Search

Falls and mobility deficits are common in people with multiple sclerosis (PwMS) across all levels of clinical disability. However, functional mobility observed in supervised settings may not reflect daily life which may impact assessments of fall risk and impairment in the clinic. To investigate this further, we compared the utility of sensor-based performance metrics from sit-stand transitions during daily life and a structured task to inform fall risk and impairment in PwMS. Thirty-seven PwMS instrumented with wearable sensors (thigh and chest) completed supervised 30-second chair stand tests (30CST) and underwent two days of instrumented daily life monitoring. Performance metrics were computed for sit-stand transitions during daily life and 30CSTs. EDSS sub scores and fall history were used to dichotomize participants into groups: pyramidal/no pyramidal impairment, sensory/no sensory impairment and high/low fall risk. The ability of performance metrics to discriminate between groups was assessed using the area under the curve (AUC). The feature that best discriminated between high and low fall risk was a chest acceleration measurement from the supervised instrumented 30CST (AUC = 0.89). Only chest features indicated sensory impairment, however the task was different between supervised and daily life. The metric that best discriminated pyramidal impairment was a chest-derived feature (AUC = 0.89) from supervised 30CSTs. The highest AUC from daily life was observed in faller classification with the average sit-stand time (0.81). While characterizing sit-stand performance during daily life may yield insights into fall risk and may be performed without a clinic visit, there remains value to conducting supervised functional assessments to provide the best classification performance between the investigated impairments in this sample.

Impairment in persons with multiple sclerosis (PwMS) can often be attributed to symptoms of motor instability and fatigue. Symptom monitoring and queued interventions often target these symptoms. Clinical metrics are currently limited to objective physician assessments or subjective patient reported measures. Recent research has turned to wearables for improving the objectivity and temporal resolution of assessment. Our group has previously observed wearable assessment of supervised and unsupervised standing transitions to be predictive of fall-risk in PwMS. Here we extend the application of standing transition quantification to longitudinal home monitoring of symptoms. Subjects (N=23) with varying degrees of MS impairment were recruited and monitored with accelerometry for a total of ~6 weeks each. These data were processed using a deep learning activity classifier to isolate periods of standing transition from which descriptive features were extracted for analysis. Participants completed daily and biweekly assessments describing their symptoms. From these data, Canonical Correlation Analysis was used to derive digital phenotypes of MS instability and fatigue. We find these phenotypes capable of distinguishing fallers from non-fallers, and further that they demonstrate a capacity to characterize symptoms at both daily and sub-daily resolutions. These results represent promising support for future applications of wearables, which may soon augment or replace current metrics in longitudinal monitoring of PwMS.