论文部分内容阅读
目的建立一个数学模型，对急性髓细胞白血病（AML）早期病死（ED）作出预测诊断。方法对193例AML各因素进行Logistic多元回归分析及判别分析，建立判别函数。结果Logistic多元回归分析表明，ED的危险因素包括体温、白细胞计数、血小板计数、骨髓增生度及白血病细胞类型等；据此建立的判别函数，总的判别符合率为86．5％，ED组及非ED组判别符合率分别为78．6％和88．7％。结论本判别函数判别符合率高，错判率低，具有一定的临床应用价值。
Objective To establish a mathematical model for predictive diagnosis of early death (ED) in acute myeloid leukemia (AML). Methods Logistic multiple regression analysis and discriminant analysis were performed on 193 AML factors to establish discriminant function. Results Logistic multiple regression analysis showed that the risk factors of ED included body temperature, white blood cell count, platelet count, myelodysplasia, and leukemia cell type. According to the established discriminant function, the total discriminant compliance rate was 86.5%. The non-ED group discrimination rate was 78.6% and 88.7%, respectively. Conclusion The discriminant function discriminates the high rate of concordance and the low misclassification rate. It has certain clinical application value.