Recurrence Quantification Analysis of Wrist Pulse Signals to Distinguish Diabetic and Non-diabetic Subjects

In ancient system of medicine pulse play a major role in the diagnosis of certain diseases. In the pulse
diagnosis, the practitioner feels the pulse of the subject by placing his fingers on the subject’s wrist at
distinct radial pulse point locations. The preliminary studies confirm that the wrist pulse signals were
analyzed using various conventional linear techniques and very less focus on non-linear techniques.
Hence, the main focus of this paper is to apply Recurrence Plot and Recurrence Quantification
Analysis (RQA), a nonlinear technique to analyze the wrist pulse signals for distinguishing between
diabetic and non-diabetic subjects. The wrist pulse signals were acquired from the subjects during the
morning hours and were analyzed using RQA techniques. It is seen that there is a significant
difference in the RQA parameters of the wrist pulse signals since these parameters are associated
with the recurrences occurring in the phase space plots of the wrist pulse signals. The results show
that there is a positive correlation between the positions of wrist pulse signal for each of the RQA
parameters applied. It was found that recurrence parameters like entropy, divergence and diagonal
line length showed significant variations with p<0.001 for diabetic and non-diabetic subjects.
Therefore, it can be concluded that RQA parameters can be used as an effective technique to identify
diabetic and non-diabetic subjects and thus may be applied on the wrist pulse signals for early
detection of various diseases.