Short-Term Physiological Forecasting with Adaptive Covariance Matrix Estimation

Cem Okan Yaldiz, Onur Selim Kilic, Omer T. Inan

Confirmation: I have read and agree with the IEEE BSN 2025 conference submission's policy on behalf of myself and my co-authors.

Keywords: Autoregressive modeling, Kalman filter, physiological forecasting, seismocardiogram, electrocardiogram, adaptive estimation

TL;DR: We propose a time-varying autoregressive multimodal Kalman filter with adaptive parameter estimation for short-term physiological forecasting.

Abstract: Short-term physiological forecasting holds promise for applications requiring capture of rapid changes in physiological signals. Modeling these transient dynamics may enable the quantification of subtle physiological changes that can be critical in many real-time or sensitive contexts, such as assessing acute stress or closed-loop resuscitation. In this paper, we demonstrate the effectiveness of a time-varying autoregressive Kalman filter-based framework for short-term forecasting of physiological features. To eliminate the need for manual hyperparameter tuning, we integrate an adaptive mechanism that dynamically estimates the process and measurement noise parameters of the Kalman filter. Our results demonstrate that the proposed method outperforms baseline models by approximately 1 ms in predicting the next heartbeat's pre-ejection period and by 2–3 ms in predicting the next heartbeat's left ventricular ejection period. Moreover, we demonstrate that it can achieve this improved performance without hyperparameter tuning. This work provides a robust forecasting framework for tracking physiological features and generating new ones to capture short-term physiological variations.

Track: 3. Signal processing, machine learning, deep learning, and decision-support algorithms for digital and computational health

NominateReviewer: Onur Selim Kilic - [e-mail]

Submission Number: 44