Giraldo Beatriz F, Rodriguez Javier, Caminal Pere, Bayes-Genis Antonio, Voss Andreas
Annu Int Conf IEEE Eng Med Biol Soc. 2015;2015:306-9. doi: 10.1109/EMBC.2015.7318361.
Cardiovascular diseases are the first cause of death in developed countries. Using electrocardiographic (ECG), blood pressure (BP) and respiratory flow signals, we obtained parameters for classifying cardiomyopathy patients. 42 patients with ischemic (ICM) and dilated (DCM) cardiomyopathies were studied. The left ventricular ejection fraction (LVEF) was used to stratify patients with low risk (LR: LVEF>35%, 14 patients) and high risk (HR: LVEF≤ 35%, 28 patients) of heart attack. RR, SBP and TTot time series were extracted from the ECG, BP and respiratory flow signals, respectively. The time series were transformed to a binary space and then analyzed using Joint Symbolic Dynamic with a word length of three, characterizing them by the probability of occurrence of the words. Extracted parameters were then reduced using correlation and statistical analysis. Principal component analysis and support vector machines methods were applied to characterize the cardiorespiratory and cardiovascular interactions in ICM and DCM cardiomyopathies, obtaining an accuracy of 85.7%.
心血管疾病是发达国家的首要死因。利用心电图（ECG）、血压（BP）和呼吸流量信号，我们获取了用于对心肌病患者进行分类的参数。对42例缺血性心肌病（ICM）和扩张型心肌病（DCM）患者进行了研究。左心室射血分数（LVEF）用于将心脏病发作低风险（LR：LVEF>35%，14例患者）和高风险（HR：LVEF≤35%，28例患者）的患者进行分层。RR、收缩压（SBP）和总时间（TTot）时间序列分别从ECG、BP和呼吸流量信号中提取。将时间序列转换为二元空间，然后使用字长为3的联合符号动力学进行分析，通过单词出现的概率对其进行表征。然后使用相关性和统计分析对提取的参数进行约简。应用主成分分析和支持向量机方法来表征ICM和DCM心肌病中的心肺和心血管相互作用，准确率达到85.7%。
