Zheng Ping, Pan Ting, Gao Ya, Chen Juan, Li Liren, Chen Yan, Fang Dandan, Li Xuechun, Gao Fei, Li Yilei
Department of Pharmacy, Nanfang Hospital, Southern Medical University, Guangzhou, China.
Clinical Pharmacy Center, Nanfang Hospital, Southern Medical University, Guangzhou, China.
Clin Transl Sci. 2025 Jan;18(1):e70092. doi: 10.1111/cts.70092.
Mycophenolic acid (MPA) is commonly used to treat autoimmune diseases in children, and therapeutic drug monitoring is recommended to ensure adequate drug exposure. However, multiple blood sampling is required to calculate the area under the plasma concentration-time curve (AUC), causing patient discomfort and waste of human and financial resources. This study aims to use machine learning and deep learning algorithms to develop a prediction model of MPA exposure for pediatric autoimmune diseases with optimizing sampling frequency. Pediatric autoimmune patients' data were collected at Nanfang Hospital between June 2018 and June 2023. Univariate analysis was applied for feature selection. Ten algorithms, including Random Forest, XGBoost, LightGBM, Gradient Boosting Decision Tree, CatBoost, Artificial Neural Network, Grandient Boosting Machine, Transformer, Wide&Deep, and TabNet, were employed for modeling based on two, three, or four concentrations of MPA. A total of 614 MPA AUC samples from 209 patients were enrolled. Among the 10 models evaluated, the Wide&Deep model exhibited the best predictive performance. The predictive performance of the Wide&Deep model using four and three blood concentration points was similar (R ≈ 1 for four points; R = 0.95 for three points). No significant difference in accuracy within ±30% was observed between models utilizing three and four blood concentration points (p = 0.06). This study demonstrates that in the Wide&Deep model, MPA exposure can be accurately estimated with three sampling points in children with autoimmune diseases. This model could help reduce discomfort in pediatric patients without reducing the accuracy of MPA exposure estimates in clinical practice.
霉酚酸（MPA）常用于治疗儿童自身免疫性疾病，建议进行治疗药物监测以确保足够的药物暴露。然而，需要多次采血来计算血浆浓度 - 时间曲线（AUC）下的面积，这会给患者带来不适，并造成人力和财力资源的浪费。本研究旨在使用机器学习和深度学习算法，开发一种针对儿童自身免疫性疾病的MPA暴露预测模型，并优化采样频率。2018年6月至2023年6月期间在南方医院收集了儿科自身免疫性疾病患者的数据。采用单变量分析进行特征选择。基于MPA的两个、三个或四个浓度，使用十种算法进行建模，包括随机森林、XGBoost、LightGBM、梯度提升决策树、CatBoost、人工神经网络、梯度提升机、Transformer、Wide&Deep和TabNet。共纳入了来自209名患者的614个MPA AUC样本。在评估的10个模型中，Wide&Deep模型表现出最佳的预测性能。使用四个和三个血药浓度点的Wide&Deep模型的预测性能相似（四个点时R≈1；三个点时R = 0.95）。使用三个和四个血药浓度点的模型在±30%范围内的准确性没有显著差异（p = 0.06）。本研究表明，在Wide&Deep模型中，自身免疫性疾病儿童通过三个采样点就能准确估计MPA暴露。该模型有助于减少儿科患者的不适，同时在临床实践中不降低MPA暴露估计的准确性。
