Evaluating Long-Range Temporal Structure in Foundation Model-Based Forecasts of Heartbeat Dynamics

Adrian Serapio, Bharath Ramsundar, Sandya Subramanian

Keywords: Time-Series, Foundation Models, ECG

TL;DR: We examine the long-range temporal structure of forecasts produced by Time-Series Foundation Models (TSFMs) on heartbeat dynamics.

Abstract: We examine the long-range temporal structure of forecasts produced by Time-Series Foundation Models (TSFMs) on heartbeat dynamics using the MIT-BIH Normal Sinus Rhythm Database (NSRDB). Our findings indicate that these models do not adequately capture long-range dependencies, as reflected in growing errors in RR-interval predictions over longer forecast horizons.

Submission Number: 119