# Mechanistic Assessment of Cardiovascular State Informed by Vibroacoustic Sensors

## TL;DR

This paper introduces a new method to estimate blood pressure using sound signals and a personalized model of the cardiovascular system.

## Contribution

A novel AI-based method to personalize a mechanistic cardiovascular model using vibroacoustic sensor data for blood pressure estimation.

## Key findings

- The method uses cardiopulmonary acoustic signals to customize a cardiovascular model.
- Simulation results show promising accuracy in blood pressure estimation compared to arterial line measurements.

## Abstract

Monitoring blood pressure, a parameter closely related to cardiovascular activity, can help predict imminent cardiovascular events. In this paper, a novel method is proposed to customize an existing mechanistic model of the cardiovascular system through feature extraction from cardiopulmonary acoustic signals to estimate blood pressure using artificial intelligence. As various factors, such as drug consumption, can alter the biomechanical properties of the cardiovascular system, the proposed method seeks to personalize the mechanistic model using information extracted from vibroacoustic sensors. Simulation results for the proposed approach are evaluated by calculating the error in blood pressure estimates compared to ground truth arterial line measurements, with the results showing promise for this method.