Heart Murmur Classification Using FFT Harmonic Ratios
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The challenge of differentiating benign from pathologic heart murmurs in patients is hindered by the limited availability of trained medical professionals, leading to delayed diagnoses and unnecessary referrals, and existing electronic solutions are resource-intensive and costly.
Innovation Solution
A computer-implemented method using a digital stethoscope to capture heart signatures, applying Fast Fourier Transform (FFT) to analyze frequency waveforms, classifying murmurs based on harmonic and non-harmonic ratios, and providing an interface for classification as benign or pathologic.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual cardiac auscultation by trained physicians is used to differentiate benign from pathologic murmurs, then diagnostic accuracy is improved, but the limited availability of trained medical professionals causes delayed diagnoses and increases loss of time
Solution Approach 1:
The patent replaces the mechanical system of manual auscultation by trained physicians with an automated electronic system using digital stethoscopes and computer algorithms. The system captures heart sounds digitally and uses spectral analysis to automatically differentiate benign from pathologic murmurs, eliminating the dependency on limited human expertise while maintaining diagnostic accuracy and significantly reducing diagnosis time.
Solution Approach 2:
The system enables self-service by allowing non-specialist healthcare providers to perform murmur classification using the automated digital stethoscope and software. The algorithm independently analyzes the heart sounds and provides classification without requiring referral to cardiologists, making the diagnostic service self-sufficient and immediately available.
2Reliability
If multiple neural networks are deployed to classify heart murmurs, then classification reliability is improved, but the device complexity and operational costs increase significantly
Solution Approach 1:
The patent extracts and implements only the essential spectral analysis features needed for murmur classification rather than deploying multiple complete neural networks. By focusing on key frequency domain characteristics and harmonic ratio analysis, the system achieves reliable classification with a simplified algorithm that requires minimal computational resources and can run on standard hardware.
3Measurement precision
If comprehensive training data for every pathology is input to ensure AI system reliability, then classification accuracy is improved, but the data requirements and system complexity increase
Solution Approach 1:
The patent changes the approach from requiring comprehensive pathology-specific training data to using universal spectral analysis parameters that apply to all murmur types. By analyzing fundamental frequency domain characteristics and harmonic ratios that are inherent to different murmur mechanisms, the system achieves accurate classification across diverse pathologies without needing extensive training datasets for each specific condition.
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
This approach enhances diagnostic accuracy and efficiency by reducing subjectivity and resource requirements, enabling rapid and reliable differentiation of heart murmurs without the need for extensive training or expensive equipment.
Implementation Method 1
The captured heart signature is processed with a Fast Fourier Transformation (FFT) to identify a plurality of component frequency waveforms
Data Source
AI summary
A method to classify heart murmurs as benign or pathologic. A digitized acoustic heart signature of a patient is captured on a computing device and processed using Fast Fourier Transformation to identify a plurality of component frequency waveforms, each having a power value. Based on the waveforms' power values, they are classified into a primary frequency waveform, harmonic frequency waveforms, and non-harmonic frequency waveforms. The heart murmur of the patient is classified using a ratio of the power values of the harmonic waveforms as a portion of the composite power value of all the waveforms, and an interface indication is provided to the user of the computing device. A computing device and software program per the invention are also disclose.