Serum Potassium Monitoring Using AI-Enabled Smartwatch Electrocardiograms
Chiu et al.
The finding, in our words
The Kardio-Net AI model predicted serum potassium from smartwatch ECGs with an AUC of 0.831 for severe hyperkalaemia (>6.5 mEq/L) in ESRD patients, achieving a mean absolute error of 0.580 mEq/L. This prospectively validated method enables remote potassium monitoring, potentially decreasing invasive blood sampling in high-risk chronic kidney disease populations.
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.
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 ↗
A 2025 review from China finds decentralised trials still far from standard practice despite the enthusiasm of regulators and industry, and names the operational gaps that keep them so: technology, oversight and data quality.
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 ↗