2024 · Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference · paywalled
Personalized Data-Driven State Models of the Circadian Dynamics in a Biometric Signal
Ike et al.
The finding, in our words
A personalised model combining an autoencoder with a recurrent neural network can reconstruct and predict actigraphy signals from light exposure, and its latent state oscillation aligns with melatonin-derived circadian phase. This approach could enable individualised circadian monitoring and feedback control applications.
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 ↗
This study found that a decentralised approach using home-based sleep apnoea screening, heart rhythm monitoring and activity tracking in patients with atrial fibrillation is feasible, with high data completeness and low drop-out rates. The results support the use of patient-centric digital tools in decentralised trials for chronic cardiac conditions.
Hashiba et al., Danish medical journal (paywalled) · source ↗
In 50 cancer patients monitored at home with an Apple Watch for 28 days, a method that classified missing step data by gap duration and context produced the most reliable daily step estimates. Daily step counts on days with at least ten hours of wear time predicted time to first clinical event (p=0.068) and identified participants at lower hazard of mortality, with 83.3% accuracy for clinical event prediction, demonstrating that processed consumer wearable data can support remote monitoring in decentralised oncology trials.
Oakley-Girvan et al., Digital biomarkers · source ↗