Heart Rate Analysis by Sparse Representation for Acute Pain Detection

Abstract

Objective pain assessment has not yet been achieved. Advanced signal processing methodologies, including the wavelet transform (WT) and the Orthogonal Matching Pursuit algorithm (OMP) were developed in the past two decades. The aim of this study was to apply and compare these time specific methods to heart rate samples of healthy subjects to investigate indicators of acute pain. Methods: 15 adult volunteers participated in a study conducted in the pain clinic at a single center. Each subject’s heart rate (HR) was sampled for 5 minutes baseline followed by a cold pressor test (CPT). Analysis was done by WT and OMP with a Fourier/ Wavelet dictionary separately. Results: Data of 11 subjects was analyzed. Compared to baseline, WT analysis showed a significant wavelet coefficients frequency (WCF) increase during the pain incline period (p<0.01) and the entire CPT (p<0.01), with significantly higher amplitudes. OMP analysis showed a significant WCF increase during pain incline and decline periods (p<0.01, p<0.05) and the entire CPT (p<0.001), with suggestive higher amplitudes. Comparing the methods, during the baseline period there was a significant reduction of WCF using OMP analysis (p<0.001). Analysis by the two way ANOVA with repeated measures showed a significant proportional increase of WCF during the incline period and the entire CPT using OMP (p<0.01). Conclusion: HR analysis by both methods has successfully indicated the painful event at its onset, without delay. Statistical analysis proved OMP to be by far more specific. This is an initial study using OMP for pain detection. Further studies need to prove the validity of this system for pain detection in different settings.