RESUMO
Introduction: It is unknown if physiological changes associated with chronic pain could be measured with inexpensive physiological sensors. Recently, acute pain and laboratory-induced pain have been quantified with physiological sensors. Objectives: To investigate the extent to which chronic pain can be quantified with physiological sensors. Methods: Data were collected from chronic pain sufferers who subjectively rated their pain on a 0 to 10 visual analogue scale, using our recently developed pain meter. Physiological variables, including pulse, temperature, and motion signals, were measured at head, neck, wrist, and finger with multiple sensors. To quantify pain, features were first extracted from 10-second windows. Linear models with recursive feature elimination were fit for each subject. A random forest regression model was used for pain score prediction for the population-level model. Results: Predictive performance was assessed using leave-one-recording-out cross-validation and nonparametric permutation testing. For individual-level models, 5 of 12 subjects yielded intraclass correlation coefficients between actual and predicted pain scores of 0.46 to 0.75. For the population-level model, the random forest method yielded an intraclass correlation coefficient of 0.58. Bland-Altman analysis shows that our model tends to overestimate the lower end of the pain scores and underestimate the higher end. Conclusion: This is the first demonstration that physiological data can be correlated with chronic pain, both for individuals and populations. Further research and more extensive data will be required to assess whether this approach could be used as a "chronic pain meter" to assess the level of chronic pain in patients.
RESUMO
Pulse rate variability is a physiological parameter that has been extensively studied and correlated with many physical ailments. However, the phase relationship between inter-beat interval, IBI, and breathing has very rarely been studied. Develop a technique by which the phase relationship between IBI and breathing can be accurately and efficiently extracted from photoplethysmography (PPG) data. A program based on Lock-in Amplifier technology was written in Python to implement a novel technique, Dynamic Phase Extraction. It was tested using a breath pacer and a PPG sensor on 6 subjects who followed a breath pacer at varied breathing rates. The data were then analyzed using both traditional methods and the novel technique (Dynamic Phase Extraction) utilizing a breath pacer. Pulse data was extracted using a PPG sensor. Dynamic Phase Extraction (DPE) gave the magnitudes of the variation in IBI associated with breathing [Formula: see text] measured with photoplethysmography during paced breathing (with premature ventricular contractions, abnormal arrhythmias, and other artifacts edited out). [Formula: see text] correlated well with two standard measures of pulse rate variability: the Standard Deviation of the inter-beat interval (SDNN) (ρ = 0.911) and with the integrated value of the Power Spectral Density between 0.04 and 0.15 Hz (Low Frequency Power or LF Power) (ρ = 0.885). These correlations were comparable to the correlation between the SDNN and the LF Power (ρ = 0.877). In addition to the magnitude [Formula: see text], Dynamic Phase Extraction also gave the phase between the breath pacer and the changes in the inter-beat interval (IBI) due to respiratory sinus arrythmia (RSA), and correlated well with the phase extracted using a Fourier transform (ρ = 0.857). Dynamic Phase Extraction can extract both the phase between the breath pacer and the changes in IBI due to the respiratory sinus arrhythmia component of pulse rate variability ([Formula: see text], but is limited by needing a breath pacer.