🛰️ Daily AI Frontier
‹ back to 2026-07-23

Zero-Shot Heart Rate Variability Forecasting from Consumer Wearables Using Time Series Foundation Models

Research Medical/Healthcare AI

Merged summary

TL;DR - Three time-series foundation models forecasted wearable-derived heart rate variability without fine-tuning, outperforming traditional baselines and potentially offering clinicians up to two hours of lead time.

  • TimesFM, Chronos, and MOIRAI were evaluated on artifact-rich data from 49 healthy individuals.
  • A variability-preserving imputation method combined linear interpolation with locally adaptive stochastic noise.
  • The models achieved average MASE scores of 0.81–0.87 across context lengths of 32 and 64 time steps.
  • Chronos and TimesFM performed best; MOIRAI offered limited improvement over baselines, suggesting domain-specific fine-tuning may be needed.

Sources (1)

Zero-Shot Heart Rate Variability Forecasting from Consumer Wearables Using Time Series Foundation Models

arXiv cs.LG Luukas Peräkylä, Fahad Sohrab, Ville Hautamäki, Merja Heinäniemi, Sui Huang, Pekka Abrahamsson 2026-07-22 arXiv:2607.20027

TL;DR - Three time-series foundation models forecasted wearable-derived heart rate variability without fine-tuning, outperforming traditional baselines and potentially offering clinicians up to two hours of lead time.

  • TimesFM, Chronos, and MOIRAI were evaluated on artifact-rich data from 49 healthy individuals.
  • A variability-preserving imputation method combined linear interpolation with locally adaptive stochastic noise.
  • The models achieved average MASE scores of 0.81–0.87 across context lengths of 32 and 64 time steps.
  • Chronos and TimesFM performed best; MOIRAI offered limited improvement over baselines, suggesting domain-specific fine-tuning may be needed.
item →