Dataset of Pulse Waves for Thousands of Virtual Subjects Aged 55-75 Years, With/out AAAs
The full database is available for downloaded from here.
This repository also includes all algorithms used to generate the database and perform subsequent pulse wave analyses, including a machine learning model for detecting abdominal aortic aneurysms (AAAs) via pulse wave analysis.
Using Nektar1D, we generated a database comprising 10,935 virtual subjects aged 55, 65 and 75 years, each with a unique set of arterial pulse waveforms.
For each subject, data are provided for arterial blood pressure (P), flow rate (Q), flow velocity (U), luminal area (A), and photoplethysmogram (PPG) signals across multiple measurement sites, along with the corresponding simulation parameters (e.g., vessel geometries, AAA size, cardiac output, arterial stiffness). These pulse waves were simulated at baseline (normal physiology), with increased global arterial stiffness characteristic of subjects with AAAs, and with varying AAA sizes.
The database was verified by comparing the simulated pulse waves and derived indices with corresponding in vivo data. Good agreement was observed, with the simulations accurately reproducing age-related changes in haemodynamic parameters and pulse wave morphology. The simulation of pulse wave propagation in vessels with aneurysms was also tested and reported in J Royal Soc Interface (2021).
The database was used to demonstrate the feasibility of early AAA detection through machine learning-based analysis of PPG signals. Given the high mortality associated with AAA rupture, early detection is essential for enabling timely and effective treatment. The widespread availability of commercial wearable devices capable of accurately measuring PPG signals at the wrist or finger presents a valuable opportunity to screen the general population for AAAs outside of the clinic.
Machine learning-based pulse wave analysis for early detection of abdominal aortic aneurysms using in silico pulse waves.
Symmetry
13(5):804, 2021
An abdominal aortic aneurysm (AAA) is usually asymptomatic until rupture, which is associated with extremely high mortality. Consequently, the early detection of AAAs is of paramount importance in reducing mortality; however, most AAAs are detected by medical imaging only incidentally. The aim of this study was to investigate the feasibility of machine learning-based pulse wave (PW) analysis for the early detection of AAAs using a database of in silico PWs. PWs in the large systemic arteries were simulated using one-dimensional blood flow modelling. A database of in silico PWs representative of subjects (aged 55, 65 and 75 years) with different AAA sizes was created by varying the AAA-related parameters with major impacts on PWs—identified by parameter sensitivity analysis—in an existing database of in silico PWs representative of subjects without AAAs. Then, a machine learning architecture for AAA detection was trained and tested using the new in silico PW database. The parameter sensitivity analysis revealed that the AAA maximum diameter and stiffness of the large systemic arteries were the dominant AAA-related biophysical properties considerably influencing the PWs. However, AAA detection by PW indexes was compromised by other non-AAA related cardiovascular parameters. The proposed machine learning model produced a sensitivity of 86.8 % and a specificity of 86.3 % in early detection of AAA from the photoplethysmogram PW signal measured in the digital artery with added random noise. The number of false positive and negative results increased with increasing age and decreasing AAA size, respectively. These findings suggest that machine learning-based PW analysis is a promising approach for AAA screening using PW signals acquired by wearable devices.
Funders
