Thijs Swinnen

Accelerometry-Based Activity Recognition and Assessment in Rheumatic and Musculoskeletal Diseases

One of the important aspects to be considered in rheumatic and musculoskeletal diseases is the patient’s activity capacity (or performance), defined as the ability to perform a task. Currently, it is assessed by physicians or health professionals mainly by means of a patient-reported questionnaire, sometimes combined with the therapist’s judgment on performance-based tasks. This work introduces an approach to assess the activity capacity at home in a more objective, yet interpretable way. It offers a pilot study on 28 patients suffering from axial spondyloarthritis (axSpA) to demonstrate its efficacy. Firstly, a protocol is introduced to recognize a limited set of six transition activities in the home environment using a single accelerometer. To this end, a hierarchical classifier with the rejection of non-informative activity segments has been developed drawing on both direct pattern recognition and statistical signal features. Secondly, the recognized activities should be assessed, similarly to the scoring performed by patients themselves. This is achieved through the interval coded scoring (ICS) system, a novel method to extract an interpretable scoring system from data. The activity recognition reaches an average accuracy of 93.5%; assessment is currently 64.3% accurate. These results indicate the potential of the approach; a next step should be its validation in a larger patient study.

Instrumented BASFI (iBASFI) Shows Promising Reliability and Validity in the Assessment of Activity Limitations in Axial Spondyloarthritis

Objective. The Bath Ankylosing Spondylitis Functional Index (BASFI) is the most popular method to assess activity capacity in axial spondyloarthritis (axSpA), to our knowledge. It is endorsed by the Assessment of Spondyloarthritis international Society. But it may have recall bias or aberrant self-judgments in individual patients. Therefore, we aimed to (1) develop the instrumented BASFI (iBASFI) by adding a body-worn accelerometer with automated algorithms to performance-based measurements (PBM), (2) study the iBASFI’s core psychometric properties, and (3) reduce the number of iBASFI items. Methods. Twenty-eight patients with axSpA wore a 2-axial accelerometer while completing 12 PBM derived from the BASFI. A chronometer and both manual and “automated algorithm-based” acceleration segmentation identified movement time. Test-retest trials and methods (algorithm vs manual segmentation/chronometer/BASFI) were compared with ICC, standard error of measurement [percentage of movement time (SEM%)], and Spearman ρ correlation coefficients. Linear regression identified the optimal set of reliable iBASFI PBM. Results. Good to excellent test-retest reliability was found for 8/12 iBASFI items (ICC range 0.812–0.997, SEM range 0.4–30.4%), typically with repeated and fast movements. Automated algorithms excellently mimicked manual segmentation (ICC range 0.900–0.998) and the chronometer (ICC range 0.878–0.998) for 10/12 iBASFI items. Construct validity compared with the BASFI was confirmed for 7/12 iBASFI items (δ range 0.504–0.755). Together, sit-to-stand speed test (stBeta 0.483), cervical rotation (stBeta −0.392), and height (stBeta −0.375) explained 59% of the variance in the BASFI (p < 0.01). Conclusion. The proof-of-concept iBASFI showed promising reliability and validity in measuring activity capacity. The number of the iBASFI’s PBM may be minimized, but further validation in larger axSpA cohorts is needed before its clinical use.

Activity Limitations in Patients with Axial Spondyloarthritis: A Role for Fear of Movement and (Re)injury Beliefs

Objective. To determine whether fear of movement and (re)injury [FOM/(R)I] beliefs, measured with the Tampa Scale for Kinesiophobia 11-item version (TSK-11), influence activity limitations and mediate the relationship between pain severity and activity limitations in axial spondyloarthritis (axSpA). Methods. In 173 patients with axSpA, these data were collected: sex, body mass index, disease duration, medication, activity limitations (BASFI; Bath Ankylosing Spondylitis Functional Index), disease activity [Bath Ankylosing Spondylitis Disease Activity Index (BASDAI); BASDAIinf, items 5 and 6; BASDAIpain, items 2 and 3; C-reactive protein and physician’s global assessment], spinal mobility (BASMI; Bath Ankylosing Spondylitis Metrology Index), and FOM/(R)I (TSK-11). Scaling assumptions and reliability of TSK-11 were tested with item-to-total correlations, item variances, and Cronbach’s alpha coefficient. Hypothesis testing determined TSK-11’s construct validity. Multiple linear regression showed the contribution of TSK-11 to BASFI (enter and backward modeling). Mediation by TSK-11 was analyzed (bias-corrected bootstrapping and Sobel test). Results. Adequate scale (Cronbach’s alpha = 0.80) and item internal consistency (range item-scale correlations 0.41–0.58, except for item 5, r = 0.23), equal item-scale correlations, and item variances were found for TSK-11. Construct validity was confirmed, except for the hypothesized positive relationship between TSK-11 and BASMI. Regression models (enter method, adjusted R2 range 53–74%) consistently identified TSK-11 as a determinant of BASFI (β range 0.155 to 0.321, p < 0.05), although BASMI (β range 0.441 to 0.537) and disease activity (β range 0.243 to 0.571, p < 0.05) were the largest determinants. TSK-11 partially mediated the BASDAIpain/BASFI relationship (B = 0.107; Sobel test, p = 0.004; bias-corrected CI 0.046–0.197). Conclusion. TSK-11 is a promising and valid tool to assess fearful beliefs in relation to activity limitations in axSpA. Future research applying TSK-11 may reveal FOM/(R)I as a novel treatment target in axSpA.

