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

• URL: http://arxiv.org/abs/2607.20027v1
• Date: Wed, 22 Jul 2026 11:12:07 GMT
• Title: Zero-Shot Heart Rate Variability Forecasting from Consumer Wearables Using Time Series Foundation Models
• Abstract summary: Short-term Heart Rate Variability (HRV) forecasting could provide clinicians with actionable lead time for detecting autonomic dysfunction and adverse cardiac events.<n> Consumer wearable devices generate fragmented, artifact-rich HRV signals that challenge conventional forecasting approaches.<n>In this study, we evaluated the forecasting ability of three Time Series Foundation Models (TSFMs), TimesFM, Chronos, and MOIRAI.
• Score: 5.572607261284016
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Short-term Heart Rate Variability (HRV) forecasting could provide clinicians with actionable lead time for detecting autonomic dysfunction and adverse cardiac events. Consumer wearable devices generate fragmented, artifact-rich HRV signals that challenge conventional forecasting approaches. In this study, we evaluated the forecasting ability of three Time Series Foundation Models (TSFMs), TimesFM, Chronos, and MOIRAI, against traditional baselines (Mean, Exponential Smoothing, and Exponentially Weighted Moving Average) on real-world wearable data collected from 49 healthy individuals. To address data fragmentation, we introduce a variability-preserving imputation method that augments linear interpolation with locally adaptive stochastic noise, retaining physiological dynamics essential for accurate forecasting. The results show that TSFMs outperformed all baselines without fine-tuning, achieving average Mean Absolute Scaled Error (MASE) between 0.81 and 0.87 across TSFMs and both context lengths (32 and 64 time steps), with Chronos and TimesFM as the top models, though MOIRAI showed limited gains over baselines. With up to a 2-hour forecast horizon, the results establish a baseline for TSFMs' performance on a real-world dataset, highlighting domain-specific fine-tuning as a promising direction for clinical deployment.

