School of Pharmacy, Nanchang University, Nanchang, China.
Department of Pharmacy, The First Affiliated Hospital of Nanchang University, Nanchang, China.
J Clin Pharm Ther. 2022 May;47(5):600-608. doi: 10.1111/jcpt.13579. Epub 2021 Nov 21.
Tacrolimus (TAC), a first-line immunosuppressant in solid-organ transplant, has a narrow therapeutic window and large inter-individual variability, which affects its use in clinical practice. Successful predictions using machine learning algorithms have been reported in several fields. However, a comparison of 10 machine learning model-based TAC pharmacogenetic and pharmacokinetic dosing algorithms for kidney transplant perioperative patients of Chinese descent has not been reported. The objective of this study was to screen and establish an appropriate machine learning method to predict the individualized dosages of TAC for perioperative kidney transplant patients.
The records of 2551 patients were collected from three transplant centres, 80% of which were randomly selected as a 'derivation cohort' to develop the dose prediction algorithm, while the remaining 20% constituted a 'validation cohort' to validate the final algorithm selected. Important features were screened according to our previously established population pharmacokinetic model of tacrolimus. The performances of the algorithms were evaluated and compared using R-squared and the mean percentage in the remaining 20% of patients.
This study identified several factors influencing TAC dosage, including CYP3A5 rs776746, CYP3A4 rs4646437, haematocrit, Wuzhi capsules, TAC daily dose, age, height, weight, post-operative time, nifedipine and the medication history of the patient. According to our results, among the 10 machine learning models, the extra trees regressor (ETR) algorithm showed the best performance in the training set (R-squared: 1, mean percentage within 20%: 100%) and test set (R-squared: 0.85, mean percentage within 20%: 92.77%) of the derivation cohort. The ETR model successfully predicted the ideal TAC dosage in 97.73% of patients, especially in the intermediate dosage range (>5 mg/day to <8 mg/day), whereby the ideal TAC dosage could be successfully predicted in 99% of the patients.
The results indicated that the ETR algorithm, which was chosen to establish the dose prediction model, performed better than the other nine machine learning models. This study is the first to establish ETR algorithms to predict TAC dosage. This study will further promote the individualized medication of TAC in kidney transplant patients in the future, which has great significance in ensuring the safety and effectiveness of drug use.
他克莫司（TAC）是实体器官移植中一线免疫抑制剂，其治疗窗较窄，个体间差异较大，这影响了其在临床实践中的应用。机器学习算法的成功预测已在多个领域得到报道。然而，尚未有报道比较 10 种基于机器学习模型的他克莫司在移植围手术期中国裔肾移植患者的药代动力学和药代动力学剂量算法。本研究的目的是筛选并建立一种合适的机器学习方法，以预测围手术期肾移植患者他克莫司的个体化剂量。
从三个移植中心收集了 2551 例患者的记录，其中 80%被随机抽取作为“推导队列”来开发剂量预测算法，其余 20%作为“验证队列”来验证最终选择的算法。根据我们之前建立的他克莫司群体药代动力学模型，筛选出重要特征。使用 R 平方和剩余 20%患者中的平均百分比来评估和比较算法的性能。
本研究确定了影响 TAC 剂量的几个因素，包括 CYP3A5 rs776746、CYP3A4 rs4646437、红细胞压积、五指胶囊、TAC 日剂量、年龄、身高、体重、术后时间、硝苯地平以及患者的用药史。根据我们的结果，在 10 种机器学习模型中，在推导队列的训练集（R 平方：1，剩余 20%患者的平均百分比：100%）和测试集（R 平方：0.85，剩余 20%患者的平均百分比：92.77%）中，额外树回归器（ETR）算法表现最佳。ETR 模型成功预测了 97.73%患者的理想 TAC 剂量，特别是在中剂量范围（>5mg/天至<8mg/天），其中 99%的患者可以成功预测理想的 TAC 剂量。
结果表明，选择建立剂量预测模型的 ETR 算法表现优于其他 9 种机器学习模型。这是首次建立 ETR 算法来预测 TAC 剂量。本研究将进一步促进未来肾移植患者 TAC 的个体化用药，这对确保药物使用的安全性和有效性具有重要意义。
