Remote monitoring of heart failure exacerbations using a smartwatch - PubMed
3 hours ago
- #heart failure
- #wearable technology
- #remote monitoring
- Remote monitoring of heart failure (HF) exacerbations using smartwatches was studied in the TRUE-HF observational cohort.
- A deep learning model trained on data from 154 patients predicted peak oxygen uptake (pVO2) with strong correlation to clinical tests (Pearson's correlation = 0.85).
- A 10% drop in wearable-derived daily pVO2 was associated with a 3.62-fold increased hazard ratio for unplanned healthcare events, occurring at a median of 7.4 days after the drop.
- External validation in the All of Us Research Program confirmed the model's predictive power, with a reduced-sensor variant showing a hazard ratio of 1.32 for healthcare utilization.
- Wearable-derived pVO2 offers earlier and improved risk discrimination compared to existing fitness estimates and clinical markers, providing a scalable approach for HF monitoring.