Prediction of Serum Concentration of Oxcarbazepine in Uygur Children with Epilepsy in Xinjiang Based on Artificial Neural Network
ZHAO Ting1, LI Hong-jian1, WENG Zhen-qun1, ZHANG Li-hua2, WANG Ting-ting1, FENG Jie1, SUN Li1, GUO Xi-hong1, YU Lu-hai1*
1. Department of Medicine, People's Hospital of Xinjiang Uygur Autonomous Region, Urumqi 830001, China; 2. College of Pharmacy, Jiangnan University, Wuxi 214000, China
Abstract：OBJECTIVE To predict the steady-state serum concentration of oxcarbazepine in Uygur children with epilepsy in Xinjiang by artificial neural network, thus to provide a theoretical basis for individualized administration of oxcarbazepine. METHODS The steady-state serum concentration of oxcarbazepine was measured in 270 Uygur children with epilepsy in the People's Hospital of Xinjiang Uygur Autonomous Region, and the relevant data was extracted. The prediction model of plasma concentration of oxcarbazepine was constructed by using Matlab (R2018a) programming software and deep learning network. RESULTS The network parameters of the model were as follows: the initial learning rate was 0.001, the final learning rate was 0.000 1, the momentum coefficient was 0.90, the maximum training times was 1 000, the genetic algebra was 6 000, and the other parameters were default values. The results of model verification showed that among the 45 Uygur children with epilepsy, the prediction errors of 45 oxcarbazepine serum trough concentrations were all less than 10%, and the rate of error of less than 15% was 100.00%. The mean prediction error(MPE) was 0.01% and the mean absolute prediction error(MAE) was 1.21%. The correlation coefficient between the predicted blood concentration and the actual determined concentration was 0.997, and the predicted result was ideal. CONCLUSION It is feasible to use artificial neural network to predict the serum concentration of oxcarbazepine in Uygur children with epilepsy in Xinjiang. It can be used in the study of individual administration of oxcarbazepine to promote the rational use of oxcarbazepine in clinic.
赵婷, 李红健, 翁振群, 章立华, 王婷婷, 冯杰, 孙力, 郭喜红, 于鲁海. 基于人工神经网络的新疆维吾尔族癫痫患儿奥卡西平血清浓度预测研究[J]. 中国药学杂志, 2020, 55(16): 1376-1380.
ZHAO Ting, LI Hong-jian, WENG Zhen-qun, ZHANG Li-hua, WANG Ting-ting, FENG Jie, SUN Li, GUO Xi-hong, YU Lu-hai. Prediction of Serum Concentration of Oxcarbazepine in Uygur Children with Epilepsy in Xinjiang Based on Artificial Neural Network. Chinese Pharmaceutical Journal, 2020, 55(16): 1376-1380.
KRASOWSKI M D. Therapeutic drug monitoring of the newer antiepilepsy medications. Pharmaceutical(Basel), 2010, 3(6):1909-1935.
[2]
YAO Y G, KONG Q P, WANG C Y, et al. Different matrilineal contributions to genetic structure of ethnic groups in the silk road region in China. Mol Biol Evol Dec, 2004, 21 (12): 2265-2280.
[3]
LIN Z Y, LIU H T, SHU Y, et al. Analysis of the Influencing Factors of the Plasma Concentration of Oxcarbazepine Active Metabolite in Children with Epilepsy . J Pediatr Pharm(儿科药学杂志), 2012,18(6):38-40.
[4]
GOREN S, KARAHOCA A, ONAT F Y, et al. Prediction of cyclosporine A blood levels: an application of the adaptive-network-based fuzzy inference system (ANFIS) in assisting drug therapy . Eur J Clin Pharmacol, 2008, 64(8):807-814.
[5]
KANG S H, POYNTON M R, KIM K M, et al. Population pharmacokinetic and pharmacodynamic models of remifen-tanil in healthy volunteers using artificial neural network analysis . Br J Clin Pharmacol, 2007, 64(1):3-13.
[6]
YAMAMURA S, KAWADA K, TAKEHIRA R, et al. Artificial neural network modeling to predict the plasma concentration of aminoglycosides in burn patients . Biomed Pharmacother, 2004, 58(4):239-244.
[7]
CHINESE MEDICAL ASSOCIATION. Clinical guidelines for diagnosis and treatment of epilepsy (临床诊疗指南癫痫病分册) . Beijing: People's Health Publishing House, 2015: 133-145.
[8]
NATIONAL PHARMACOPOEIA COMMITTEE. Notes on Clinical Drug use in Pharmacopoeia of the People's Republic of China Volume of Chemical Drugs and Biological Products(中华人民共和国药典临床用药须知化学药和生物制品卷) . Beijing: China Medical Science and Technology Press, 2010: 45-46.
[9]
REN B, HE Q Y, XU Q, et al. Prediction of mycophenolic acid exposure in renal transplantation recipients by artificial neural network . Acta Pharm Sin(药学学报), 2009, 44 (12):1397-1401. CHEN M. Refined Solution of the Principle and Example of MATLAB Neural Network(MATLAB神经网络原理与实例精解) . Beijing: Qinghua University Press, 2013:156-177. XU C H, AI Y S, CHEN H T. Prediction of plasma level of cyclosporine A in patients after kidney transplantation using neural networks . Chin J Hosp Pharm(中国医院药学杂志), 2008, 28(4):276-278. YANG J, JIAO Z, SHI X J. Study on Simultaneous Analysis of Six Antiepileptic Drugs and Two Active Metabolites in Human Plasma by HPLC . Chin Pharm J(中国药学杂志), 2006, 41(24):1899-1891. WANG Y H, WANG L. Advances in Therapeutic Drug Monitoring of New Antiepileptic Drugs . J Pediatr Pharm(儿科药学杂志), 2010, 16(3):51. QIU F, HE X J, ZHAO L M, et al. Prediction of drug concentration in children with epilepsy after taking carbamazepine by artificial neural network . China Medical Engineering(中国医学工程), 2012, 20(6):18-21. HUSSAIN A S, YU X, JOHNSON R D. Application of neural computing in pharmacyeutical product development . Pharm Res, 1991, 8(10):1248-1252. CORRIGAN B W, MAYO P R, JAMALI F. Application of a neural net work for gentami-cin concentration prediction in a general hospital population . Ther Drug Monit, 1997,19 (1) : 25-28. WU M L, ZHU Z Y, WANG K. Prediction of Serum valproic Acid concentration in Children with Epilepsy based on back Propagation Neural Network . Chin Pharm J(中国药学杂志),2012,47(10):766-770.
2020, Vol. 55 
