Affiliated Hospital of Qingdao University, Qingdao, China; Qingdao Municipal Hospital, Qingdao, China.
Department of Neuroscience, Central Clinical School, Monash University, Melbourne, Victoria, Australia.
Epilepsy Res. 2024 Sep;205:107397. doi: 10.1016/j.eplepsyres.2024.107397. Epub 2024 Jun 28.
Epilepsy is a serious complication after an ischemic stroke. Although two studies have developed prediction model for post-stroke epilepsy (PSE), their accuracy remains insufficient, and their applicability to different populations is uncertain. With the rapid advancement of computer technology, machine learning (ML) offers new opportunities for creating more accurate prediction models. However, the potential of ML in predicting PSE is still not well understood. The purpose of this study was to develop prediction models for PSE among ischemic stroke patients.
Patients with ischemic stroke from two stroke centers were included in this retrospective cohort study. At the baseline level, 33 input variables were considered candidate features. The 2-year PSE prediction models in the derivation cohort were built using six ML algorithms. The predictive performance of these machine learning models required further appraisal and comparison with the reference model using the conventional triage classification information. The Shapley additive explanation (SHAP), based on fair profit allocation among many stakeholders according to their contributions, is used to interpret the predicted outcomes of the naive Bayes (NB) model.
A total of 1977 patients were included to build the predictive model for PSE. The Boruta method identified NIHSS score, hospital length of stay, D-dimer level, and cortical involvement as the optimal features, with the receiver operating characteristic curves ranging from 0.709 to 0.849. An additional 870 patients were used to validate the ML and reference models. The NB model achieved the best performance among the PSE prediction models with an area under the receiver operating curve of 0.757. At the 20 % absolute risk threshold, the NB model also provided a sensitivity of 0.739 and a specificity of 0.720. The reference model had poor sensitivities of only 0.15 despite achieving a helpful AUC of 0.732. Furthermore, the SHAP method analysis demonstrated that a higher NIHSS score, longer hospital length of stay, higher D-dimer level, and cortical involvement were positive predictors of epilepsy after ischemic stroke.
Our study confirmed the feasibility of applying the ML method to use easy-to-obtain variables for accurate prediction of PSE and provided improved strategies and effective resource allocation for high-risk patients. In addition, the SHAP method could improve model transparency and make it easier for clinicians to grasp the prediction model's reliability.
癫痫是缺血性中风后的严重并发症。尽管有两项研究已经开发出了预测中风后癫痫（PSE）的模型，但它们的准确性仍然不足，并且其在不同人群中的适用性尚不确定。随着计算机技术的飞速发展，机器学习（ML）为创建更准确的预测模型提供了新的机会。然而，ML 在预测 PSE 中的潜力仍未被充分理解。本研究的目的是为缺血性中风患者建立 PSE 预测模型。
本回顾性队列研究纳入了来自两个中风中心的缺血性中风患者。在基线水平，考虑了 33 个输入变量作为候选特征。在推导队列中，使用六种 ML 算法构建了 2 年 PSE 预测模型。这些机器学习模型的预测性能需要进一步评估，并与传统分诊分类信息的参考模型进行比较。基于根据贡献公平分配多方利益的 Shapley 加性解释（SHAP），用于解释朴素贝叶斯（NB）模型的预测结果。
共纳入 1977 例患者构建 PSE 预测模型。Boruta 方法确定 NIHSS 评分、住院时间、D-二聚体水平和皮质受累为最佳特征，ROC 曲线范围为 0.709 至 0.849。另外 870 例患者用于验证 ML 和参考模型。在 PSE 预测模型中，NB 模型的表现最佳，ROC 曲线下面积为 0.757。在 20%绝对风险阈值下，NB 模型的敏感性为 0.739，特异性为 0.720。参考模型的敏感性仅为 0.15，尽管 AUC 达到了 0.732。此外，SHAP 方法分析表明，NIHSS 评分较高、住院时间较长、D-二聚体水平较高和皮质受累是缺血性中风后癫痫的阳性预测因素。
本研究证实了应用 ML 方法使用易于获得的变量准确预测 PSE 的可行性，并为高危患者提供了改进的策略和有效的资源分配。此外，SHAP 方法可以提高模型的透明度，使临床医生更容易掌握预测模型的可靠性。
