JMIR Publications

ABSTRACT

Background:

Smartphones and wearables are revolutionizing assessment of cognitive and motor function in neurological disorders, allowing for objective, frequent, and remote data collection. These assessments, however, typically provide a plethora of sensor-derived measures (SDMs) and selecting the most suitable for a given context of use is a challenging, often overlooked, problem.

Objective:

Here, we develop and apply an SDM selection framework, including automated data quality checks and the evaluation of statistical properties, to identify robust SDMs that describe cognitive and motor function of people with multiple sclerosis (PwMS).

Methods:

The proposed framework was applied to data from a cross-sectional study involving 85 PwMS and 68 healthy subjects, who underwent in-clinic supervised and remote unsupervised smartphone-based assessments. The assessment provided high-quality recordings from cognitive, manual dexterity and mobility tests, from which 47 SDMs, based on established literature, were extracted using previously developed and publicly available algorithms. These SDMs were first separately and then jointly screened for bias and normality by two expert assessors. Selected SDMs were then analyzed to establish their reliability, using intraclass correlation coefficient and minimal detectable change at 95% confidence.

Results:

Sixteen (34%) of the SDMs passed the selection framework. All selected SDMs demonstrated moderate-to-good reliability in remote settings (intraclass correlation coefficient: 0.5-0.85 and minimal detectable change at 95% confidence: 19%-35%).

Conclusions:

Reported results highlight that smartphone-based assessments are suitable tools to remotely obtain high-quality SDMs of cognitive and motor function in PwMS. The presented SDM selection framework promises to increase interpretability and standardization of smartphone-based SDMs in PwMS, paving the way for their future use in interventional trials.