Cycle Variability Features for Non-Invasive Cardiac Diagnosis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for diagnosing cardiac diseases and conditions often require invasive procedures, specialized facilities, or exposure to radiation, posing risks and disadvantages.
Innovation Solution
A non-invasive system that analyzes cycle variability features extracted from biophysical signals, such as cardiac and photoplethysmographic signals, using machine-learning classifiers to estimate disease presence, severity, and localization without requiring invasive techniques or radiation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional statistical measures (mean, standard deviation) are used to characterize physiological signals, then the analysis is simple and computationally efficient, but the measures fail to capture non-stationary dynamics and cycle variability-related features
Solution Approach 1:
The patent transforms the analysis approach by changing from traditional statistical parameters (mean, standard deviation) to cycle variability-related features derived from instantaneous amplitude and frequency. This parameter transformation enables capture of non-stationary dynamics while maintaining computational feasibility through systematic processing steps including envelope detection, Hilbert transform, and spectral analysis.
Solution Approach 2:
The patent replaces traditional mechanical/statistical signal analysis methods with advanced signal processing techniques including Hilbert transform, envelope detection, and spectral analysis. This substitution enables extraction of instantaneous amplitude and frequency information, capturing non-stationary characteristics that traditional methods miss.
2Measurement precision
If advanced signal processing techniques are applied to extract cycle variability features, then the characterization of physiological systems is improved, but the computational requirements and processing time increase
Solution Approach 1:
The patent applies preliminary processing steps including envelope detection and Hilbert transform to extract instantaneous amplitude and frequency before performing spectral analysis. This preliminary action organizes the signal data in a way that facilitates efficient computation of cycle variability features, reducing overall processing time.
Solution Approach 2:
The patent segments the physiological signal into individual cycles and processes each cycle separately to extract cycle variability-related features. This segmentation enables focused analysis of specific physiological events while maintaining computational efficiency through batch processing of segmented data.
3Measurement precision
If cycle variability-related features are extracted from biophysical signals, then physiological system characterization is enhanced, but the difficulty of detecting and measuring these features increases
Solution Approach 1:
The patent introduces intermediate processing steps including envelope detection and Hilbert transform that serve as mediators between the raw biophysical signal and the final cycle variability features. These intermediaries systematically extract instantaneous amplitude and frequency information, making the measurement process more structured and less error-prone.
Solution Approach 2:
The patent replaces direct measurement approaches with advanced signal processing techniques including spectral analysis and Hilbert transform. This substitution provides robust mathematical frameworks for detecting cycle variability features, reducing measurement difficulty through systematic computational methods.
Data Source
Figure 1
Figure 2
Figure 3A
AI summary
The exemplified methods and systems facilitate the use, for diagnostics, monitoring, or treatment, of one or more cycle variability based features or parameters determined from biophysical signals such as cardiac or photoplethysmography signals that are acquired non-invasively from surface sensors placed on a patient while the patient is at rest. The estimated metric may be used to assist a physician or other healthcare provider in diagnosing the presence or non-presence and/or severity and/or localization of diseases or conditions or in the treatment of said diseases or conditions.