AI Waveform Analysis for Instantaneous Intrinsic Frequency Determination

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current methods for instantaneous determination of cardiovascular waveform intrinsic frequencies are computationally expensive and non-convex, making them inefficient for real-time clinical applications, particularly in diagnosing cardiovascular diseases using machine learning models.

Innovation Solution

An AI-based methodology that maps cardiovascular waveforms to intrinsic frequency parameters using a modified sparse time-frequency representation method, allowing for non-invasive and instantaneous analysis on client devices like smartphones, which avoids the need for calibration and reduces data complexity through normalization and resampling.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional signal analysis methods are used to determine intrinsic frequencies, then measurement precision is improved, but computational complexity and processing time increase significantly

Engineering Contradiction:

Improveintrinsic frequency determination accuracyVSAvoidcomputational complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent transforms the complex intrinsic frequency determination problem into a simpler parameter estimation problem by changing the mathematical parameters from direct frequency calculation to phase-based estimation. This allows the use of efficient algorithms that maintain precision while reducing computational burden significantly.

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The patent replaces traditional mechanical signal processing methods with an AI-based computational approach. The trained neural network model substitutes complex iterative signal analysis algorithms, providing equivalent or superior measurement precision with dramatically reduced computational complexity and faster processing speed.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If traditional signal analysis methods are used to determine intrinsic frequencies, then measurement precision is improved, but processing speed decreases

Engineering Contradiction:

Improveintrinsic frequency determination accuracyVSAvoidprocessing speed

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

The patent performs preliminary training of the AI model offline using extensive signal data. This preliminary action pre-computes the optimal parameter mappings, so that during actual clinical use, the system can rapidly determine intrinsic frequencies by simply applying the pre-trained model to new waveforms, achieving both high precision and fast processing speed.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent replaces slow traditional signal processing algorithms with a trained neural network that can instantly process cardiovascular waveforms. The AI model substitutes iterative mathematical optimization with direct computational inference, dramatically increasing processing speed while preserving measurement precision.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Measurement precision

If detailed waveform data is retained for analysis, then measurement precision is improved, but data storage requirements increase

Engineering Contradiction:

Improvesignal analysis accuracyVSAvoiddata storage requirements

Core Design Contradiction:

Measurement precisionVSQuantity of substance

Solution Approach 1:

The patent extracts only the essential features from detailed waveform data that are necessary for intrinsic frequency determination. By identifying and extracting the critical temporal and morphological characteristics of cardiovascular waveforms, the system maintains measurement precision while storing only the extracted features rather than complete high-resolution waveform data.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The patent segments the continuous waveform data into discrete characteristic points and intervals that contain the essential information for analysis. By dividing the waveform into key segments (such as systolic and diastolic phases with their respective features), the system reduces data storage requirements while preserving the precision needed for accurate intrinsic frequency determination.

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS20230148969A1Sequentially-reduced artificial intelligence methodology for instantaneous determination of waveform intrinsic frequencies

Publication Date: 2023.05.18 ECOLE POLYTECHNIQUE FEDERALE DE LAUSANNE (EPFL)

AI summary

Artificial intelligence (AI) based methodology for instantaneous signal analysis of cardiovascular waveforms using a single or multiple hemodynamic waveform(s) is described. For example, a system comprising at least one programmable processor and a non-transitory machine-readable medium storing instructions which, when executed by the at least one programmable processor, cause the at least one programmable processor to perform operations comprising receiving patient data having one or more cardiovascular waveforms related to a cardiac cycle or a vasculature of a patient; calculating, from the one or more waveforms, at least one output from a signal analysis method, inputting, into a trained artificial intelligence model, cardiovascular waveforms; determining, utilizing the trained artificial intelligence model, the clinically relevant parameters from a signal analysis method; and in response to determining the output parameters, providing the information about the underlying pathology to a user.