinical value of these forecasts for patients. ANN NEUROL 2020;88:588-595.

来源:Ann Neurol,查看原文。版权归原作者所有。

引用

  1. Goldenholz DM, Goldenholz SR, Romero J, et al. Development and Validation of Forecasting Next Reported Seizure Using e-Diaries. Ann Neurol. 2020. PMID: 32567720. doi:10.1002/ana.25812

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。