利用人工神经网络技术预测癫痫患儿服用卡马西平后体内药物浓度  

Prediction of plasma level of Carbamazepine in patients by artificial neural network

作　　者：邱枫[1] 何晓静[1] 肇丽梅[1] 孙亚欣[1] 

机构地区：[1]中国医科大学附属盛京医院药学部,辽宁沈阳110004

出　　处：《中国医学工程》2012年第6期18-19,21,共3页China Medical Engineering

摘　　要：目的利用人工神经网络技术预测癫痫患儿服用卡马西平后体内药物浓度。方法收集216例癫痫患儿服用卡马西平后血药浓度监测结果及监测当日身高、体量、肝肾功能等18项相关指标,根据神经网络和遗传算法的基本原理,建立卡马西平浓度预测模型,并用该浓度预测模型进行样本预测分析。结果样本(54个病例)的预测结果表明,与实际测定浓度相比,误差小于10%的有31个浓度,误差在10%-15%之间的有11个浓度,误差在15%-20%之间的有6个浓度,误差大于20%的有6个浓度。人工神经网络预测的血药浓度和实际测定浓度之间的相关系数为0.9156。结论利用人工神经网络技术预测癫痫患儿服用卡马西平后血药浓度比较可行,有待将其广泛应用于治疗个体化给药设计的研究。[ Objective ] Plasma levels of earhamazepine in patients were predicted by artificial neural network （ANN） simulator. [ Methods ] A data set of 18 physiologieal measurements for 216 patients was used to develop the model. Predictive model on plasma level of earbamazepine was based on neural network and genetic-algorithm. Then, samples were forecasted using the predictive model. [ Results ] Plasma levels of earbamazepine from 54 patients demonstrated that the deviations of 31 points were less than 10%, that of 11 points were between 10% and 15%, that of 6 points were between 15% and 20%, and that of 6 points exceed to 20%, compared with determination concentration. The correlation coefficients between determinated and predicted values obtained by ANN prediction using standardized data sets were 0.9156. [ Conclusion ] Prediction of plasma levels of carbamazepine in patients by ANN is feasible, it will be widely used in individualized dosage design.

关 键 词：人工神经网络 卡马西平 血药浓度 预测 

分 类 号：R742.1[医药卫生—神经病学与精神病学]