Blood concentration monitoring of tacrolimus in patients with nephrotic syndrome and establishment of MLP prediction model

YAN Xiaolu; OUYANG Hua; ZHU Longsheng; ZHENG Lingzhao; LIN Xiaoqing; LIN Xiaofeng; LI Hongyuan

doi:10.6039/j.issn.1001-0408.2024.05.13

您当前的位置：

首页 >

文章列表页 >

Blood concentration monitoring of tacrolimus in patients with nephrotic syndrome and establishment of MLP prediction model

更新时间：2024-03-08

- Blood concentration monitoring of tacrolimus in patients with nephrotic syndrome and establishment of MLP prediction model
- ZHONGGUO YAOFANG Vol. 35, Issue 5, Pages: 584-589(2024)
- 作者机构：
  
  1.福建医科大学药学院，福州　350122
  2.厦门大学附属中山医院药学部，福建厦门　361004
  3.厦门市药学会，福建厦门　361004
  4.西交利物浦大学智能工程学院，江苏苏州　215006
- 作者简介：
- 基金信息：
- DOI：10.6039/j.issn.1001-0408.2024.05.13
  CLC： R969
- Published：15 March 2024，
  
  Received：03 August 2023，
  
  Revised：17 February 2024，
扫描看全文
严晓鹭,欧阳华,朱隆昇等.肾病综合征患者他克莫司血药浓度监测及MLP预测模型建立 ^Δ[J].中国药房,2024,35(05):584-589.

YAN Xiaolu,OUYANG Hua,ZHU Longsheng,et al.Blood concentration monitoring of tacrolimus in patients with nephrotic syndrome and establishment of MLP prediction model[J].ZHONGGUO YAOFANG,2024,35(05):584-589.
严晓鹭,欧阳华,朱隆昇等.肾病综合征患者他克莫司血药浓度监测及MLP预测模型建立 ^Δ[J].中国药房,2024,35(05):584-589. DOI： 10.6039/j.issn.1001-0408.2024.05.13.

YAN Xiaolu,OUYANG Hua,ZHU Longsheng,et al.Blood concentration monitoring of tacrolimus in patients with nephrotic syndrome and establishment of MLP prediction model[J].ZHONGGUO YAOFANG,2024,35(05):584-589. DOI： 10.6039/j.issn.1001-0408.2024.05.13.

摘要

目的

考察肾病综合征（NS）患者使用他克莫司后的血药浓度监测情况，同时建立他克莫司血药浓度预测模型。

方法

收集厦门大学附属中山医院2020年1月1日至2023年8月31日166例NS患者使用他克莫司的血药浓度监测数据（共计509次），并对其疗效、药物不良反应（ADR）与血药浓度的相关性进行分析。利用其中109例含有基因信息的NS患者的302次血药浓度监测数据建立多层感知机（MLP）预测模型，并对其进行验证。

结果

在疗效方面，未缓解组患者的中位血药浓度为2.20 ng/mL，显著低于部分缓解组的4.00 ng/mL（

＜0.001）和完全缓解组的3.60 ng/mL（

＝0.002）。在ADR方面，发生ADR组患者的中位血药浓度为5.01 ng/mL，显著高于未发生ADR组的3.37 ng/mL（

＝0.001），且经受试者工作特征曲线亚组分析后可知，他克莫司血药浓度≥6.65 ng/mL时，患者更易发生血肌酐升高[曲线下面积（AUC）为0.764，

＜0.001]；他克莫司血药浓度≥6.55 ng/mL时，患者更易发生血糖升高（AUC＝0.615，

＝0.005）。所建立的MLP预测模型的损失函数值为0.9，预测值与实测值的平均误差绝对值为0.279 5 ng/mL，验证散点图的决定系数为0.984，说明模型取得了良好的预测效果。

结论

他克莫司血药浓度对NS患者的疗效和ADR均有影响。利用MLP模型进行血药浓度预测的准确率高，预测值与实测值之间误差小，该模型可作为临床个体化用药方案中的重要工具。

Abstract

OBJECTIVE

To investigate the monitoring of tacrolimus blood concentration in patients with nephrotic syndrome （NS），and to establish a prediction model for tacrolimus blood concentration.

