Purpose

There remain major challenges for the clinician in managing patients with epilepsy effectively. Choosing anti-seizure medications (ASMs) is subject to trial and error. About one-third of patients have drug-resistant epilepsy (DRE). Surgery may be considered for selected patients, but time from diagnosis to surgery averages 20 years. We reviewed the potential use of machine learning (ML) predictive models as clinical decision support tools to help address some of these issues.

Methods

We conducted a comprehensive search of Medline and Embase of studies that investigated the application of ML in epilepsy management in terms of predicting ASM responsiveness, predicting DRE, identifying surgical candidates, and predicting epilepsy surgery outcomes. Original articles addressing these 4 areas published in English between 2000 and 2020 were included.

Results

We identified 24 relevant articles: 6 on ASM responsiveness, 3 on DRE prediction, 2 on identifying surgical candidates, and 13 on predicting surgical outcomes. A variety of potential predictors were used including clinical, neuropsychological, imaging, electroencephalography, and health system claims data. A number of different ML algorithms and approaches were used for prediction, but only one study utilized deep learning methods. Some models show promising performance with areas under the curve above 0.9. However, most were single setting studies (18 of 24) with small sample sizes (median number of patients 55), with the exception of 3 studies that utilized large databases and 3 studies that performed external validation. There was a lack of standardization in reporting model performance. None of the models reviewed have been prospectively evaluated for their clinical benefits.

Conclusion

The utility of ML models for clinical decision support in epilepsy management remains to be determined. Future research should be directed toward conducting larger studies with external validation, standardization of reporting, and prospective evaluation of the ML model on patient outcomes.

中文翻译：

---

用于癫痫管理决策支持的机器学习模型：批判性评论

目的

临床医生在有效管理癫痫患者方面仍然存在重大挑战。选择抗癫痫药物 (ASM) 需要反复试验。大约三分之一的患者患有耐药性癫痫 (DRE)。某些患者可能会考虑手术，但从诊断到手术的平均时间为 20 年。我们回顾了机器学习 (ML) 预测模型作为临床决策支持工具的潜在用途，以帮助解决其中一些问题。

方法

我们对 Medline 和 Embase 的研究进行了全面搜索，这些研究调查了 ML 在预测 ASM 反应性、预测 DRE、确定手术候选者和预测癫痫手术结果方面的癫痫管理中的应用。包括 2000 年至 2020 年间以英文发表的针对这 4 个领域的原始文章。

结果

我们确定了 24 篇相关文章：6 篇关于 ASM 反应性，3 篇关于 DRE 预测，2 篇关于确定手术候选者，13 篇关于预测手术结果。使用了各种潜在的预测因素，包括临床、神经心理学、成像、脑电图和卫生系统索赔数据。许多不同的机器学习算法和方法被用于预测，但只有一项研究使用了深度学习方法。一些模型显示出有希望的性能，曲线下面积高于 0.9。然而，除了 3 项利用大型数据库的研究和 3 项进行外部验证的研究外，大多数是单一环境研究（24 项中的 18 项），样本量较小（患者中位数为 55 人）。报告模型性能缺乏标准化。

结论

ML 模型在癫痫管理中用于临床决策支持的效用仍有待确定。未来的研究应转向进行更大规模的研究，进行外部验证、报告标准化以及对 ML 模型对患者结果的前瞻性评估。