Cardiac Time Interval Marking from Heart Valve Signals
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current cardiopulmonary health monitoring techniques, such as echocardiograms, require expensive devices and skilled operators, limiting their applicability, and existing methods fail to effectively capture and analyze cardiac valve events and vibrations for comprehensive heart function assessment.
Innovation Solution
A system and method using tri-axial accelerometers to capture multi-channel vibration signals combined with electrocardiogram signals, employing machine learning and signal processing techniques like PCA, SVD, and deep learning to identify and mark cardiac time intervals, enabling the separation and analysis of individual heart valve events and respiratory sounds.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If echocardiogram is used for cardiac health assessment, then measurement precision is improved, but device complexity and cost increase
Solution Approach 1:
The patent replaces complex mechanical ultrasound imaging systems with simple accelerometer-based vibration sensing. The accelerometers detect mechanical vibrations from heart valve events, allowing cardiac assessment without expensive echocardiography equipment. This substitution maintains diagnostic capability while dramatically reducing device complexity and cost.
Solution Approach 2:
The patent creates simplified copies of echocardiogram functionality using accelerometers that capture vibration patterns analogous to ultrasound data. By analyzing these vibration copies through signal processing and machine learning, the system reproduces key diagnostic information from complex echocardiograms using simple sensors.
2Measurement precision
If echocardiogram is used for cardiac health assessment, then measurement precision is improved, but ease of operation deteriorates
Solution Approach 1:
The patent implements automated signal processing and machine learning algorithms that perform diagnostic analysis without requiring skilled operators. The system automatically captures vibrations, separates heart valve signals from respiratory and motion artifacts, and generates diagnostic results, making cardiac assessment accessible to non-experts and eliminating the need for specialized training.
Solution Approach 2:
The patent replaces the need for skilled operators performing complex ultrasound procedures with automated accelerometer-based detection. The machine learning models automatically interpret vibration patterns, substituting human expertise with algorithmic analysis that is equally accurate but requires no specialized training.
3Measurement precision
If source separation techniques are applied to capture individual valve events, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent replaces complex mechanical signal separation hardware with software-based source separation algorithms. The machine learning models digitally separate mixed vibrations from multiple heart valves, respiratory sounds, and body movements, achieving precise valve event detection without additional complex sensing hardware.
Solution Approach 2:
The patent creates separate digital copies of individual valve event signals from the mixed vibration input. Through source separation algorithms, the system generates isolated signal representations of each heart valve event, enabling precise analysis of individual valves while using simple accelerometer hardware.
Data Source
AI summary
A system for marking cardiac time intervals from heart valve signals includes a non-invasive sensor unit for capturing electrical signals and composite vibration objects, a memory containing computer instructions, and one or more processors coupled to the memory. The one or more processors causes the one or more processors to perform operations including separating a plurality of individual heart vibration events into heart valve signals from the composite vibration objects, and marking cardiac time interval from the heart valve signals by detecting individual heartbeats using at least one or more of a PCA algorithm or deep learning.