Recurrence quantification analysis on pulse morphological changes in patients with coronary heart disease.

OBJECTIVE To show that the pulse diagnosis used in Traditional Chinese Medicine, combined with nonlinear dynamic analysis, can help identify cardiovascular diseases. METHODS Recurrence quantification analysis (RQA) was used to study pulse morphological changes in 37 inpatients with coronary heart disease (CHD) and 37 normal subjects (controls). An independent sample t-test detected significant differences in RQA measures of their pulses. A support vector machine (SVM) classified the groups according to their RQA measures. Classic time-domain parameters were used for comparison. RESULTS RQA measures can be divided into two groups. One group of measures [ecurrence rate (RR), determinism (DEL), average diagonal line length (L), maximum length of diagonal structures (Lmax), Shannon entropy of the frequency distribution of diagonal line lengths (ENTR), laminarity (LAM), average length of vertical structures (TT), maximum length of vertical structures (Vmax)] showed significantly higher values for patients with CHD than for normal subjects (P < 0.05). The other measures (RR_std, L_std, Lmax_std, TT_std, Vmax_std) showed significantly lower values for the CHD group than for normal subjects (P < 0.05). SVM classification accuracy was higher with RQA measures: With RQA (16 parameters) accuracy was at 88.21%, and with RQA (12 parameters) accuracy was at 84.11%. In contrast, with classic time-domain (15 parameters) accuracy was 75.73%, and with time-domain (7 parameters) accuracy was 74.70%. CONCLUSION Nonlinear dynamic methods such as RQA can be used to study functional and structural changes in the pulse noninvasively. Pulse signals of individuals with CHD have greater regularity, determinism, and stability than normal subjects, and their pulse morphology displays less variability. RQA can distinguish the CHD pulse from the healthy pulse with an accuracy of 88.21%, thereby providing an early diagnosis of cardiovascular diseases such as CHD.

[1]  J. B. Gao,et al.  Detecting nonstationarity and state transitions in a time series. , 2001, Physical review. E, Statistical, nonlinear, and soft matter physics.

[2]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[3]  J. B. Gao,et al.  Recurrence Time Statistics for Chaotic Systems and Their Applications , 1999 .

[4]  L. Cao.  Practical method for determining the minimum embedding dimension of a scalar time series , 1997 .

[5]  Norbert Marwan,et al.  Extended Recurrence Plot Analysis and its Application to ERP Data , 2002, Int. J. Bifurc. Chaos.

[6]  D. Ruelle,et al.  Recurrence Plots of Dynamical Systems , 1987 .

[7]  Jianbo Gao,et al.  On the structures and quantification of recurrence plots , 2000 .

[8]  Sun Ren.  Application of the HHT & time domain method to the wrist-pulse-signal analysis in patients of coronary heart disease , 2008 .

[9]  C L Webber,et al.  Dynamical assessment of physiological systems and states using recurrence plot strategies. , 1994, Journal of applied physiology.

[10]  Jianbo Gao,et al.  Recurrence Time Statistics for Chaotic Systems and Their Applications , 1999 .

[11]  J. Ruan,et al.  Principal component cluster analysis of ECG time series based on Lyapunov exponent spectrum , 2004 .

[12]  Fraser,et al.  Independent coordinates for strange attractors from mutual information. , 1986, Physical review. A, General physics.

[13]  H. Abarbanel,et al.  Determining embedding dimension for phase-space reconstruction using a geometrical construction. , 1992, Physical review. A, Atomic, molecular, and optical physics.

[14]  J. Zbilut,et al.  Embeddings and delays as derived from quantification of recurrence plots , 1992 .

[15]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[16]  Max Q.-H. Meng,et al.  Morphology Variability Analysis of Wrist Pulse Waveform for Assessment of Arteriosclerosis Status , 2008, Journal of Medical Systems.

[17]  N. Marwan,et al.  Nonlinear analysis of bivariate data with cross recurrence plots , 2002, physics/0201061.