Department of Urology and Transplant Surgery, Ruijin Hospital, Shanghai Jiaotong University School of Medicine, Shanghai, China.
Department of Urology and Transplant Surgery, Zhongshan Hospital, Shanghai Fudan University, Shanghai, China.
Ther Drug Monit. 2022 Dec 1;44(6):738-746. doi: 10.1097/FTD.0000000000001020.
To predict mycophenolic acid (MPA) exposure in renal transplant recipients using a deep learning model based on a convolutional neural network with bilateral long short-term memory and attention methods.
A total of 172 Chinese renal transplant patients were enrolled in this study. The patients were divided into a training group (n = 138, Ruijin Hospital) and a validation group (n = 34, Zhongshan Hospital). Fourteen days after renal transplantation, rich blood samples were collected 0-12 hours after MPA administration. The plasma concentration of total MPA was measured using an enzyme-multiplied immunoassay technique. A limited sampling strategy based on a convolutional neural network-long short-term memory with attention (CALS) model for the prediction of the area under the concentration curve (AUC) of MPA was established. The established model was verified using the data from the validation group. The model performance was compared with that obtained from multiple linear regression (MLR) and maximum a posteriori (MAP) methods.
The MPA AUC 0-12 of the training and validation groups was 54.28 ± 18.42 and 41.25 ± 14.53 µg·ml -1 ·h, respectively. MPA plasma concentration after 2 (C 2 ), 6 (C 6 ), and 8 (C 8 ) hours of administration was the most significant factor for MPA AUC 0-12 . The predictive performance of AUC 0-12 estimated using the CALS model of the validation group was better than the MLR and MAP methods in previous studies (r 2 = 0.71, mean prediction error = 4.79, and mean absolute prediction error = 14.60).
The CALS model established in this study was reliable for predicting MPA AUC 0-12 in Chinese renal transplant patients administered mycophenolate mofetil and enteric-coated mycophenolic acid sodium and may have good generalization ability for application in other data sets.
基于卷积神经网络结合双边长短时记忆和注意力方法的深度学习模型，预测肾移植受者麦考酚酸（MPA）的暴露情况。
本研究共纳入 172 例中国肾移植患者。患者分为训练组（n = 138，瑞金医院）和验证组（n = 34，中山医院）。肾移植后 14 天，在 MPA 给药后 0-12 小时采集丰富的血样。采用酶联免疫吸附试验技术测定总 MPA 的血浆浓度。建立了基于卷积神经网络-长短时记忆结合注意力（CALS）模型的预测 MPA 浓度-时间曲线下面积（AUC）的有限采样策略。使用验证组的数据验证所建立的模型。比较了模型性能与多元线性回归（MLR）和最大后验（MAP）方法的结果。
训练组和验证组的 MPA AUC 0-12 分别为 54.28 ± 18.42 和 41.25 ± 14.53 µg·ml -1 ·h。给药后 2 小时（C 2 ）、6 小时（C 6 ）和 8 小时（C 8 ）的 MPA 血浆浓度是 MPA AUC 0-12 的最显著因素。验证组 CALS 模型估计的 AUC 0-12 的预测性能优于之前研究中的 MLR 和 MAP 方法（r 2 = 0.71，平均预测误差=4.79，平均绝对预测误差=14.60）。
本研究建立的 CALS 模型可靠，可预测中国接受吗替麦考酚酯和麦考酚酸钠肠溶片的肾移植患者的 MPA AUC 0-12，并且可能具有良好的推广能力，适用于其他数据集。
