JMIR Publications

ABSTRACT

Background:

Facioscapulohumeral muscular dystrophy (FSHD) is a progressive muscle dystrophy disorder leading to significant disability impairing activities of daily living. Currently, FSHD symptom severity is assessed by clinical assessments such as for example the FSHD Clinical Score, the Timed Up and Go test (TUG), and Reachable Workspace (RWS) assessment. These assessments are limited in their ability to capture changes on a continuous basis and to capture the full impact of disease on patients’ quality of life. Real-world data related to physical activity, sleep and social behavior could potentially provide additional insight in the impact of the disease and might be useful in assessing treatment effects on aspects which are important contributors to FSHD patients’ functioning and wellbeing.

Objective:

This study investigated the feasibility of using smartphones and wearables to capture symptoms related to FSHD based on continuous collection of multiple features, such as number of steps, sleep, and app usage. We also tried to identify features that can be used to discriminate between FSHD patients and non FSHD-control subjects.

Methods:

In this exploratory non-interventional study, 38 FSHD patients and 20 non-FSHD control subjects were monitored using a smartphone monitoring application (CHDR MORE) for a duration of 6 weeks. At the first and last day of the study period, clinicians assessed the subjects’ FSHD Clinical Score and TUG time. Subjects installed the monitoring app on their Android smartphones, were given a Withings Steel HR smartwatch and were instructed to measure their weight and blood pressure on a weekly basis using the Withings Body+ scale and Withings Blood Pressure Monitor. The user experience and perceived burden of the app on subjects’ smartphones was assessed at 6 weeks using a questionnaire. With the data collected, we sought to 1) discriminate between FSHD and non-FSHD control subjects using logistic regression and 2) identify which of the behavioral features were most salient in distinguishing the two groups.

Results:

Overall, the subjects stated that the app was well tolerated, but 67% of subjects noticed a difference in battery life duration. Data completeness was about 80% for the app data and >83%, >80%, and >75%, for the watch, scale, and blood pressure monitor, respectively. We classified FSHD and non-FSHD control subjects with 93% accuracy, 100% sensitivity and 80% specificity. Features relating to smartphone acceleration, app usage, location, physical activity, sleep, and call behavior were the most salient features for the classification.

Conclusions:

Remote monitoring data collection allows for the collection of dense daily activity data in FSHD patients and control subjects for 6 weeks. We demonstrated the initial ability to detect differences in features in FSHD patients and non-FSHD control subjects using smartphones and wearables, mainly based on data related to physical and social activity. Clinical Trial: Toetsingonline: NL69288.056.19 https://www.toetsingonline.nl/to/ccmo_search.nsf/fABRpop?readform&unids=CEDAE53367050D04C12586AB001641E9