论文部分内容阅读
利用判别分析方法通过对测量的12个阿尔茨海默氏症(Alzheimer’s disease,AD)患者和12个健康者的尿液样本中儿茶酚胺(Catecholamines,CA)含量的测定及浓度作为训练集建立判别函数,进行疾病的诊断,交叉验证错误率为4.2%。采用随机余下的4个数据带入判别函数,进行预测,结果表明具有很好的预测能力,正确率达到了100%。此方法可以通过测量人体尿液中CA含量测定及浓度来诊断AD,对AD的尽早检测和早期治疗非常重要。2组线性判别函数分别为-19.91024+0.21873*E+0.23742*NE+0.11155*DOA+0.41789*L-DOPA-0.12661*DOPAC;-2.24864+0.03070*E+0.04914*NE+0 06892*DOA+0.01704*L-DOPA+0.01598*DOPAC。
Discriminant analysis was used to establish the discriminant function by measuring and measuring the content of Catecholamines (CA) in the urine of 12 patients with Alzheimer’s disease (AD) and 12 healthy subjects , The diagnosis of disease, cross-validation error rate of 4.2%. Using the remaining four random data into the discriminant function to predict, the results show that with good predictive ability, the correct rate reached 100%. This method can be measured by measuring the concentration of human urine CA content and to diagnose AD, AD early detection and early treatment is very important. The linear discriminant functions of the two groups were respectively -19.91024 + 0.21873 * E + 0.23742 * NE + 0.11155 * DOA + 0.41789 * L-DOPA- 0.12661 * DOPAC; -2.24864 + 0.03070 * E + 0.04914 * NE + 0 06892 * DOA + 0.01704 * L-DOPA + 0.01598 * DOPAC.