Back

Wearable technologies for children with chronic illness: A Proof-of-Concept Study

McErlane, F.; Davies, E. H.; ollivier, c.; Mayhew, A.; Anyanwu, O.; Harbottle, V.; Donald, A.

2020-10-27 pediatrics
10.1101/2020.10.25.20219139 medRxiv
Show abstract

ObjectiveTo determine the feasibility of wearable technologies in physical activity assessment in three paediatric diseases, namely Niemann-Pick C (NP-C), Juvenile Idiopathic Arthritis (JIA) and Duchenne Muscular Dystrophy (DMD). DesignProof of concept feasibility study Setting and patientsThirty children were recruited across three UK hospitals (Royal Manchesters Children Hospital, Great Ormond Street Childrens Hospital and the Great North Childrens Hospital). Ten were diagnosed with NP-C, eight with DMD and twelve with JIA. InterventionAll participants completed the 6-minute walk test (6MWT) at enrolment. Patients were provided with disease specific smartphone apps paired with a wearable device via Bluetooth. Ambulation was recorded in 30-minute epochs measuring average daily maximum (ADM), average daily steps (ADS), and average daily steps per 30-minute epoch (ASE). ResultsMedian 6MWT results were 450m, 325m and 434.5m for the NP-C, DMD and JIA cohorts respectively. Wearable data capture was feasible in all three disease groups, although complete data capture was not sustained. A statistically significant between-cohort difference was identified for ADM, ADS and ASE. Statistically significant differences were found between DMD/JIA for ADM; NP-C/DMD for ADS and DMD/JIA for ASE. DiscussionWearable sensor technologies have the potential to add important information to our understanding of ambulation in chronic paediatric disease. The wearable devices were easy to use and popular with patients although key features need to be addressed to ensure higher engagement in future deployments. As the technology continues to evolve at a rapid pace, opportunities to implement child friendly solutions are already available.

Matching journals

The top 3 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.