【作者】 王志刚； 赖丽娟； 吴效明； 熊冬生；

【Author】 Zhigang Wang Lijuan Lai Xiaoming Wu Dongsheng Xiong(Department of Biomedical Engineering,South China University of Technology,Guangzhou 510006,China)

【机构】 华南理工大学生物医学工程系；

【摘要】 ICU中,急性低血压发生的预见性判断主要依靠医生的经验。为了自动检测和预报急性低血压的发生,本文运用医学信息学理论,对发生与未发生急性低血压两者间平均动脉压信号进行小波多尺度分解,选取各层小波系数的统计特征中位数和最大值,用于支持向量机的分类预测器的学习和训练,建立分类预测模型,预测准确率达90%。实验结果表明,相对于直接提取患者平均动脉压信号的统计特征参数作为预测特征,本方法具有更好的预测效果,有利于实现急性低血压提前预测。更多还原

【Abstract】 In intensive care units(ICU),the prediction of acute hypotensive episodes(AHE) occurrence in advance is depended mainly on the doctors’ experience.To detect automatically and forecast the occurrence of AHE,the theory of medical Informatics has been applied to this paper.In our study,the mean arterial blood pressure(MAP) signals of those who experienced AHE and those who do not are both described on different scales by using wavelet transform.Through the extraction of the median and maximum from the wavelet coefficients for learning and training based on support vector machine(SVM),a predicting model with a predictive accuracy of 90% has developed.The experiment demonstrates that the proposed approach has better prediction accuracy comparing with the one which extracts statistical parameters from the MAP signals directly,and is beneficial to early prediction of AHE and intervention.更多还原