Pressure Wave Morphology for Non-Invasive Cardiac Output Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing cardiovascular monitoring systems require multiple invasive and non-invasive measurements, as well as extensive computing resources, to estimate key parameters like cardiac output, making them costly and impractical for widespread use.
Innovation Solution
A simplified method using non-invasively measured physiologic inputs, such as brachial systolic and diastolic blood pressure, heart rate, and pulse wave velocity, in conjunction with a calibrated one-dimensional arterial tree model and artificial intelligence, to estimate cardiac output without extensive computing resources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple invasive and non-invasive measurements are used to estimate cardiovascular parameters, then measurement precision is improved, but device complexity and cost increase
Solution Approach 1:
The patent extracts and utilizes only the essential feature from complex cardiovascular monitoring - the uncorrelated pressure signal morphology - while discarding the need for multiple invasive sensors and complex measurement systems. This single pressure signal contains sufficient information when processed through the arterial tree model to estimate cardiac output and other parameters accurately.
Solution Approach 2:
The patent introduces a calibrated one-dimensional arterial tree model as an intermediary computational layer between the simple non-invasive pressure measurement and the complex cardiovascular parameters. This model acts as a mediator that translates basic pressure wave morphology into accurate estimates of cardiac output, central blood pressure, and other hemodynamic parameters without requiring direct measurement of each parameter.
2Reliability
If multiple physiologic parameters are measured non-invasively, then reliability of cardiovascular parameter estimation is improved, but ease of operation deteriorates
Solution Approach 1:
The patent extracts the critical diagnostic information contained in the morphology of the uncorrelated pressure signal while eliminating the need to measure multiple separate physiologic parameters. The arterial tree model is trained to recognize patterns in this single pressure signal that reliably indicate cardiovascular status, making the system both simple to operate and reliable.
Solution Approach 2:
The patent performs preliminary training of the arterial tree model using a database of synthetic data generated from calibrated models before clinical deployment. This pre-training establishes the reliability of the system in advance, allowing the actual clinical device to operate simply by applying the pre-trained model to patient pressure signals without requiring complex real-time adjustments or multiple measurements.
3Measurement precision
If extensive computing resources are allocated for real-time cardiovascular parameter computation, then measurement precision is improved, but loss of energy increases
Solution Approach 1:
The patent performs computationally intensive model training and database generation in advance, creating a pre-trained arterial tree model and synthetic data database. During actual clinical use, the system only needs to apply the pre-trained model to patient pressure signals, dramatically reducing real-time computing requirements and energy consumption while maintaining high measurement precision.
Solution Approach 2:
The patent creates a simplified computational copy of the complex cardiovascular system through the calibrated one-dimensional arterial tree model. This computational model replicates the essential hemodynamic relationships, allowing accurate parameter estimation through simpler calculations rather than requiring extensive real-time computing resources on the actual physiological system.
Data Source
AI summary
Methods are provided for estimating key reliably and accurately predicting cardiac output using a limited set of non-invasively monitored physiologic inputs, and a calibrated one-dimensional arterial tree model, a database of synthetic data generated from such a model, and an artificial intelligence module. Systems for estimating CO based on non-invasively measured physiologic inputs also are provided that may be implemented without the need for extensive real-time computing resources.