METHODS

Data from 509 concentration monitoring sessions of 166 NS patients using tacrolimus were collected from January 1， 2020 to August 31， 2023 in Zhongshan Hospital Affiliated to Xiamen University. The relationship of efficacy and adverse drug reaction（ADR） with blood concentration was analyzed. A multilayer perceptron （MLP） prediction model was established by using the blood concentration monitoring data of 302 times from 109 NS patients with genetic information， and then verified.

RESULTS

In terms of efficacy， the median blood concentration of tacrolimus in the non-remission group was 2.20 ng/mL， which was significantly lower than that in the partial remission group （4.00 ng/mL，

＜0.001） and the complete remission group （3.60 ng/mL，

＝0.002）. In terms of ADR， the median blood concentration of tacrolimus in the ADR group was 5.01 ng/mL， which was significantly higher than that in the non-ADR group （3.37 ng/mL）（

＝0.001）. According to the subgroup analysis of the receiver operating characteristic curve， when the blood concentration of tacrolimus was ≥6.65 ng/mL， patients were more likely to develop elevated blood creatinine [area under the curve （AUC） was 0.764，

＜0.001）； when the blood concentration of tacrolimus was ≥6.55 ng/mL， patients were more likely to develop blood glucose （AUC＝0.615，

＝0.005）. The established MLP prediction model has a loss function of 0.9， with an average absolute error of 0.279 5 ng/mL between the predicted and measured values. The determination coefficient of the validation scatter plot was 0.984， indicating an excellent predictive performance of the model.

CONCLUSION

Tacrolimus blood concentration has an impact on both efficacy and ADR in NS patients. The use of the MLP model for predicting blood concentration exhibits high accuracy with minimal error between predicted and measured values. The model can be used as an important tool in clinical individualized medication regimens.

关键词

他克莫司肾病综合征血药浓度监测多层感知机预测模型个体化用药

Keywords

nephrotic syndromeblood concentration monitoringmultilayer perceptronprediction modelindivi- dualized medication

references

Kidney Disease：Improving Global Outcomes Glomerular Diseases Work Group. KDIGO 2021 clinical practice guideline for the management of glomerular diseases[J]. Kidney Int，2021，100（4S）：S1-S276.

李馥伶，林美钦，宋洪涛，等. 影响他克莫司体内药动学参数、临床疗效的因素[J]. 中国药房，2016，27（2）：279-282.

LI F L，LIN M Q，SONG H T，et al. Factors affecting pharmacokinetic parameters and clinical efficacy of tacrolimus in vivo[J]. China Pharm，2016，27（2）：279-282.

ZHENG P，YU Z，LI L R，et al. Predicting blood concentration of tacrolimus in patients with autoimmune diseases using machine learning techniques based on real-world evidence[J]. Front Pharmacol，2021，12：727245.

CHEN H X，CHENG Q，LI F，et al. Efficacy and safety of tacrolimus and low-dose prednisone in Chinese children with steroid-resistant nephrotic syndrome[J]. World J Pediatr，2020，16（2）：159-167.

POPESCU M C，BALAS V E，PERESCU-POPESCU L，et al. Multilayer perceptron and neural networks[J]. WSEAS Trans Circuits Syst，2009，8（7）：579-588.

LIANG T，SHEN J H，ZHANG S M，et al. Using ultrasound-based multilayer perceptron to differentiate early breast mucinous cancer and its subtypes from fibroadenoma[J]. Front Oncol，2021，11：724656.

AKTER S，DAS D，HAQUE R U，et al. AD-CovNet：an exploratory analysis using a hybrid deep learning model to handle data imbalance，predict fatality，and risk factors in Alzheimer’s patients with COVID-19[J]. Comput Biol Med，2022，146：105657.

