This study aimed to develop a classifier using supervised machine learning to effectively assess the impact of clinical, demographical, and biochemical factors in accurately predicting the antiseizure medications (ASMs) treatment response in people with epilepsy (PWE). Data was collected from 786 PWE at the Outpatient Department of Neurology, Institute of Human Behavior and Allied Sciences (IHBAS), New Delhi, India from 2005 to 2015. Patients were followed up at the 2nd, 4th, 8th, and 12th month over the span of 1 year for the drugs being administered and their dosage, the serum drug levels, the frequency of seizure control, drug efficacy, the adverse drug reactions (ADRs), and their compliance to ASMs. Several features, including demographic details, medical history, and auxiliary examinations electroencephalogram (EEG) or Computed Tomography (CT) were chosen to discern between patients with distinct remission outcomes. Remission outcomes were categorized into ‘good responder (GR)’ and ‘poor responder (PR)’ based on the number of seizures experienced by the patients over the study duration. Our dataset was utilized to train seven classical machine learning algorithms i.e Extreme Gradient Boost (XGB), K-Nearest Neighbor (KNN), Support Vector Classifier (SVC), Decision Tree (DT), Random Forest (RF), Naïve Bayes (NB) and Logistic Regression (LR) to construct classification models. Our research findings indicate that 1) among the seven algorithms examined, XGB and SVC demonstrated superior predictive performances of ASM treatment outcomes with an accuracy of 0.66 each and ROC-AUC scores of 0.67 (XGB) and 0.66 (SVC) in distinguishing between PR and GR patients. 2) The most influential factor in discerning PR to GR patients is a family history of seizures (no), education (literate) and multitherapy with Chi-square (χ2) values of 12.1539, 8.7232 and 13.620 respectively and odds ratio (OR) of 2.2671, 0.4467, and 1.9453 each. 3). Furthermore, our surrogate analysis revealed that the null hypothesis for both XGB and SVC was rejected at a 100 % confidence level, underscoring the significance of their predictive performance. These findings underscore the robustness and reliability of XGB and SVC in our predictive modelling framework. Utilizing XG Boost and SVC-based machine learning classifier, we successfully forecasted the likelihood of a patient's response to ASM treatment, categorizing them as either PR or GR, post-completion of standard epilepsy examinations. The classifier’s predictions were found to be statistically significant, suggesting their potential utility in improving treatment strategies, particularly in the personalized selection of ASM regimens for individual epilepsy patients.

中文翻译：

---

使用机器学习算法预测北印度人群抗癫痫药物治疗的疗效


本研究旨在开发一种使用监督机器学习的分类器，以有效评估临床、人口统计和生化因素的影响，准确预测癫痫患者 (PWE) 的抗癫痫药物 (ASM) 治疗反应。数据收集自 2005 年至 2015 年印度新德里人类行为与相关科学研究所 (IHBAS) 神经科门诊的 786 名 PWE。在治疗期间的第 2、4、8 和 12 个月对患者进行了随访。所用药物及其剂量、血清药物水平、癫痫发作控制频率、药物疗效、药物不良反应（ADR）及其对 ASM 的依从性的跨度为 1 年。选择了一些特征，包括人口统计详细信息、病史和辅助检查脑电图（EEG）或计算机断层扫描（CT）来区分具有不同缓解结果的患者。根据患者在研究期间经历的癫痫发作次数，缓解结果分为“良好反应者（GR）”和“不良反应者（PR）”。我们的数据集用于训练七种经典机器学习算法，即极限梯度提升 (XGB)、K 最近邻 (KNN)、支持向量分类器 (SVC)、决策树 (DT)、随机森林 (RF)、朴素贝叶斯 (NB) ）和逻辑回归（LR）构建分类模型。我们的研究结果表明，1) 在所检查的七种算法中，XGB 和 SVC 对 ASM 治疗结果表现出卓越的预测性能，准确度均为 0.66，在区分 PR 和GR患者。 2) 区分 PR 和 GR 患者的最有影响力的因素是癫痫家族史（无）、教育程度（有文化）和多重治疗，卡方 (χ2) 值分别为 12.1539、8.7232 和 13.620，比值比 (OR) 为分别为 2.2671、0.4467 和 1.9453。 3）。此外，我们的替代分析显示，XGB 和 SVC 的原假设均以 100% 的置信水平被拒绝，强调了它们预测性能的重要性。这些发现强调了 XGB 和 SVC 在我们的预测建模框架中的稳健性和可靠性。利用 XG Boost 和基于 SVC 的机器学习分类器，我们成功预测了患者对 ASM 治疗做出反应的可能性，在完成标准癫痫检查后将其分类为 PR 或 GR。研究发现分类器的预测具有统计显着性，表明它们在改进治疗策略方面具有潜在效用，特别是在为个体癫痫患者个性化选择 ASM 方案方面。