Key result
The novel ICBN method for heart rate variability measurement achieved an 89.66% recognition accuracy for congestive heart failure and 91.86% for atrial fibrillation.
Why the study?
Does the novel ICBN method accurately classify congestive heart failure and atrial fibrillation based on heart rate variability?
Observational (n=144)
Does the novel ICBN method accurately classify congestive heart failure and atrial fibrillation based on heart rate variability?
Effect estimate: 89.66% accuracy for CHF; 91.86% accuracy for AF
The proposed ICBN method for heart rate variability measurement achieves high accuracy in classifying congestive heart failure and atrial fibrillation.
Novel HRV entropy metric is hypothesis-generating; requires prospective validation before any clinical consideration.
The complex fluctuation of heart rate variability reflects the autonomous regulation function of the heart. In this paper, a novel method of measuring the heart rate variability is proposed. Firstly, the heart rate variability signal is decomposed by the improved complete ensemble empirical mode decomposition with adaptive noise method, and the multiple intrinsic mode functions are obtained, and the bubble entropy of each intrinsic mode function is calculated to obtain an entropy value vector. Then, the vector is mapped to a network based on a limited penetrable horizontal visibility graph method. By calculating various characteristic parameters of the network, the coupling relationship between the nonlinear features of heart rate variability in different time-frequency scale states are studied. The characteristic parameters include mean value of aggregation coefficient (MC), the characteristic path length (CL), the topological entropy of network (TE), the network level weighted bubble value (WB), and the pseudo mean value of node weight (PW). Firstly, the heart rate variabilities of 29 patients with congestive heart failure and 29 normal sinus heart rhythm subjects are analyzed by time domain, frequency domain and ICBN analysis method, the T test is used for statistical analysis, and Fisher discriminant method is used for classification. The results show that the time domain triangular index HRVTI, frequency domain index LF/HF, WB, PW and CL in ICBN have statistical differences. The accuracy rate of recognition model based on WB, CL, frequency domain index LF/HF and Fisher discriminant method is 89.66%. Secondly, the heart rate variabilities of 43 patients with atrial fibrillation arrhythmia and another 43 normal sinus heart rhythm subjects are analyzed by the same methods, including the time domain analyzed method, frequency domain analyzed method, and ICBN analyzed method. Then, the T test is also used for statistical analysis, and Fisher discriminant method is used for classification. The results show that using the time domain index pNN5 and RMSSD, frequency index LF/HF, ICBN index WB and PW as the feature vectors, and the Fisher discriminant mode as the classifier, the accuracy rate of recognition for atrial fibrillation arrhythmia is 91.86%. From these results it is concluded that the ICBN method provides a new idea for the heart rate variability measurement.
No takes yet. Share an insight, caveat, or question.
Shao et al. (2019) conducted an observational in Congestive heart failure and Atrial fibrillation (n=144). ICBN method (HRV measurement) vs. Traditional time and frequency domain HRV analysis was evaluated on Classification accuracy for congestive heart failure and atrial fibrillation (89.66% accuracy for CHF; 91.86% accuracy for AF). The novel ICBN method for heart rate variability measurement achieved an 89.66% recognition accuracy for congestive heart failure and 91.86% for atrial fibrillation.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: