Parallel convolutional neural networks for non-invasive cardiac hemodynamic estimation: integrating uncalibrated PPG signals with nonlinear feature analysis

• Published in: Physiological measurement Vol. 46; no. 3; pp. 35008 - 35021
• Main Authors: Ipar, Eugenia, Cymberknop, Leandro J, Armentano, Ricardo L
• Format: Journal Article
• Language: English
• Published: England IOP Publishing 31.03.2025
• Subjects: Adult; cardiac hemodynamic status; cardiovascular health; Convolutional Neural Networks; Deep Learning; Female; Heart - physiology; Hemodynamics; Humans; Male; Middle Aged; Neural Networks, Computer; Nonlinear Dynamics; parallel convolutional neural networks; Photoplethysmography; Signal Processing, Computer-Assisted; cardiac hemodynamic status; parallel convolutional neural networks; photoplethysmography; cardiovascular health

Objective. Understanding cardiac hemodynamic status (CHS) is essential for accurate cardiovascular health assessment, as it is governed by key parameters such as cardiac output (CO), systemic vascular resistance (SVR), and arterial compliance (AC). This study aims to develop a non-invasive method us...