Feasibility and scalability of a fitness tracker study: Results from a longitudinal analysis of persons with multiple sclerosis

MS Pattern Explorer: interactive visual exploration of temporal activity patterns for multiple sclerosis

OBJECTIVES

This article describes the design and evaluation of MS Pattern Explorer, a novel visual tool that uses interactive machine learning to analyze fitness wearables' data. Applied to a clinical study of multiple sclerosis (MS) patients, the tool addresses key challenges: managing activity signals, accelerating insight generation, and rapidly contextualizing identified patterns. By analyzing sensor measurements, it aims to enhance understanding of MS symptomatology and improve the broader problem of clinical exploratory sensor data analysis.

MATERIALS AND METHODS

Following a user-centered design approach, we learned that clinicians have 3 priorities for generating insights for the Barka-MS study data: exploration and search for, and contextualization of, sequences and patterns in patient sleep and activity. We compute meaningful sequences for patients using clustering and proximity search, displaying these with an interactive visual interface composed of coordinated views. Our evaluation posed both closed and open-ended tasks to participants, utilizing a scoring system to gauge the tool's usability, and effectiveness in supporting insight generation across 15 clinicians, data scientists, and non-experts.

RESULTS AND DISCUSSION

We present MS Pattern Explorer, a visual analytics system that helps clinicians better address complex data-centric challenges by facilitating the understanding of activity patterns. It enables innovative analysis that leads to rapid insight generation and contextualization of temporal activity data, both within and between patients of a cohort. Our evaluation results indicate consistent performance across participant groups and effective support for insight generation in MS patient fitness tracker data. Our implementation offers broad applicability in clinical research, allowing for potential expansion into cohort-wide comparisons or studies of other chronic conditions.

CONCLUSION

MS Pattern Explorer successfully reduces the signal overload clinicians currently experience with activity data, introducing novel opportunities for data exploration, sense-making, and hypothesis generation.

From wearable sensor data to digital biomarker development: ten lessons learned and a framework proposal

Wearable sensor technologies are becoming increasingly relevant in health research, particularly in the context of chronic disease management. They generate real-time health data that can be translated into digital biomarkers, which can provide insights into our health and well-being. Scientific methods to collect, interpret, analyze, and translate health data from wearables to digital biomarkers vary, and systematic approaches to guide these processes are currently lacking. This paper is based on an observational, longitudinal cohort study, BarKA-MS, which collected wearable sensor data on the physical rehabilitation of people living with multiple sclerosis (MS). Based on our experience with BarKA-MS, we provide and discuss ten lessons we learned in relation to digital biomarker development across key study phases. We then summarize these lessons into a guiding framework (DACIA) that aims to informs the use of wearable sensor data for digital biomarker development and chronic disease management for future research and teaching.

Exploring the Major Barriers to Physical Activity in Persons With Multiple Sclerosis: Observational Longitudinal Study

BACKGROUND

Physical activity (PA) represents a low-cost and readily available means of mitigating multiple sclerosis (MS) symptoms and alleviating the disease course. Nevertheless, persons with MS engage in lower levels of PA than the general population.

OBJECTIVE

This study aims to enhance the understanding of the barriers to PA engagement in persons with MS and to evaluate the applicability of the Barriers to Health Promoting Activities for Disabled Persons (BHADP) scale for assessing barriers to PA in persons with MS, by comparing the BHADP score with self-reported outcomes of fatigue, depression, self-efficacy, and health-related quality of life, as well as sensor-measured PA.

