Non-invasive LVEDP Estimation Using Peripheral Pressure and Timing Signals
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for determining left ventricular end diastolic pressure (LVEDP) are either invasive, unsuitable for certain patient types, or only measure surrogate parameters, lacking a reliable non-invasive solution for accurate and safe assessment.
Innovation Solution
A system comprising a signal processor, pressure sensor, and timing sensor that non-invasively measures peripheral artery blood pressure and heart-related timing signals, using machine learning models trained during heart failure events to estimate LVEDP or pulmonary capillary wedge pressure (PCWP) based on physiological effects and heartbeat cycles.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If invasive catheterization procedures are used to measure LVEDP, then measurement precision is improved, but device complexity and patient risk increase
Solution Approach 1:
The patent uses an intermediary approach by measuring peripheral artery pressure (e.g., radial or carotid artery) as a surrogate that can be non-invasively obtained and then processed through transfer functions and machine learning models to estimate central aortic pressure and LVEDP. This intermediary measurement avoids direct invasive catheterization while still providing accurate estimation through physiological relationships.
Solution Approach 2:
The patent replaces the mechanical invasive catheterization system with a non-invasive pressure sensor system combined with computational algorithms. Instead of physically inserting catheters into the heart, the system uses external pressure sensors on peripheral arteries combined with machine learning models (neural networks, support vector machines) to computationally derive LVEDP, eliminating the need for invasive mechanical intervention.
2Measurement precision
If invasive catheterization procedures are used to measure LVEDP, then measurement precision is improved, but ease of operation deteriorates
Solution Approach 1:
The patent uses an intermediary approach by measuring peripheral artery pressure (e.g., radial or carotid artery) as a surrogate that can be non-invasively obtained and then processed through transfer functions and machine learning models to estimate central aortic pressure and LVEDP. This intermediary measurement avoids direct invasive catheterization while still providing accurate estimation through physiological relationships.
Solution Approach 2:
The system enables self-service by allowing continuous or repeated LVEDP measurements to be performed by healthcare providers or even patients themselves using non-invasive peripheral pressure monitoring, eliminating the need for specialized invasive procedures that require trained personnel and complex setup.
3Ease of operation
If non-invasive surrogate pressure measurements are used, then ease of operation is improved, but measurement precision deteriorates
Solution Approach 1:
The patent transforms the measurement approach by changing from direct LVEDP measurement to measuring peripheral artery pressure parameters and then using computational transformations (transfer functions, machine learning models) to derive LVEDP. This parameter transformation maintains ease of non-invasive measurement while improving precision through advanced signal processing and physiological modeling.
Solution Approach 2:
The patent applies local quality by using patient-specific calibration and personalized machine learning models that adapt to individual physiological characteristics. The system tailors the measurement and estimation process to each patient's specific hemodynamic properties, improving measurement precision while maintaining non-invasive ease of operation.
4Measurement precision
If machine learning models are trained during heart failure events, then measurement precision is improved, but loss of time increases
Solution Approach 1:
The patent applies preliminary action by training the machine learning models during the heart failure event itself, using the available data from the acute setting. Rather than waiting for post-event data collection, the system utilizes the heart failure event period for model training, thereby preparing the personalized model in advance for subsequent LVEDP predictions during recovery and follow-up.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables accurate, non-invasive determination of LVEDP and PCWP, improving heart failure management with reduced risk and increased accessibility for patients, as validated by animal and human data showing clinically meaningful prediction accuracy.
Implementation Method 1
a pressure sensor operatively connected to said signal processor to communicate therewith, wherein said pressure sensor is structured to be brought into mechanical connection with an external surface region of said subject so as to provide peripheral pressure signals corresponding to a peripheral artery blood pressure
Implementation Method 2
a timing sensor operatively connected to said signal processor to communicate therewith, wherein said timing sensor is structured to non-invasively measure a physical property of said subject's heart that is correlated with said subject's heart beat so as to provide timing signals comprising timing information with respect to heartbeat cycles
Data Source
AI summary
The present application relates to systems and methods for non-invasively determining at least one of left ventricular end diastolic pressure (LVEDP) or pulmonary capillary wedge pressure (PCWP) in a subject's heart, comprising: receiving, by a computer, a plurality of signals from a plurality of non-invasive sensors that measure a plurality of physiological effects that are correlated with functioning of said subject's heart, said plurality of physiological effects including at least one signal correlated with left ventricular blood pressure and at least one signal correlated with timing of heartbeat cycles of said subject's heart; training a machine learning model on said computer using said plurality of signals for periods of time in which said plurality of signals were being generated during a heart failure event of said subject's heart; determining said LVEDP or PCWP using said machine learning model at a time subsequent to said training and subsequent to said heart failure event.