---

作 者 ：麦其鹏,李续娥,吴艳华,周诚

期 刊 ：中国中药杂志 2010年 35卷 24期 页码：3371.

关键词：中药复方；抗衰老药效；性味归经；BP神经网络；

Keywords:Chinese prescription medicine, anti-aging, four natures, five flavors, meridian tropism, BP neural network,

摘 要 ：目的: 建立科学、快速的抗衰老药效预测模型。 方法 :根据中药复方的组方原则,运用人工神经网络的理论和方法,建立中药抗衰老药效与其性味归经之间关系的BP神经网络模型,通过实例对抗衰老指标进行评价分析。 结果 :模型预测复方的抗衰老指标超氧化物歧化酶(SOD)、丙二醛(MDA)、谷胱甘肽过氧化物酶(GSH-PX)的准确率为93.33%。 结论 :模型能很好地预测复方的抗衰老药效。

Abstract:Objective : To establish a scientific, rapid anti-aging prediction model. Method : According to the institutional principle of Chinese prescription medicine and by using the theory and method of artificial neural network, a BP model was built up to cope with the relation between anti-aging and four natures, five flavors as well as meridian tropism of Chinese medicinal herbs. Result : The accuracy that the model predicted the prescription‘s anti-aging index of superoxide dismutase (SOD), malondialdehyde(MDA), glutathione peroxidase (GSH-PX) was 93.33%. Conclusion : The model can predict the efficacy of anti-aging prescription very well.

---