Activity recognition for physical therapy: fusing signal processing features and movement patterns

This paper discusses the classification of activities in the context of physical therapy. Usually, specific standardized activities are subjectively assessed, often by means of a patient-reported questionnaire, to estimate a patients activity capacity, defined as the ability to execute a task. Automatic recognition of these activities is of vital importance for a more objective and quantitative approach to the problem. The proposed accelerometry-based algorithm merges standard signal processing features with information obtained from direct activity pattern matching using dynamic time warping (DTW) in a linear model. This study with 28 spondyloarthritis patients performing 10 activities shows the improvement in activity classification accuracy due to the fusion of the two approaches, up to 93.6%. This is a significant increase compared to similar models based on either of the approaches alone (p < 0.01). Although this paper mainly contributes to the activity recognition step, it also briefly discusses the advantages of the approach with regard to further automated evaluation of the recognized activities.

Turning tables: a structured focus group method to remediate unequal power during participatory design in health care

In a participatory design process, patients as well as care providers play a critical role in the design and development of healthcare apps. However, special attention should be given to problematic group dynamics that may arise from unequal power across participants. In this paper, we present Turning Tables, a focus group method, inspired by social interdependence theory (SIT), to mitigate asymmetric power. First, we present our SIT-inspired protocol for conducting focus groups. Next, via a qualitative analysis of 2 focus groups, we describe group dynamics and evaluate our method. Observations show that by splitting teams into patients versus care providers, and by specifying turn-taking (giving the floor to patients first), unequal power can be mitigated. However, observations also show that participants default back into their traditional roles during less formalized moments.

Recognition of Physical Activities from a Single Arm-Worn Accelerometer: A Multiway Approach

In current clinical practice, functional limitations due to chronic musculoskeletal diseases are still being assessed subjectively, e.g., using questionnaires and function scores. Performance-based methods, on the other hand, offer objective insights. Hence, they recently attracted more interest as an additional source of information. This work offers a step towards the shift to performance-based methods by recognizing standardized activities from continuous readings using a single accelerometer mounted on a patient’s arm. The proposed procedure consists of two steps. Firstly, activities are segmented, including rejection of non-informative segments. Secondly, the segments are associated to predefined activities using a multiway pattern matching approach based on higher order discriminant analysis (HODA). The two steps are combined into a multi-layered framework. Experiments on data recorded from 39 patients with spondyloarthritis show results with a classification accuracy of 94.34% when perfect segmentation is assumed. Automatic segmentation has 89.32% overlap with this ideal scenario. However, combining both drops performance to 62.34% due to several badly-recognized subjects. Still, these results are shown to significantly outperform a more traditional pattern matching approach. Overall, the work indicates promising viability of the technique to automate recognition and, through future work, assessment, of functional capacity.

Widespread pain in axial spondyloarthritis: clinical importance and gender differences

BackgroundThere is a remarkable lack of detailed knowledge on pain areas in axial spondyloarthritis (axSpA), and their clinical relevance is largely unknown. Pain area may reflect local disease processes, but amplification of nervous system signalling may alter this relationship. Also, gender differences in pain area may exist in axSpA, possibly confounding disease activity outcomes. Therefore, we firstly detailed pain locations in axSpA and evaluated gender differences. Secondly, we explored the relationship of regional pain definitions with clinical outcomes. Finally, we explored the role of pain area in the assessment of disease activity.MethodsBody charts informed on the presence of axial, peripheral articular and non-articular pain in 170 patients (108 men, 62 women) with axSpA. Multivariate Odds Ratios (ORs) were used to compare genders. General linear models were used to explore clinical differences in disease activity (Bath Ankylosing Spondylitis Disease Activity Index [BASDAI]), activity limitations (Bath Ankylosing Spondylitis Functional Index [BASFI]), fear of movement (Tampa Scale for Kinesiophobia 11-item version [TSK-11]), anxiety (Hospital Anxiety and Depression Scale subscale anxiety [HADS-A]) and depression (HADS subscale depression [HADS-D]) between four subgroups classified by widespread non-articular pain (WNAP+/−) and physician global assessment of disease activity (PGDA+/−) (p < .05). Principal Component Analysis (PCA) was performed to explore gender differences in the structure of disease activity.ResultsAxial thoracic pain was least prevalent (lumbar, 74.4%; cervical, 47.6%; cervicothoracic, 47.6%; thoracic, 32.4%), but it was about three times more likely in women (OR, 2.92; p = .009). Axial cervicothoracic junction pain spread more diffusely in women (OR, 2.48; p = .018). Women exhibited a two- to threefold increased likelihood of widespread axial (OR, 3.33; p = .007) and peripheral articular (OR, 2.34; p = .023) pain. A subgroup of WNAP+/PGDA− combined with low PGDA (27% of all patients) was associated with worse BASFI, BASDAI, HADS-A and HADS-D in men and worse TSK-11 and HADS-A in women (p < .05). Disease activity outcomes showed a two-factor structure in women but not in men.ConclusionsIn patients with axSpA, the location and spread of pain was different between genders and was related to worse clinical status. On the basis of pain area and PGDA, clinical subgroups exhibiting a remarkably distinct health status were identified. Outcome instruments such as BASDAI should acknowledge gender differences to ensure structural validity.