While there is growing interest in developing technology to support pain assessment, pain-related self-management, and healthcare personalisation, there are currently no datasets on nonverbal pain behaviour in the context of functional activities.To address this gap, we introduce the EmoPain(at)Home dataset which consists of motion capture data and self-reported pain, worry, and confidence intensities captured from people with chronic pain. The data were recorded during self-selected functional activities in the home, e.g. vacuuming. We include analysis of the dataset as well as baseline classification of pain levels with average F1 score of 0.61 for two classes. We additionally discuss inclusivity considerations for capture of datasets in naturalistic settings, based on lessons learnt within our study.

No abstract

<p>Chronic pain is a prevalent condition where fear of movement and pain interferes with everyday functioning. Yet, there is no open body movement dataset for people with chronic pain in everyday settings. Our EmoPain@Home dataset addresses this with capture from people with and without chronic pain in their homes, while they performed their routine activities. The data includes labels for pain, worry, and movement confidence continuously recorded for activity instances for the people with chronic pain. We explored two-level pain detection based on this dataset and obtained 0.62 mean F1 score. However, extension of the dataset led to deterioration in performance confirming high variability in pain expressions for real world settings. We investigated activity recognition for this setting as a first step in exploring the use of the activity label as contextual information for improving pain level classification performance. We obtained mean F1 score of 0.43 for 9 activity types, highlighting its feasibility. Further exploration, however, showed that data from healthy people cannot be easily leveraged for improving performance because worry and low confidence alter activity strategies for people with chronic pain. Our dataset and findings lay critical groundwork for automatic assessment of pain experience and behaviour in the wild. </p>

Single-session, brief interventions in therapy for young people make up a large proportion of service provision, including in digital mental health settings. Current nomothetic mental health measures are not specifically designed to capture the benefit or ‘change’ directly related to these brief interventions. As a consequence, we set out to design an outcome measure to concretely demonstrate the value of single-session interventions. The Session Wants and Needs Outcome Measure (SWAN-OM) aims to capture in-session goals and focuses on being user-centric, elements critical to the success of single-session and brief interventions which typically are asset-based and solution-focused. We describe the 4-stage process that was followed to develop this measure: (I) classical item generation and development, (II) content and (III) face validity pilot testing, and (IV) a user-experience approach with young people using framework analysis. This final stage was critical to ensure the integration of this outcome tool into a web-based digital therapy setting, a context which adds another layer of design complexity to item and measure development. This iterative methodology was used to overcome the challenges encountered and to place the needs of the young people and service practitioners at the centre of the design process, thus ensuring measure usability. To end, we highlight the main lessons learnt from engaging in this design process. Specifically, the needs of a measure for single-session interventions are considered, before outlining the learning associated with integrating the measure into a digital mental health platform. Both of these areas are emerging fields and, as such, this study contributes to our understanding of how an idiographic patient outcome theory driven measure can be created for use in a web-based digital mental health therapy service.

The EDUCAtional Technology Exchange programme (EDUCATE) at UCL Institute of Education provides the context for this paper, which describes the programme’s vision, objectives and key activities, and sets the context for the collection of articles that follow. This university-led programme was underpinned by Luckin’s (2016) golden triangle of evidence-informed educational technology (edtech) as it sought to support 252 small and medium-sized enterprises to become more research-informed through a six-month research training and mentoring programme. The evaluation of the programme’s design-based research cycles revealed the importance of the careful choice and evolution of its boundary objects. These boundary objects, namely each enterprise’s ‘logic model’ and research proposal, facilitated meaningful conversations between the programme’s research mentors and the enterprises. These boundary objects involved several iterations, during which the language of the two communities became more aligned, helping to bridge the academic knowledge and practices with those of the enterprises.