Related papers

• SOTER: A Generative Time-Series Foundation Model for Wearable Human Physiological Signals [29.86069351223442]
  We present SOTER, a generative foundation model for wearable physiological time series that unifies cross-channel coupling, spectrum-guided expert specialization, and continuous-time latent evolution within a single pre-training framework.<n>We pre-train SOTER on 226 billion time points from five public physiological datasets and evaluate the same pre-trained model across out-of-distribution zero-shot forecasting, frozen-encoder linear-probe classification, and continuous-time imputation on wearable benchmarks.
  arXiv  Detail & Related papers  (2026-09-15T08:11:03Z)
• MedFlow: Class-Aware Multi-Scale Generation for Medical Time-Series Synthesis [61.211117385840396]
  We propose MedFlow, a class-aware flow matching framework for medical time-series synthesis.<n>MedFlow employs a vector-quantized multi-scale tokenizer to represent medical sequences at complementary temporal resolutions.<n> Token Marginal Guidance, which incorporates class-conditional token statistics directly into the flow matching process, steers generation toward class-specific regions.
  arXiv  Detail & Related papers  (2026-09-04T07:02:12Z)
• A censoring-aware target interface for tabular foundation models in survival prediction [1.402135576373209]
  We introduce SurvFM-RMST, a censoring-aware target-interface framework.<n>It converts survival outcomes into jackknife pseudo-observation targets for restricted mean survival time.<n>In simulations with known conditional RMST, SurvFM-RMST recovered restricted event-free time accurately.
  arXiv  Detail & Related papers  (2026-07-10T16:26:19Z)
• TimeLAVA: Learning-Agnostic Data Valuation for Time Series [48.76711740818533]
  TimeLAVA is a learning-agnostic framework that values temporal segments by their marginal contribution to minimize distributional discrepancy between evaluated and reference data.<n>We provide theoretical guarantees linking valuation to model-agnostic generalization and prove bounded sensitivity to contamination.
  arXiv  Detail & Related papers  (2026-06-17T06:16:16Z)
• Domain-Adaptive Arrhythmia Classification Using a Hybrid Transformer on Wearable Heart Signals [0.8594140167290097]
  We propose a hybrid transformer model that processes continuous ECG signals alongside seven heart rate variability (HRV) features.<n>We employ representation learning techniques, including Maximum Mean Discrepancy (MMD), to align feature distributions between source and target domains.<n>When tested on wearable device data with an unseen domain, the model achieved an F1-macro 95% and balanced accuracy of 96.15%.
  arXiv  Detail & Related papers  (2026-05-05T22:03:48Z)
• TimeAPN: Adaptive Amplitude-Phase Non-Stationarity Normalization for Time Series Forecasting [67.91113180885601]
  TimeAPN explicitly models and predicts non-stationary factors from both the time and frequency domains.<n>TimeAPN consistently improves long-term forecasting accuracy across multiple prediction horizons.<n>It outperforms state-of-the-art reversible normalization methods.
  arXiv  Detail & Related papers  (2026-03-18T07:21:24Z)
• Synapse: Adaptive Arbitration of Complementary Expertise in Time Series Foundational Models [50.877082340479085]
  We study how different Time Series Foundational Models (TSFMs) exhibit specialized performance profiles across various forecasting settings.<n>We propose Synapse, a novel arbitration framework for TSFMs.<n>Results demonstrate that Synapse consistently outperforms other popular ensembling techniques as well as individual TSFMs.
  arXiv  Detail & Related papers  (2025-11-07T18:01:51Z)
• Enabling Granular Subgroup Level Model Evaluations by Generating Synthetic Medical Time Series [3.5347586732342435]
  We introduce textitEnhanced TimeAutoDiff, which augments the latent diffusion objective with distribution-alignment penalties.<n>We benchmark all models on MIMIC-III and eICU, on 24-hour mortality and binary length-of-stay tasks.<n>For 32 intersectional subgroups, large synthetic cohorts cut-level AUROC estimation error by up to 50%.
  arXiv  Detail & Related papers  (2025-10-22T16:17:29Z)
• A Unified Frequency Domain Decomposition Framework for Interpretable and Robust Time Series Forecasting [81.73338008264115]
  Current approaches for time series forecasting, whether in the time or frequency domain, predominantly use deep learning models based on linear layers or transformers.<n>We propose FIRE, a unified frequency domain decomposition framework that provides a mathematical abstraction for diverse types of time series.<n>Fire consistently outperforms state-of-the-art models on long-term forecasting benchmarks.
  arXiv  Detail & Related papers  (2025-10-11T09:59:25Z)
• MIRA: Medical Time Series Foundation Model for Real-World Health Data [39.55921588296102]
  A unified foundation model for medical time series offers the potential to reduce annotation burdens, minimize model customization, and enable robust transfer.<n>We introduce MIRA, a unified foundation model specifically designed for medical time series forecasting.<n> MIRA achieves reductions in forecasting errors by an average of 10% and 7% in out-of-distribution and in-distribution scenarios, respectively, when compared to other zero-shot and fine-tuned baselines.
  arXiv  Detail & Related papers  (2025-06-09T09:27:17Z)
• Finetuning and Quantization of EEG-Based Foundational BioSignal Models on ECG and PPG Data for Blood Pressure Estimation [46.36100528165335]
  Photoplethysmography and electrocardiography can potentially enable continuous blood pressure (BP) monitoring.<n>Yet accurate and robust machine learning (ML) models remains challenging due to variability in data quality and patient-specific factors.<n>In this work, we investigate whether a model pre-trained on one modality can effectively be exploited to improve the accuracy of a different signal type.<n>Our approach achieves near state-of-the-art accuracy for diastolic BP and surpasses by 1.5x the accuracy of prior works for systolic BP.
  arXiv  Detail & Related papers  (2025-02-10T13:33:12Z)
• Synthesizing Multimodal Electronic Health Records via Predictive Diffusion Models [69.06149482021071]
  We propose a novel EHR data generation model called EHRPD. It is a diffusion-based model designed to predict the next visit based on the current one while also incorporating time interval estimation. We conduct experiments on two public datasets and evaluate EHRPD from fidelity, privacy, and utility perspectives.
  arXiv  Detail & Related papers  (2024-06-20T02:20:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.