Back

Comparative Evaluation of Wearable Sensor Form Factors for Physiological Monitoring in Youth with Autism Spectrum Disorder

Stewart, C.; Albertazzi, A.; Tasarz, J.; Kim, K.; Gandara, V.; Blucher, C.; Reyes-Martinez, C. C.; Smarr, B.; Besterman, A. D.

2026-05-07 health informatics
10.64898/2026.05.06.26352564 medRxiv
Show abstract

Sudden behavioral outbursts in youth with autism spectrum disorder (ASD) are difficult to predict and create substantial caregiving burdens. Wearable physiological monitoring might enable prediction, but sustained use may be limited by tolerability. We evaluated adherence and data completeness in 40 youth with ASD over a two-week period across four device types (wristband, headband, adhesive chest patch, and finger ring) alongside caregiver-reported useability and comfort. Data completeness varied markedly by device, with the patch achieving the highest completeness ([~]80%), followed by the wristband ([~]60%), headband ([~]50%), and ring ([~]20%). In multivariate analyses, adherence was driven by the device form factor rather than participant-level clinical characteristics. Devices rated as more comfortable did not yield higher completeness, revealing a divergence between reported preference and actual use. These findings suggest that device choice is a key consideration for studies in ASD youths, highlighting the need for research into model stability across sensor types in neurodivergent populations.

Matching journals

The top 6 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.