Abstract
Heart rate variability (HRV) analysis has quantified the functioning of the autonomic regulation of the heart and heart's ability to respond. However, majority of studies on HRV report several differences between patients with congestive heart failure (CHF) and healthy subjects, such as time-domain, frequency domain and nonlinear HRV measures. In the paper, we mainly presented a new approach to detect congestive heart failure (CHF) based on combination support vector machine (SVM) and three nonstandard heart rate variability (HRV) measures (e.g. SUM_TD, SUM_FD and SUM_IE). The CHF classification model was presented by using SVM classifier with the combination SUM_TD and SUM_FD. In the analysis performed, we found that the CHF classification algorithm could obtain the best performance with the CHF classification accuracy, sensitivity and specificity of 100%, 100%, 100%, respectively.
Highlights
Autonomic dysfunction is a typical feature of chronic heart failure and is associated with severity of disease and prognosis in chronic heart failure (CHF) [1]
We presented a congestive heart failure (CHF) patients’ classification algorithm based on three new nonstandard heart rate variability (HRV) measures and support vector machine (SVM)
We aim to investigate the CHF classification power from three nonstandard short-term HRV features (e.g. SUM_TD, SUM_FD and SUM_IE) based on SVM classifier
Summary
Autonomic dysfunction is a typical feature of chronic heart failure and is associated with severity of disease and prognosis in chronic heart failure (CHF) [1]. The significant difference of heart rate variability between patients with chronic heart failure and healthy people was widely reported in previous studies [2]. The heart rate variability (HRV) measures have been mainly studied for the prognosis of the disease, in particular, as predictor of the risk of mortality. The low-frequency spectral component LF (ranging between 0.03 and 0.15 Hz) decreased in CHF patients with advanced disease and was related to the progression of the heart failure [6]. Guzzetti et al (2000) suggested information content present in non-linear analysis of HRV in CHF patients has prognostic relevance independently from the time domain and spectral analysis of HRV [7]. Some guide evidences that HRV analysis shouldn’t form the primary basis for CHF assessment, because of its sensitivity and specificity
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
