Department of Pharmacy, Xiangya Hospital, Central South University, No.87 Xiangya Road, Changsha, 410008, China.
Institute for Rational and Safe Medication Practices, National Clinical Research Center for Geriatric Disorders, Xiangya Hospital, Central South University, Changsha, 410008, China.
Arch Toxicol. 2024 Sep;98(9):3049-3061. doi: 10.1007/s00204-024-03803-5. Epub 2024 Jun 16.
Valproic acid (VPA) is a primary medication for epilepsy, yet its hepatotoxicity consistently raises concerns among individuals. This study aims to establish an automated machine learning (autoML) model for forecasting the risk of abnormal increase of transaminase levels while undergoing VPA therapy for 1995 epilepsy patients. The study employed the two-tailed T test, Chi-square test, and binary logistic regression analysis, selecting six clinical parameters, including age, stature, leukocyte count, Total Bilirubin, oral dosage of VPA, and VPA concentration. These variables were used to build a risk prediction model using "H2O" autoML platform, achieving the best performance (AUC training = 0.855, AUC test = 0.789) in the training and testing data set. The model also exhibited robust accuracy (AUC valid = 0.742) in an external validation set, underscoring its credibility in anticipating VPA-induced transaminase abnormalities. The significance of the six variables was elucidated through importance ranking, partial dependence, and the TreeSHAP algorithm. This novel model offers enhanced versatility and explicability, rendering it suitable for clinicians seeking to refine parameter adjustments and address imbalanced data sets, thereby bolstering classification precision. To summarize, the personalized prediction model for VPA-treated epilepsy, established with an autoML model, displayed commendable predictive capability, furnishing clinicians with valuable insights for fostering pharmacovigilance.
丙戊酸（VPA）是治疗癫痫的主要药物，但它的肝毒性一直是人们关注的问题。本研究旨在为 1995 名接受 VPA 治疗的癫痫患者建立一个自动化机器学习（autoML）模型，以预测转氨升高的风险。该研究采用了双侧 T 检验、卡方检验和二项逻辑回归分析，选择了 6 个临床参数，包括年龄、身高、白细胞计数、总胆红素、VPA 的口服剂量和 VPA 浓度。这些变量被用于使用“H2O”autoML 平台构建风险预测模型，在训练和测试数据集上取得了最佳性能（AUC 训练=0.855，AUC 测试=0.789）。该模型在外部验证集中也表现出了稳健的准确性（AUC 有效=0.742），突显了其在预测 VPA 诱导的转氨酶异常方面的可信度。通过重要性排名、部分依赖和 TreeSHAP 算法阐明了这 6 个变量的意义。该新模型提供了增强的通用性和可解释性，使其适用于希望改进参数调整和处理不平衡数据集的临床医生，从而提高分类精度。总之，使用 autoML 模型建立的 VPA 治疗癫痫的个性化预测模型显示出了良好的预测能力，为临床医生提供了有价值的药物警戒洞察。
