In this paper, we propose a data-driven model lever-aging a Limited Penetrable Weighted Visibility Graph (LPWVG) derived from the photoplethysmogram (PPG) waveform for Pulse Wave Velocity (PWV) estimation. Four distinct LPWVGs were constructed employing diverse weighted methods. Subsequently, various features have been computed and extracted from PPG images, including two-dimensional Semi-classical Signal Analysis (SCSA)-based features, frequency-based features, and shape-based features. These features were then input into different machine-learning models. The proposed approach's performance was rigorously evaluated using both in-silico and real PPG pulse wave data. The obtained results provide compelling evidence supporting the feasibility and effectiveness of the proposed method for accurate PWV estimation in biomedical applications.

Download full-text PDF

Source
http://dx.doi.org/10.1109/EMBC53108.2024.10782510DOI Listing

Publication Analysis

Top Keywords

pulse wave
12
wave velocity
8
limited penetrable
8
penetrable weighted
8
weighted visibility
8
visibility graph
8
pwv estimation
8
features
6
velocity estimation
4
estimation photoplethysmogram-based
4

Similar Publications

Extreme storm events drive beach connectivity through headland bypassing.

Sci Total Environ

March 2025

Coastal and Marine Research Centre, Griffith University, Gold Coast campus - G51, QLD 4222, Australia.

Headland bypassing is a mainly wave-driven coastal process that interconnects sediment compartments and allows the continuity of longshore sediment transport. In turn, waves are subject to the variability of atmospheric patterns and climate drivers. This study focuses on identifying the atmospheric systems and associated hydrodynamic conditions that have triggered bypassing pulses in the study area, Fingal Head (New South Wales, Australia), over the last 33 years.

View Article and Find Full Text PDF

Medical image-based computational fluid dynamics (CFD) is a valuable tool for studying cardiovascular hemodynamics and its role in vascular pathologies. However, patient-specific flow rate measurements are rare. As a remedy, individual flow rates are typically estimated using anatomical features.

View Article and Find Full Text PDF

Purpose: Sedentary behavior (SB) contributes to the heightened risk of cardiovascular disease (CVD) in endometrial cancer survivors (ECS). This feasibility study aimed to evaluate key outcomes to assess the practicality of SB reduction interventions for ECS. Secondary aims included SB domain assessment and preliminary efficacy testing of the relationship between SB and arterial stiffness.

View Article and Find Full Text PDF

Background: Pedal acceleration time (PAT) is a novel indicator of peripheral arterial disease in the lower limbs. Elevated PAT values are associated with worse limb ischemia. Arterial stiffness indexes are another class of indicators recently studied in patients with chronic limb-threatening ischemia (CLTI).

View Article and Find Full Text PDF

Nerve signal conduction, and particularly in myelinated nerve fibers, is a highly dynamic phenomenon that is affected by various biological and physical factors. The propagation of such moving electric signals may seemingly help elucidate the mechanisms underlying normal and abnormal functioning. This work aims to derive the exact physical wave solutions of the nonlinear partial differential equations with fractional beta-derivatives for the cases of transmission of nerve impulses in coupled nerves.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!