Human Observer and Automatic Assessment of Movement Related Self-Efficacy in Chronic Pain: From Exercise to Functional Activity

Abstract

Abstract-Clinicians tailor intervention in chronic pain rehabilitation to movement related self-efficacy (MRSE). This motivates us to investigate automatic MRSE estimation in this context towards the development of technology that is able to provide appropriate support in the absence of a clinician. We first explored clinical observer estimation, which showed that body movement behaviours, rather than facial expressions or engagement behaviours, were more pertinent to MRSE estimation during physical activity instances. Based on our findings, we built a system that estimates MRSE from bodily expressions and bodily muscle activity captured using wearable sensors. Our results (F1 scores of 0.95 and 0.78 in two physical exercise types) provide evidence of the feasibility of automatic MRSE estimation to support chronic pain physical rehabilitation. We further explored automatic estimation of MRSE with a reduced set of low-cost sensors to investigate the possibility of embedding such capabilities in ubiquitous wearable devices to support functional activity. Our evaluation for both exercise and functional activity resulted in F1 score of 0.79. This result suggests the possibility of (and calls for more studies on) MRSE estimation during everyday functioning in ubiquitous settings. We provide a discussion of the implication of our findings for relevant areas.

Recurrent network based automatic detection of chronic pain protective behavior using MoCap and sEMG data

“…The majority of the work done on automatic detection of pain behavior (including protective behavior) has been on automatic differentiation of people with CP from healthy control participants, as in the studies of [13,14,15] on lower back and neck CP. Protective behavior is also seen as a cue of low selfefficacy, and [11] proposed to use feature-engineering methods to characterize it. [9,10,35] further provides evidence that lowcost body sensing technology can enable the detection of pain related experiences in functional activities.…”

Automatic Detection of Reflective Thinking in Mathematical Problem Solving Based on Unconstrained Bodily Exploration

“…Thus, two of our researchers (R1 and R2) with experience working with children and also present during the data collection (and so familiar with the tasks given to the children) independently labelled the data. The raters continuously rated all 120 videos recorded (without audio, to force them to rely on visual cues, similar to [22]), using the Elan annotation software [23] [24]. The raters specifically marked periods of reflective thinking within these videos.…”

“…Further, Support Vector Machine (SVM) [36] and Random Forest (RF) [37] are established as efficacious algorithms for movement-based affect detection (e.g. in [22], [25]). We explored polynomial and gaussian kernels for the SVM in our work.…”

“…Our analysis of these behaviours contributes to the oeuvre of bodily action coding taxonomy amassed over a wealth of behaviour analysis literature (e.g. [22]).…”

Analysis of cognitive states during bodily exploration of mathematical concepts in visually impaired children

“…Computational approaches of confidence level are more rare. Most frequently researchers focused similar topics such as on leadership detection in multi-user scenarios, e.g., social games [4], and self-efficacy in physical rehabilitation [35]. We are not unaware, at this stage, of any existing model for the recognition of confidence level from full body cues in context of single-user task in education (for physical rehabilitation context, see [35]).…”