论文部分内容阅读
胎心宫缩图(CTG)的计算机分析对确定胎儿状态具有重要意义,然而目前基于传统分类标准方法判断的效果不甚理想。为了提高胎儿状态评估准确率,提出了一种新的方法。新方法改进了分类标准,并使用模糊集合来表示CTG参数,从而用得到的集合形成一个特征向量来表示CTG信号,然后计算该信号特征向量与标准状态特征向量之间的欧氏距离,通过比较欧氏距离确定该信号所对应的胎儿状态。实验表明,新方法与专家一结果比较,准确率为88.3%,远高于传统方法的69.9%,而假阳性率仅为7.2%,远低于传统方法的34.9%;与专家二结果比较,准确率为90.3%,远高于传统方法的66.0%,而假阳性率仅为9.0%,远低于传统方法的38.2%。本研究表明新方法有效、可靠。
Computer analysis of Fetal Heart Contraction (CTG) is of great importance in determining the status of the fetus. However, the current judgment based on the traditional classification criteria is less than satisfactory. In order to improve the accuracy of fetal status assessment, a new method is proposed. The new method improves the classification standard, and uses the fuzzy set to express the CTG parameters, so as to form a feature vector to represent the CTG signal by using the set, and then calculates the Euclidean distance between the signal feature vector and the standard state feature vector. By comparing Euclidean distance to determine the signal corresponding to the fetal state. Experiments show that the accuracy of the new method is 88.3% compared with that of the expert, which is much higher than the 69.9% of the traditional method, while the false positive rate is only 7.2%, much lower than the 34.9% of the traditional method. The accuracy rate was 90.3%, much higher than the 66.0% of the traditional method, while the false positive rate was only 9.0%, much lower than the traditional method of 38.2%. This study shows that the new method is effective and reliable.