Deep Learning-Based Automated Versus Manual Snoring Scoring in Sleep Disordered Breathing
Kang et al.
The finding, in our words
Automated snoring analysis using deep learning showed strong agreement with expert manual scoring for snoring time and percentage in 100 adults undergoing polysomnography. This supports its potential as an objective, reproducible digital biomarker for sleep-disordered breathing that could enable remote or decentralised assessment.
A paraphrase to the Library’s standard, never the abstract. The source is one link away and is always the authority.
In progressive multiple sclerosis, higher serum neurofilament light chain levels were associated with reduced daily step counts from wearables, while higher step counts were linked to lower sNfL. A ten percent increase in steps corresponded to a 0.015 decrease in sNfL z-score, suggesting rising sNfL may predict subsequent mobility decline.
Joseph et al., Annals of clinical and translational neurology (paywalled) · source ↗
The High-Definition Oncology feasibility study in 30 women with metastatic cancer demonstrated high adherence to biospecimen collection (97.4% plasma, 80.7% stool) and wearable monitoring (70–95% of days captured for activity, heart rate, sleep, and oxygen saturation). This establishes a viable framework for decentralised, multimodal data collection in oncology to support individualised treatment models.
Garma et al., JCO precision oncology (paywalled) · source ↗
Wearing-off symptoms during natalizumab treatment in multiple sclerosis correlate with fatigue but not with inflammatory or neurodegenerative biomarkers, suggesting they are not markers of disease activity. Passive wearable monitoring detected subtle end-of-cycle motor declines and dynamic activity features that aligned with fatigue, indicating potential for digital biomarkers to serve as remote endpoints in decentralised neurological care.
Masanneck et al., Neurotherapeutics : the journal of the American Society for Experimental NeuroTherapeutics (paywalled) · source ↗
Short-term PM2.5 exposure raised nocturnal cough frequency by 2.4 per cent for each 10 μg/m³ increase across 32 cities. Audio recordings from a mobile sleep app, processed by artificial intelligence, provide a feasible digital biomarker for real-time environmental health surveillance.
Xia et al., Communications health (paywalled) · source ↗
Patients with metastatic cancer who recorded ≤3013 steps/day during the 14‑day post‑discharge period had substantially higher rates of 90‑day unplanned readmission (73% versus 13%) and mortality (47% versus 9%) than more active patients. Wearable‑derived mobility is a promising decentralised digital biomarker for risk stratification after hospital discharge, but requires external validation before guiding supportive care.
Akdogan et al., Supportive care in cancer : official journal of the Multinational Association of Supportive Care in Cancer (paywalled) · source ↗