发表机构
Tampere University; University of Eastern Finland（坦佩雷大学; 东芬兰大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究利用时间序列基础模型从消费级可穿戴设备预测心率变异性，针对数据碎片化问题引入变异性保留插补方法，结果显示TSFMs在无需微调时优于传统基线模型，为其在真实数据集上的性能建立基线，凸显特定领域微调对临床部署的潜力。
AI 中文摘要
短期心率变异性（HRV）预测可为临床医生提供检测自主神经功能障碍和不良心脏事件的可操作提前期。消费级可穿戴设备生成的HRV信号碎片化且伪迹丰富，对传统预测方法构成挑战。本研究评估了三种时间序列基础模型（TSFMs），即TimesFM、Chronos和MOIRAI，与传统基线模型（均值、指数平滑和指数加权移动平均）在从49名健康个体收集的真实可穿戴数据上的预测能力。为解决数据碎片化问题，引入了一种变异性保留插补方法，该方法通过局部自适应随机噪声增强线性插值，保留准确预测所需的生理动态。结果表明，TSFMs在无需微调的情况下优于所有基线模型，在不同上下文长度（32和64个时间步）下，TSFMs的平均平均绝对缩放误差（MASE）在0.81至0.87之间，Chronos和TimesFM是顶级模型，MOIRAI相对于基线模型的提升有限。对于长达2小时的预测范围，该结果为TSFMs在真实数据集上的性能建立了基线，突出了特定领域微调作为临床部署的一个有前景的方向。
英文摘要
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.
CommentsAccepted to Computing in Cardiology (CinC) 2026. 4 pages, 2 figures, 3 tables
