How Can Affect Be Detected and Represented in Technological Support for Physical Rehabilitation?

Abstract

Although clinical best practice suggests that affect awareness could enable more effective technological support for physical rehabilitation through personalisation to psychological needs, designers need to consider what affective states matter, and how they should be tracked and addressed. In this article, we set the standard by analysing how the major affective factors in chronic pain (pain, fear/anxiety, and low/depressed mood) interfere with everyday physical functioning. Further, based on discussion of the modality that should be used to track these states to enable technology to address them, we investigated the possibility of using movement behaviour to automatically detect the states. Using two body movement datasets on people with chronic pain, we show that movement behaviour enables very good discrimination between two emotional distress levels (F1=0.86), and three pain levels (F1=0.9). Performance remained high (F1=0.78 for two pain levels) with a reduced set of movement sensors. Finally, in an overall discussion, we suggest how technology-provided encouragement and awareness can be personalised given the capability to automatically monitor the relevant states, towards addressing the barriers that they pose. In addition, we highlight movement behaviour features to be tracked to provide technology with information necessary for such personalisation.

Automatic Recognition of Multiple Affective States in Virtual Rehabilitation by Exploiting the Dependency Relationships

“…When music is used to generate emotions, some music pieces can induce mixed emotions of relaxed-calm-sad, but it is improbable that they elicit the emotions of surprise and quietness, or relaxed and angry at the same time [5]. In the health field, chronic pain patients exhibit protective behaviour during exercise in response to their anxiety, fear towards, and low confidence in such movements [16]. In addition, the work reported in [6] shows how the relationship between pain and protective behaviour is mediated by anxiety.…”

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

“…rigidity or stiffness in movement, use of support) [3] emerge from fear and low selfefficacy of/for the movements that are essential to these activities [4,5,33,34,36]. To address these underlying factors, physiotherapists adapt the type and amount of feedback and the forms of activities prescribed based on their observations of the strategies a patient uses during physical rehabilitation sessions in pain management programs [6,35]. As the rehabilitation is moving from clinical settings to home-based self-management, technology should be able to provide similar services by detecting these behaviors [35].…”

“…To address these underlying factors, physiotherapists adapt the type and amount of feedback and the forms of activities prescribed based on their observations of the strategies a patient uses during physical rehabilitation sessions in pain management programs [6,35]. As the rehabilitation is moving from clinical settings to home-based self-management, technology should be able to provide similar services by detecting these behaviors [35]. Wearable body sensing technology provides unique opportunities for physical rehabilitation in that: i) it can enable personalized, real-time feedbacks to be accessible to patients outside of clinical settings; and ii) it can be used ubiquitously as physical rehabilitation at home comprise unconstraint daily activities.…”

Learning Temporal and Bodily Attention in Protective Movement Behavior Detection

“…Second, we are keen to understand what such modality alone (without sEMG) can achieve using attention mechanisms with respect to the state of the art. Still, as previous studies [15] [33] have shown that sEMG data are critical for high performance, future work should explore the combination of the two types of data.…”

“…As discussed in [33] [35] [36], people suffering from CLBP tend to engage different body parts at different stages of the movement rather than in a synergetic way, despite the fact that such strategies make the movement more difficult to execute. This approach could be due to perceived higher control over the movement, and/or the fear of pain or injury, or reduced proprioception/coordination capabilities as discussed in [33] [38]. For example, let us analyze in more detail P14's darker (and so higher) temporal attention scores during stand-to-sit ( Fig.…”