Page 138 - 《中国药房》2025年1期

[22] ZHANG H Y，BU F J，LI L，et al. Prediction of drug-drug neic hematopoietic stem cell transplantation in children
interaction between tacrolimus and principal ingredients with β-thalassemia major[J]. Pharmgenomics Pers Med，
of Wuzhi capsule in Chinese healthy volunteers using 2021，14：1221-1237.
physiologically-based pharmacokinetic modelling[J]. Ba‐ [33] BARTELINK I H，RADEMAKER C M，SCHOBBEN A F，
sic Clin Pharmacol Toxicol，2018，122（3）：331-340. et al. Guidelines on paediatric dosing on the basis of deve-
[23] GREENER J G，KANDATHIL S M，MOFFAT L，et al. A lopmental physiology and pharmacokinetic considerations
guide to machine learning for biologists[J]. Nat Rev Mol [J]. Clin Pharmacokinet，2006，45（11）：1077-1097.
Cell Biol，2022，23（1）：40-55. [34] 焦正，李新刚，尚德为，等. 模型引导的精准用药：中国专
[24] LEE S，SONG M，HAN J，et al. Application of machine 家共识：2021 版[J]. 中国临床药理学与治疗学，2021，26
learning classification to improve the performance of van‐ （11）：1215-1228.
comycin therapeutic drug monitoring[J]. Pharmaceutics， JIAO Z，LI X G，SHANG D W，et al. Model informed pre‐
2022，14（5）：1023. cision dosing：China expert consensus report：2021 edition
[25] FU Q，JING Y，LIU MR G，et al. Machine learning-based [J]. Chin J Clin Pharmacol Ther，2021，26（11）：1215-
method for tacrolimus dose predictions in Chinese kidney 1228.
transplant perioperative patients[J]. J Clin Pharm Ther， [35] DEL VALLE-MORENO P，SUAREZ-CASILLAS P，
2022，47（5）：600-608. MEJÍAS-TRUEBA M，et al. Model-informed precision
[26] WOILLARD J B，LABRIFFE M，DEBORD J，et al. Ta‐ dosing software tools for dosage regimen individualiza‐
crolimus exposure prediction using machine learning[J]. tion：a scoping review[J]. Pharmaceutics，2023，15（7）：
Clin Pharmacol Ther，2021，110（2）：361-369. 1859.
[27] SONG X W，LIU F H，GAO H E，et al. Compare the per‐ [36] KANTASIRIPITAK W，VAN DAELE R，GIJSEN M，
formance of multiple machine learning models in predic- et al. Software tools for model-informed precision dosing：
ting tacrolimus concentration for infant patients with how well do they satisfy the needs?[J]. Front Pharmacol，
living donor liver transplantation[J]. Pediatr Transplant， 2020，11：620.
2023，27（1）：e14379. [37] TAYLOR Z L，POWELEIT E A，PAICE K，et al. Tutorial
[28] LIN Z M，CHOU W C. Machine learning and artificial in‐ on model selection and validation of model input into
telligence in toxicological sciences[J]. Toxicol Sci，2022， precision dosing software for model-informed precision
189（1）：7-19. dosing[J]. CPT Pharmacometrics Syst Pharmacol，2023，
[29] KRZYWINSKI M，ALTMAN N. Multiple linear regres‐ 12（12）：1827-1845.
sion[J]. Nat Methods，2015，12（12）：1103-1104. [38] EL-KHATEEB E，BURKHILL S，MURBY S，et al.
[30] KANAMITSU K，YORIFUJI T，ISHIDA H，et al. Clinical Physiological-based pharmacokinetic modeling trends in
factors affecting the dose conversion ratio from intrave‐ pharmaceutical drug development over the last 20-years；
nous to oral tacrolimus formulation among pediatric hema‐ in-depth analysis of applications，organizations，and plat‐
topoietic stem cell transplantation recipients[J]. Ther Drug forms[J]. Biopharm Drug Dispos，2021，42（4）：107-117.
Monit，2020，42（6）：803-810. [39] CHOU W C，LIN Z M. Machine learning and artificial
[31] 陈铭，许静，陈峰，等. 基因多态性对难治性肾病综合征 intelligence in physiologically based pharmacokinetic
患儿他克莫司血药浓度及其肾毒性的影响[J]. 安徽医 modeling[J]. Toxicol Sci，2023，191（1）：1-14.
学，2023，44（1）：82-87. [40] LI Z R，LI R D，NIU W J，et al. Population pharmacoki‐
CHEN M，XU J，CHEN F，et al. Effect of gene polymor‐ netic modeling combined with machine learning approach
phism on blood concentration and nephrotoxicity of tacro‐ improved tacrolimus trough concentration prediction in
limus in children with refractory nephrotic syndrome[J]. Chinese adult liver transplant recipients[J]. J Clin Pharma‐
Anhui Med J，2023，44（1）：82-87. col，2023，63（3）：314-325.
[32] LI C X，LU J J，ZHOU S R，et al. Influential factors and （收稿日期：2024-04-27 修回日期：2024-12-17）
efficacy analysis of tacrolimus concentration after alloge‐ （编辑：胡晓霖）

· 128 · China Pharmacy 2025 Vol. 36 No. 1 中国药房 2025年第36卷第1期