WADA T，ISHIMOTO T，NAKAYA I，et al. A digest of the evidence-based clinical practice guideline for nephrotic syndrome 2020[J]. Clin Exp Nephrol，2021，25（12）：1277-1285.

中国成人肾病综合征免疫抑制治疗专家组. 中国成人肾病综合征免疫抑制治疗专家共识[J]. 中华肾脏病杂志，2014，30（6）：467-474.

Expert Group on Immunosuppressive Therapy for Adult Nephrotic Syndrome in China. Expert consensus on immunosuppressive therapy for adult nephrotic syndrome in China[J]. Chin J Nephrol，2014，30（6）：467-474.

LI M，XU M，LIU W，et al. Effect of CYP3A4，CYP3A5 and ABCB1 gene polymorphisms on the clinical efficacy of tacrolimus in the treatment of nephrotic syndrome[J]. BMC Pharmacol Toxicol，2018，19（1）：14.

LIAO M H，WANG M L，ZHU X，et al. Tacrolimus population pharmacokinetic model in adult Chinese patients with nephrotic syndrome and dosing regimen identification using Monte Carlo simulations[J]. Ther Drug Monit，2022，44（5）：615-624.

THÖLKING G，SCHÜTTE-NÜTGEN K，SCHMITZ J， et al. A low tacrolimus concentration/dose ratio increases the risk for the development of acute calcineurin inhibitor-induced nephrotoxicity[J]. J Clin Med，2019，8（10）：1586.

SONG J L，LI M，YAN L N，et al. Higher tacrolimus blood concentration is related to increased risk of post-transplantation diabetes mellitus after living donor liver transplantation[J]. Int J Surg，2018，51：17-23.

凌静，蒋艳，邹素兰，等. 肾病综合征患者他克莫司的群体药动学研究[J]. 中国现代应用药学，2020，37（24）：3019-3024.

LING J，JIANG Y，ZOU S L，et al. Population pharmacokinetics of tacrolimus in patients with nephrotic syndrome[J]. China Ind Econ，2020，37（24）：3019-3024.

HUANG Q B，LIN X B，WANG Y，et al. Tacrolimus pharmacokinetics in pediatric nephrotic syndrome：a combination of population pharmacokinetic modelling and machine learning approaches to improve individual prediction[J]. Front Pharmacol，2022，13：942129.

MO X L，CHEN X J，ZENG H S，et al. Tacrolimus in the treatment of childhood nephrotic syndrome：machine learning detects novel biomarkers and predicts efficacy[J]. Pharmacotherapy，2023，43（1）：43-52.

YUAN W J，SUI L，XIN H L，et al. Discussion on machine learning technology to predict tacrolimus blood concentration in patients with nephrotic syndrome and membranous nephropathy in real-world settings[J]. BMC Med Inform Decis Mak，2022，22（1）：336.

BRUNET M，VAN GELDER T，ÅSBERG A，et al. Therapeutic drug monitoring of tacrolimus-personalized therapy：second consensus report[J]. Ther Drug Monit，2019，41（3）：261-307.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Study on the correlation between opioid-induced constipation and gene polymorphism

Application of machine learning in the therapeutic drug monitoring and individual drug therapy

免疫抑制剂药效学监测的研究进展

我院再生障碍性贫血患者环孢素A血药浓度监测及其对疗效的影响

Related Author

ZHANG Xinyu

YANG Jing

ZHENG Lei

GUAN Yuyao

CHANG Wenlai

LIN Zhongkun

ZHANG Yahui

FU Zheng

Related Institution

Dept. of Pharmacy， Shandong Medical College

Dept. of Pharmacy， Shandong Provincial Third Hospital

School of Medical and Pharmaceutical Science， Ocean University of China

Dept. of Pharmacy， Shandong Provincial Hospital

Dept. of Pharmacy， the First Affiliated Hospital of Army Medical University

Address：8/F,129 Daping Main Street,Yuzhong District,Chongqing 400042,P.R.China
Technical support is provided by Beijing Founder Electronics co., LTD 渝ICP备15012710号公网安备50010302001817
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