A Multi-scenario Attention-based Generative Model for Personalized Blood Pressure Time Series Forecasting

TL;DR

This paper introduces a personalized, multi-scenario attention-based generative model utilizing ECG and PPG signals for accurate blood pressure forecasting, demonstrating robustness across diverse datasets and scenarios.

Contribution

The work presents a novel multi-scenario attention-based generative model that incorporates 2D representation learning for personalized blood pressure prediction from physiological signals.

Findings

Achieves accurate BP forecasts within AAMI standards across three scenarios.

Demonstrates robustness and reliability in diverse patient datasets.

Provides early detection of abnormal BP fluctuations in critical care.

Abstract

Continuous blood pressure (BP) monitoring is essential for timely diagnosis and intervention in critical care settings. However, BP varies significantly across individuals, this inter-patient variability motivates the development of personalized models tailored to each patient's physiology. In this work, we propose a personalized BP forecasting model mainly using electrocardiogram (ECG) and photoplethysmogram (PPG) signals. This time-series model incorporates 2D representation learning to capture complex physiological relationships. Experiments are conducted on datasets collected from three diverse scenarios with BP measurements from 60 subjects total. Results demonstrate that the model achieves accurate and robust BP forecasts across scenarios within the Association for the Advancement of Medical Instrumentation (AAMI) standard criteria. This reliable early detection of abnormal fluctuations in BP is crucial for at-risk patients undergoing surgery or intensive care. The proposed model provides a valuable addition for continuous BP tracking to reduce mortality and improve prognosis.