Physiological Signal Pathological Fluctuation Detection

Solution Overview

Problem

Existing methods for analyzing physiological signals fail to accurately capture important features of individual fluctuations, leading to ineffective predictive models for clinical conditions.

Innovation Solution

A method and system that utilize a pattern matching algorithm with a wavelet function to identify pathological fluctuations in physiological signals, such as heart rate decelerations, by sweeping a template function through time series data and calculating correlation coefficients, allowing for the detection of risks associated with clinical conditions like sepsis.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If indirect statistical measures are used to analyze physiological signals, then the analysis process is simplified, but the ability to capture important features of individual fluctuations is lost

Engineering Contradiction:

Improveanalysis process simplicityVSAvoidfeature capture accuracy

Core Design Contradiction:

Ease of operationVSMeasurement precision

Solution Approach 1:

The patent creates a template function that copies the characteristic shape of pathological fluctuations (such as decelerations in heart rate). This template is then matched against the physiological signal to identify similar patterns. By using a simplified template representation rather than complex statistical models, the system maintains ease of operation while accurately capturing the essential features of individual fluctuations through direct pattern comparison

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The patent replaces complex statistical analysis mechanisms with a pattern matching mechanism based on template correlation. Instead of using indirect statistical measures that lose detailed feature information, the system uses direct template matching with correlation coefficients to preserve and detect important fluctuation characteristics while maintaining computational simplicity

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Ease of manufacture

If previous statistical methods are used for predictive modeling, then the model development is easier, but the predictive accuracy for clinical conditions is insufficient

Engineering Contradiction:

Improvemodel development easeVSAvoidpredictive model accuracy

Core Design Contradiction:

Ease of manufactureVSReliability

Solution Approach 1:

The patent creates a template function that copies the characteristic shape of pathological fluctuations (such as decelerations in heart rate). This template is then matched against the physiological signal to identify similar patterns. By using a simplified template representation rather than complex statistical models, the system maintains ease of operation while accurately capturing the essential features of individual fluctuations through direct pattern comparison

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The patent replaces complex statistical analysis mechanisms with a pattern matching mechanism based on template correlation. Instead of using indirect statistical measures that lose detailed feature information, the system uses direct template matching with correlation coefficients to preserve and detect important fluctuation characteristics while maintaining computational simplicity

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS8615291B2Method, system and computer program method for detection of pathological fluctuations of physiological signals to diagnose human illness

Publication Date: 2013.12.24 NATIONAL INSTITUTES OF HEALTH

AI summary

Method, system, and computer program method for detecting pathological fluctuations of physiological signals to diagnose human illness. The method comprises performing a sliding window analysis to find sequences in physiological signal data that match amplitude- and duration-adjusted versions of a template function to within a specified tolerance.