基因表达式编程辅助诊断脂肪肝的新模型研究

Research on the new model for auxiliary diagnosis of fatty livers based on gene expression programming

目的利用人工计算模型建立起对脂肪肝的辅助诊断的新方法。方法基于对甘肃省某电厂196名职工的血糖、总胆固醇、低密度脂蛋白胆固醇、高密度脂蛋白胆固醇、甘油三酯的检测指标,采用基因表达式编程(GEP)方法对是否是脂肪肝的人群进行分类判别。结果 GEP方法获得的特异度和敏感度分别为99%和67%,准确率为95.92%。阳性预测值(PPV)为99.33%,阴性预测值(NPV)为96.13%。结论 GEP方法建立的诊断模型可用于脂肪肝的辅助诊断。

Objective To establish a new model for auxiliary diagnosis of fatty livers through gene expression programming.Methods The gene expression programming（GEP） was used to classify the population with fatty liver according to the test data of serum glucose,total cholesterol,low density lipoprotein cholesterol,high density lipoprotein cholesterol and triglyceride from 196 power plant workers.Results The percentages of specificity,sensitivity and accuracy of GEP were 99%,67% and 95.92% respectively,and the percentages of positive predictive value（PPV） and negative predictive value（NPV） were 99.33 and 96.13% respectively.Conclusions The new model can be used for diagnosis of fatty livers.