Cardiac Valve Timing Estimation from Non-Simultaneous Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for constructing Pressure-Volume (PV) loops from cardiac data are challenging due to the need for simultaneous measurement of pressure and volume, which is often impractical and risky, especially with left heart catheterization, limiting the comprehensive determination of cardiac valve events and hemodynamic information.
Innovation Solution
A system and method using a computing device to analyze physiological data signals, particularly left ventricular pressure data and electrocardiogram signals, to predict and synchronize cardiac valve opening and closing times, allowing for the construction of PV loops from non-simultaneously acquired data using machine learning models and derivative features.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If left heart catheterization is performed to obtain direct left ventricular pressure measurement, then measurement precision is improved, but device complexity and risk of complications increase
Solution Approach 1:
The patent uses machine learning models to create a virtual copy of the pressure-volume loop from non-simultaneous pressure and volume measurements, eliminating the need for complex simultaneous catheterization. The model learns the relationship between pressure and volume from training data and generates synthetic PV loops that replicate what would be obtained from direct simultaneous measurement.
Solution Approach 2:
The patent introduces machine learning models as an intermediary that bridges non-simultaneous pressure and volume measurements to reconstruct the pressure-volume relationship. The model acts as a mediator that infers the missing simultaneous measurement information from separate pressure and volume datasets.
2Measurement precision
If simultaneous pressure and volume measurement is performed to construct PV loops, then measurement precision is improved, but device complexity and procedural risk increase
Solution Approach 1:
The patent performs preliminary actions by collecting and storing pressure and volume measurements separately at different times, then uses machine learning to reconstruct the simultaneous relationship. This allows the system to prepare the necessary data components in advance without requiring complex simultaneous measurement hardware.
Solution Approach 2:
The machine learning model creates a computational replica of the simultaneous pressure-volume relationship from non-simultaneous measurements, generating synthetic PV loops that mirror what would be obtained from direct simultaneous measurement without requiring the complex hardware setup.
3Ease of operation
If non-simultaneous pressure and volume data are used to construct PV loops, then ease of operation is improved, but measurement precision deteriorates due to timing synchronization issues
Solution Approach 1:
The machine learning model serves as an intermediary that resolves the timing synchronization issue between non-simultaneous pressure and volume measurements. It learns the temporal relationships from training data and accurately pairs pressure and volume values that correspond to the same cardiac cycle phase, eliminating timing mismatch errors.
Solution Approach 2:
The system uses feedback from the machine learning model to continuously improve the synchronization of non-simultaneous measurements. The model learns from training data the correct temporal relationships and applies this knowledge to accurately align pressure and volume measurements from different time points, with the ability to refine predictions based on observed patterns.
Data Source
AI summary
The present disclosure describes system and methods for determining cardiac events from a physiological data signal and optionally constructing a Pressure-Volume (PV) loop display from non-simultaneously acquired measurements of pressure and volume data. One such method comprises obtaining, by a computing device, a physiological data signal of a heart of an individual; identifying, by the computing device, features of the physiological data signal and applying the features as inputs to a prediction model; determining, by the computing device using the prediction model, the cardiac events for one or more valves of the heart, wherein the cardiac events include timing of opening and closing of the one or more valves of the heart; and outputting, by the computing device, the cardiac events determined using the prediction model. The physiological data signal can be combined with non-simultaneously acquired volume data to create a PV loop display.