Longitudinal voice monitoring in a decentralized Bring Your Own Device trial for respiratory illness detection
Santamaria et al.
The finding, in our words
A fully decentralised trial of 9151 participants using a mobile app for daily voice capture found two machine learning algorithms met pre-specified success criteria for screening viral respiratory illness, with sensitivity increasing as symptoms increased while specificity remained consistent. This demonstrates voice-based digital biomarkers can identify infections remotely and validates bring-your-own-device trial designs.
A paraphrase to the Library’s standard, never the abstract. The source is one link away and is always the authority.
A direct-to-participant, multichannel recruitment strategy enrolled 34,244 older adults into a virtual trial testing an Apple Watch based heart health programme with electrocardiogram and irregular rhythm notification features, achieving broad geographic and gender diversity but under-representing non-White ethnic groups.
Home spirometry gave slightly lower percent-predicted FEV1 values than office measurements cross-sectionally, but the three-month change in lung function did not differ significantly between settings. This suggests home spirometry can reliably detect treatment effects, supporting its use as an endpoint for decentralised cystic fibrosis trials.
Rosenfeld et al., Annals of the American Thoracic Society (paywalled) · source ↗
Analysis of six studies revealed that decentralised clinical trial elements enhanced data completeness by enabling direct access to medical records, although this introduced a significant burden for data abstraction. The results suggest that decentralised approaches are not a universal solution but provide specific metrics that can help design fit-for-purpose trials.
Wearable-derived digital biomarkers have been accepted by regulatory agencies as endpoints in clinical trials for Duchenne muscular dystrophy, showing their potential to support decentralised diagnostics through patient-centric monitoring. This matters because it enables more sensitive and continuous assessment of disease progression outside clinical settings.
Ma et al., Neurology and therapy (paywalled) · source ↗
The study found that acoustic speech features differed significantly between Android and iOS devices, with iOS recordings showing more periodic content but less high-frequency energy, while Android devices exhibited greater measurement variability. These platform-specific differences, coupled with participant experience challenges such as iOS users struggling with background noise checks, demonstrate that device choice and app instruction design materially affect data quality and trial outcomes in decentralised digital biomarker studies.
Chappie et al., Journal of voice : official journal of the Voice Foundation (paywalled) · source ↗