任 斌 何秋毅 许 琼 王长希 陈 杰 郑志华 黎曙霞 陈 孝. 人工神经网络预测肾移植受者霉酚酸体内暴露药量J. 药学学报, 2009,44(12): 1397-1401.
引用本文: 任 斌 何秋毅 许 琼 王长希 陈 杰 郑志华 黎曙霞 陈 孝. 人工神经网络预测肾移植受者霉酚酸体内暴露药量J. 药学学报, 2009,44(12): 1397-1401.
LIN Bin, He-Qiu-Yi, Hu- Qiong, Wang-Chang-Xi, Chen- Jie, Zheng-Zhi-Hua, Li-Shu-Xia, Chen- Xiao. Prediction of mycophenolic acid exposure in renal transplantation recipients by artificial neural networkJ. 药学学报, 2009,44(12): 1397-1401.
Citation: LIN Bin, He-Qiu-Yi, Hu- Qiong, Wang-Chang-Xi, Chen- Jie, Zheng-Zhi-Hua, Li-Shu-Xia, Chen- Xiao. Prediction of mycophenolic acid exposure in renal transplantation recipients by artificial neural networkJ. 药学学报, 2009,44(12): 1397-1401.

人工神经网络预测肾移植受者霉酚酸体内暴露药量

Prediction of mycophenolic acid exposure in renal transplantation recipients by artificial neural network

  • 摘要:

    建立人工神经网络用于估算霉酚酸 (MPA) 体内暴露药量 (AUC)64例肾移植受者术后不同时间服用霉酚酸酯 (MMF), 于服药前以及服药后0.511.52346812 h10个时间点采取外周静脉血, 采用高效液相色谱法检测血浆MPA浓度, 用线性梯形法计算服药后012 h-时曲线下面积 (AUC0−12 h), 采用遗传算法配合动量法优化网络参数, 建立人工神经网络。以00.52 h血药浓度数据预测AUC0−12 h, 人工神经网络平均预测误差 (MPE) 与平均绝对误差 (MAE) 分别为−1.53%9.12%, 准确度及精密度优于多元线性回归。以00.5 h血药浓度数据预测AUC0−12 h, 人工神经网络MPEMAE分别为6.03%15.30%, 准确度及精密度亦优于多元线性回归。人工神经网络预测的准确度和精密度均优于多元线性回归法, 可用于预测MPA AUC0−12 h

     

    Abstract:

    The paper is aimed to establish an artificial neural network (ANN) for predicting mycophenolic acid (MPA) area under the plasma concentration-time curve (AUC) in renal transplantation recipients.        64 Chinese renal transplantation recipients receiving mycophenolate mofetil (MMF) were investigated.  10 timed samples were drawn at different days after transplantation.  Plasma MPA concentration was determined by HPLC method and area under curve over the period of 0 to 12 h (AUC0−12 h) was calculated using the linear trapezoidal rule.  ANN was established after network parameters were optimized using momentum method   in combination with genetic algorithm.  Furthermore, the predictive performance of ANN was compared   with that of multiple linear regression (MLR).  When using plasma MPA concentration of 0, 0.5, 2 h after MMF administration to predict MPA AUC0−12 h, mean prediction error and mean absolute prediction error were −1.53% and 9.12%, respectively.  Accuracy and precision of prediction by ANN were superior to that of MLR prediction, and similar results could be found when using plasma MPA concentration of 0, 0.5 h to predict MPA AUC0−12 h.  The accuracy and precision of ANN prediction were superior to that of MLR prediction, and ANN can be used to predict MPA AUC0−12 h.

     

/

返回文章
返回