cs.AINov 7, 2026

Pulse waveform morphology encodes haemodynamic signatures of impending stroke

Authors: Cheng Ding, Jiaming Liu, Jian Wu, Hongxia Xu, Daoqiang Zhang

Organizations: College of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics, Nanjing, Jiangsu, China · Key Laboratory of Brain-Machine Intelligence Technology, Ministry of Education, Nanjing University of Aeronautics and Astronautics, Nanjing, Jiangsu, China · State Key Laboratory of Transvascular Implantation Devices and TIDRI, School of Medicine, Zhejiang University, Hangzhou, 310009, Zhejiang, China · Zhejiang Key Laboratory of Medical Imaging Artificial Intelligence, Zhejiang University, Hangzhou, 310058, Zhejiang, China

Abstract

Stroke is a disorder of the circulation, yet the haemodynamic state that immediately precedes it has rarely been observed, because continuous physiological recordings before a stroke are seldom available. Photoplethysmography (PPG), recorded by every pulse oximeter and by hundreds of millions of wearable devices, captures the peripheral pulse beat by beat, but its morphology is largely discarded. Here we ask whether pulse waveform morphology encodes haemodynamic signatures of impending stroke. Using in-hospital stroke as a natural experiment that provides continuous PPG before physician-adjudicated stroke recognition, we studied intensive-care (MIMIC-III, n=176n=176) and emergency-department (MC-MED, n=154n=154) cohorts and described each beat with interpretable descriptors of pulse timing, amplitude, contour and variability. At a nominal 360-min horizon, morphology separated pre-recognition from stable windows with F1F_1 scores of 0.941 and 0.989 (sensitivity 0.998 and 0.980), with models transferred unchanged to the second cohort, and outperformed heart rate alone on identical windows. The signature was dominated by systolic crest time and its change from each patient's own baseline, feature attribution was concordant across cohorts (Spearman ρ=0.865ρ=0.865), and morphology recorded in the first two hours of care stratified the subsequent clinical course (F1F_1 0.714 and 0.691). In high-risk patients without stroke, 29% and 14% of windows were positive, but five-window persistence rules limited alerts to 17% and 2% of patients. The results demonstrate that the routinely recorded pulse thus carries haemodynamic imprint of the period preceding stroke, positioning pulse morphology as a candidate continuous cerebrovascular biomarker.

Figures & tables

Explore similar work

CardsList
  1. In-Hospital Stroke Risk-State Classification from PPG-Derived Hemodynamic Features

    Feb 10, 2026Jiaming Liu, Cheng Ding, Jian Wu +2PhotoplethysmographyClinical Risk Prediction

  2. When2What: A Timing-Conditioned Framework for Long-Horizon Forecasting of Continuous Cardiovascular Waveforms

    Nov 6, 2026Chaoqi Zhang, Shujie Yan, Zhao Zhang +6Time Series ForecastingLong-Term Time Series Forecasting