METHODS

Study participants (n=45; median age 46, IQR 40-51 years; median Expanded Disability Status Scale score 4.5, IQR 3.5-6) were recruited among persons with MS attending inpatient neurorehabilitation. They wore a Fitbit Inspire HR (Fitbit Inc) throughout their stay at the rehabilitation clinic (phase 1; 2-4 wk) and for the 4 following weeks at home (phase 2; 4 wk). Sensor-based step counts and cumulative minutes in moderate to vigorous PA were computed for the last 7 days at the clinic and at home. On the basis of PA during the last 7 end-of-study days, we grouped the study participants as active (≥10,000 steps/d) and less active (<10,000 steps/d) to explore PA barriers compared with PA level. PA barriers were repeatedly assessed through the BHADP scale. We described the relevance of the 18 barriers of the BHADP scale assessed at the end of the study and quantified their correlations with the Spearman correlation test. We evaluated the associations of the BHADP score with end-of-study reported outcomes of fatigue, depression, self-efficacy, and health-related quality of life with multivariable regression models. We performed separate regression analyses to examine the association of the BHADP score with different sensor-measured outcomes of PA.

RESULTS

The less active group reported higher scores for the BHADP items Feeling what I do doesn't help, No one to help me, and Lack of support from family/friends. The BHADP items Not interested in PA and Impairment were positively correlated. The BHADP score was positively associated with measures of fatigue and depression and negatively associated with self-efficacy and health-related quality of life. The BHADP score showed an inverse relationship with the level of PA measured but not when dichotomized according to the recommended PA level thresholds.

CONCLUSIONS

The BHADP scale is a valid and well-adapted tool for persons with MS because it reflects common MS symptoms such as fatigue and depression, as well as self-efficacy and health-related quality of life. Moreover, decreases in PA levels are often related to increases in specific barriers in the lives of persons with MS and should hence be addressed jointly in health care management.

Implementation of Remote Activity Sensing to Support a Rehabilitation Aftercare Program: Observational Mixed Methods Study With Patients and Health Care Professionals

BACKGROUND

Physical activity is central to maintaining the quality of life for patients with complex chronic conditions and is thus at the core of neurorehabilitation. However, maintaining activity improvements in daily life is challenging. The novel Stay With It program aims to promote physical activity after neurorehabilitation by cultivating self-monitoring skills and habits.

OBJECTIVE

We examined the implementation of the Stay With It program at the Valens Rehabilitation Centre in Switzerland using the normalization process theory framework, focusing on 3 research aims. We aimed to examine the challenges and facilitators of program implementation from the perspectives of patients and health care professionals. We aimed to evaluate the potential of activity sensors to support program implementation and patient acceptance. Finally, we aimed to evaluate patients' engagement in physical activity after rehabilitation, patients' self-reported achievement of home activity goals, and factors influencing physical activity.

METHODS

Patients were enrolled if they had a disease that was either chronic or at risk for chronicity and participated in the Stay With It program. Patients were assessed at baseline, the end of rehabilitation, and a 3-month follow-up. The health care professionals designated to deliver the program were surveyed before and after program implementation. We used a mixed methods approach combining standardized questionnaires, activity-sensing data (patients only), and free-text questions.

RESULTS

This study included 23 patients and 13 health care professionals. The diverse needs of patients and organizational hurdles were major challenges to program implementation. Patients' intrinsic motivation and health care professionals' commitment to refining the program emerged as key facilitators. Both groups recognized the value of activity sensors in supporting program implementation and sustainability. Although patients appreciated the sensor's ability to monitor, motivate, and quantify activity, health care professionals saw the sensor as a motivational tool but expressed concerns about technical difficulties and potential inaccuracies. Physical activity levels after patients returned home varied considerably, both within and between individuals. The self-reported achievement of activity goals at home also varied, in part because of vague definitions. Common barriers to maintaining activity at home were declining health and fatigue often resulting from heat and pain. At the 3-month follow-up, 35% (8/23) of the patients withdrew from the study, with most citing deteriorating physical health as the reason and that monitoring and discussing their low activity would negatively affect their mental health.

CONCLUSIONS

Integrating aftercare programs like Stay With It into routine care is vital for maintaining physical activity postrehabilitation. Although activity trackers show promise in promoting motivation through monitoring, they may lead to frustration during health declines. Their acceptability may also be influenced by an individual's health status, habits, and technical skills. Our study highlights the importance of considering health care professionals' perspectives when integrating new interventions into routine care.