Heart Rate Variability Pattern Analysis via Multidimensional Phase Space

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current methods fail to provide a compact, universal, and adaptable representation of cyclic or quasi-periodical dissipative systems, particularly for heart rate variability analysis, which is essential for diagnosing and prognosing cardiac health, as they either overlap time scales or conceal complex multidimensional sequences, making it difficult to identify universal variability patterns and pathological arrhythmias.

Innovation Solution

A system that calculates and visually represents the normalized variability of time intervals between heart cycles using a specific algorithmic transformation, allowing for spatial representation in multiple dimensions, including color, to identify common patterns and correlations, and compare individual systems with universal patterns, independent of time scales.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If Fourier transform or Wavelet transforms are used for time scale analysis, then frequency domain information is obtained, but time scales overlap and universal variability patterns become inaccessible

Engineering Contradiction:
Improveuniversal variability patternsVSAvoidtime scale overlap
Core Design Contradiction:
Loss of informationVSDevice complexity

Solution Approach 1:

The patent transforms the one-dimensional time series of heart rate intervals into N-dimensional space (where N≥2), creating a multidimensional phase space representation. This dimensional transformation allows separation of overlapping time scales that cannot be distinguished in traditional frequency domain analysis, making universal variability patterns accessible without the limitations of Fourier or Wavelet transforms.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

Solution Approach 2:

The patent segments the continuous time series into discrete vectors of N consecutive time intervals, creating N-dimensional vectors that represent local temporal patterns. This segmentation approach allows analysis of variability at multiple scales simultaneously without the overlapping problems of traditional transforms, as each vector captures a specific temporal window's characteristics.

Inventive Principle:
Principle #1Segmentation

2Device complexity

If traditional HRV analysis methods are used, then time domain parameters are calculated, but complex multidimensional sequences are concealed and compact representation is not achieved

Engineering Contradiction:
Improverepresentation compactnessVSAvoidmultidimensional sequences
Core Design Contradiction:
Device complexityVSLoss of information

Solution Approach 1:

The patent merges multiple time domain parameters (mean, standard deviation, skewness, kurtosis, etc.) into a single N-dimensional vector for each window of consecutive intervals. This consolidation provides a compact representation that preserves all multidimensional sequence information, allowing comprehensive characterization of heart rate variability in a unified structure that is both compact and information-rich.

Inventive Principle:
Principle #5Merging (Combining)

3Measurement precision

If high dimensional representation is used to capture complex patterns, then identification accuracy improves, but visualization and interpretation become difficult

Engineering Contradiction:
Improvepattern identification accuracyVSAvoidvisualization and interpretation
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

The patent applies different analytical treatments to different aspects of the N-dimensional vectors. Statistical parameters (mean, standard deviation, skewness, kurtosis) are calculated to characterize local temporal patterns within each window, while the full N-dimensional vectors preserve global sequence information. This local quality approach enables both high-dimensional pattern recognition and simplified statistical interpretation.

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The patent uses color coding to represent different dimensions or characteristics of the N-dimensional vectors in visualizations. By mapping high-dimensional data to visual attributes like color, the system enables intuitive interpretation of complex patterns while maintaining the full dimensional information for accurate pattern identification and comparison with reference patterns.

Inventive Principle:
Principle #32Color changes

Data Source

PatentEP3420891B1System for obtaining useful data associated with heart rate variability pattern
Publication Date: 2024.03.20 UNIV DE SEVILLA
  • EP3420891B1 patent drawingFigure 1
  • EP3420891B1 patent drawingFigure 2(a)~2(d)
  • EP3420891B1 patent drawingFigure 3(a)~3(b3)

AI summary

The invention relates to a method for providing a description, graphical representation, and a graphical identification of specific operating patterns of quasi-periodic cyclic systems, such as, but not limited to, reciprocating combustion engines, rotary machines, or biological organs such as the heart. The invention also relates to a method for calculating an indicator evaluating the heart health or condition of an individual, as well as for diagnosing and issuing prognoses relating to the functionality, pathology, or standard of health of a machine or organism equipped with a motor or organ that operates cyclically, and to provide a description, a compact graphical representation, and a graphical identification of specific operating patterns of dynamic systems, e.g. economic systems such as the stock market.