应用火焰原子吸收法（ Ｆ Ａ Ａ Ｓ） 和石墨炉原子吸收法（ Ｇ Ｆ Ａ Ａ Ｓ） 测定了脑栓塞患者和对照组（ 健康人） 血清中 Ｚｎ 、 Ｃｕ 、 Ｆｅ 、 Ｃａ 、 Ｍｇ 、 Ｃｒ、 Ｍｎ 和 Ｓｒ 等的含量。对所得数据用反向传播神经网络（ Ｂ Ｐ法） 进行分析， 建立了脑栓塞的神经网络识别系统， 预报识别率达１００ ％ ， 可作为该病诊断的一种有效的辅助手段 The serum levels of Zn, Cu, Fe, Ca, Mg, Cr, Cr and Cr in brain tissue of patients with cerebral embolism and healthy controls were measured by flame atomic absorption spectrometry (FAAS) and graphite furnace atomic absorption spectrometry Mn and Sr and the like. The data were analyzed by backpropagation neural network (B-P method), and a neural network identification system of cerebral embolism was established with a prediction rate of 100%, which can be used as an effective aid in the diagnosis of the disease