Non-Invasive LVEDP Assessment Using PPG Signal Classification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for diagnosing cardiac diseases such as diastolic heart failure and pulmonary hypertension involve invasive procedures, radiation, or specialized imaging facilities, posing risks and limitations.
Innovation Solution
A non-invasive system using machine-learned classifiers to analyze biophysical signals, specifically cardiac and photoplethysmographic measurements, to estimate metrics like elevated left ventricular end-diastolic pressure (LVEDP) for disease diagnosis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If invasive procedures or specialized imaging facilities are used to diagnose cardiac diseases, then diagnostic accuracy is improved, but patient risk and device complexity increase
Solution Approach 1:
The patent replaces invasive mechanical procedures (catheterization, imaging) with non-invasive optical sensing (photoplethysmography) and computational analysis. The PPG sensor captures blood volume changes optically, and machine learning algorithms process these signals to estimate LVEDP, eliminating the need for physical intrusion into the patient's body while maintaining diagnostic capability.
Solution Approach 2:
The patent introduces photoplethysmographic signals as an intermediary medium to indirectly measure LVEDP. Instead of directly measuring pressure through invasive catheters, the system uses PPG waveforms as a surrogate that correlates with LVEDP, allowing estimation through computational models without direct contact with the left ventricle.
2Measurement precision
If invasive procedures are used to measure LVEDP, then measurement precision is improved, but ease of operation deteriorates
Solution Approach 1:
The patent substitutes complex invasive measurement systems with simple optical sensors and computational algorithms. The PPG sensor and processing system can be integrated into portable devices, making the procedure as simple as placing a finger on a sensor, comparable to using a pulse oximeter, while providing LVEDP estimation accuracy previously only achievable through complex catheterization procedures.
3Reliability
If traditional invasive methods are used for disease diagnosis, then diagnostic reliability is improved, but device complexity increases
Solution Approach 1:
The patent replaces complex invasive diagnostic equipment with simple optical sensors coupled with machine learning processing. The PPG sensor is a standard, simple device already widely used in consumer electronics, and the computational complexity is handled through software algorithms rather than complex hardware, enabling reliable LVEDP measurement with minimal equipment.
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 and precise diagnosis of cardiac conditions without invasiveness, supplementing or replacing traditional evaluation modalities with numerical scores and related information.
Implementation Method 1
a first photoplethysmographic signal and a second photoplethysmographic signal from a photoplethysmographic sensor
Data Source
AI summary
A clinical evaluation system and method are disclosed that facilitate the use of features or parameters extracted from biophysical signals in a model or classifier (e.g., a machine-learned classifier) to estimate metrics associated with the physiological state of a patient, including for the presence or non-presence of elevated left ventricular end-diastolic pressure (elevated LVEDP), as an example indicator of a disease medical condition that could be assessed by using the system and method described herein.