Page 131 - 《中国药房》2023年1期
P. 131
再次,机器学习对计算机知识背景要求较高,但目 2019,40(12):1603-1610.
前多数医务工作者对该领域了解不多,使得其应用受 [13] XUE L,ZHANG W W,DING X L,et al. Population phar‐
限;而拥有计算机知识背景的人员可能对医学知识不太 macokinetics and individualized dosage prediction of cy‐
了解,导致其所建模型和预测结果让临床人员难以理 closporine in allogeneic hematopoietic stem cell transplant
解。随着机器学习的快速发展,学科交叉的不断深入, patients[J]. Am J Med Sci,2014,348(6):448-454.
[14] CANDELA-BOIX M R,RAMÓN-LÓPEZ A,NALDA-
今后可推荐医务工作者接受机器学习相关训练,从而能
MOLINA R,et al. Population pharmacokinetics models of
更好地分析、整合信息并在机器学习的辅助下作出更为
sirolimus in renal transplant patients:a systematic review
科学的临床决策。
[J]. Farm Hosp,2021,45(7):77-83.
总之,基于治疗药物监测的个体化治疗是临床合理
[15] 傅晓华,洪晓丹,刘石带,等 . 人工神经网络模型在肾移
用药的重要环节,机器学习相比传统方法能够更精准地 植患者他克莫司个体化给药中的应用[J]. 中国药学杂
预测血药浓度和给药剂量,提高临床精准用药水平,减 志,2013,48(12):1000-1004.
少不良反应的发生。相信在未来的治疗药物监测和个 [16] 洪晓丹,李碧虹,罗美娟,等 . 肝移植受者他克莫司血药
体化用药实践中,机器学习将发挥更大的作用,实现个 浓度早期预测方案及评估[J].中国医院药学杂志,2013,
体化治疗决策的智能化。 33(5):381-385.
参考文献 [17] CHEN H Y,CHEN T C,MIN D I,et al. Prediction of ta‐
[ 1 ] DEO R C.Machine learning in medicine[J]. Circulation, crolimus blood levels by using the neural network with ge‐
2015,132(20):1920-1930. netic algorithm in liver transplantation patients[J]. Ther
[ 2 ] KOLLURI S,LIN J,LIU R,et al. Machine learning and Drug Monit,1999,21(1):50-56.
artificial intelligence in pharmaceutical research and de‐ [18] THISHYA K,VATTAM K K,NAUSHAD S M,et al. Arti‐
velopment:a review[J]. AAPS J,2022,24(1):19. ficial neural network model for predicting the bioavailabi-
[ 3 ] 刘雨安,杨小文,李乐之.机器学习在疾病预测的应用研 lity of tacrolimus in patients with renal transplantation[J].
究进展[J].护理学报,2021,28(7):30-34. PLoS One,2018,13(4):e0191921.
[ 4 ] 刘子暖,杨俊杰,陈韵岱.机器学习在冠状动脉计算机断 [19] CAI N,ZHANG X,ZHENG C,et al. A novel random fo-
层扫描领域的应用及进展[J].解放军医学杂志,2021,46 rest integrative approach based on endogenous CYP3A4
(3):286-293. phenotype for predicting tacrolimus concentrations and
[ 5 ] 张景奇,史文宝,纪秀娟.机器学习在医疗和公共卫生中 dosages in Chinese renal transplant patients[J]. J Clin
应用[J].中国公共卫生,2019,35(10):1449-1452. Pharm Ther,2020,45(2):318-323.
[ 6 ] VAMATHEVAN J,CLARK D,CZODROWSKI P,et al. [20] SEELING W,PLISCHKE M,DE BRUIN J S,et al.
Applications of machine learning in drug discovery and Knowledge-based immunosuppressive therapy for kidney
development[J]. Nat Rev Drug Discov,2019,18(6): transplant patients:from theoretical model to clinical inte‐
463-477. gration[J]. Stud Health Technol Inform,2015,216:1119.
[ 7 ] 韦炳华,叶毅芳,罗美娟,等 . 肝移植患者他克莫司个体 [21] TANG J,LIU R,ZHANG Y L,et al. Application of
化给药研究[J].中国临床药理学与治疗学,2012,17(7): machine-learning models to predict tacrolimus stable dose
791-796. in renal transplant recipients[J]. Sci Rep,2017,7:42192.
[ 8 ] 傅晓华,叶毅芳,罗美娟,等 . 人工神经网络预测肝移植 [22] WOILLARD J B,LABRIFFE M,DEBORD J,et al. Ta‐
术受者他克莫司血药浓度[J]. 药学学报,2012,47(9): crolimus exposure prediction using machine learning[J].
1134-1140. Clin Pharmacol Ther,2021,110(2):361-369.
[ 9 ] BADILLO S,BANFAI B,BIRZELE F,et al. An introduc‐ [23] WOILLARD J B,LABRIFFE M,PRÉMAUD A,et al. Es‐
tion to machine learning[J]. Clin Pharmacol Ther,2020, timation of drug exposure by machine learning based on
107(4):871-885. simulations from published pharmacokinetic models:the
[10] KOZA J R,BENNETT F H,ANDRE D,et al. Automated example of tacrolimus[J]. Pharmacol Res,2021,167:
design of both the topology and sizing of analog electrical 105578.
circuits using genetic programming[J]. Artif Intell Des, [24] 余俊先,史丽敏,李珊,等 . 肾移植受者的环孢素剂量预
1996:123-134. 测[J].中国医院药学杂志,2010,30(17):1451-1454.
[11] PUNCHOO R,BHOORA S,PILLAY N. Applications of [25] 余俊先,史丽敏,王汝龙,等.基于人工神经网络的环孢素A
machine learning in the chemical pathology laboratory[J]. 个体化给药设计[J].中国药学杂志,2010,45(12):927-930.
J Clin Pathol,2021,74(7):435-442. [26] 余俊先,夏杰,史丽敏,等 . 人工神经网络建立的环孢素
[12] LI T F,HU L,MA X L,et al. Population pharmacokine- A 血药浓度预测模型[J]. 中国药物应用与监测,2010,7
tics of cyclosporine in Chinese children receiving hemato‐ (1):52-55.
poietic stem cell transplantation[J]. Acta Pharmacol Sin, (下转第128页)
中国药房 2023年第34卷第1期 China Pharmacy 2023 Vol. 34 No. 1 · 121 ·