Multimodal Physiological Change Detection for Respiratory Distress

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for detecting changes in a patient's physiological state, particularly respiratory distress, are limited by their reliance on single-modal analysis of physiological data, leading to false alarms and inadequate characterization of the patient's overall condition, and often require complex signal processing and multiple sensors.

Innovation Solution

A multimodal method that correlates and fuses data from multiple types of physiological signals, including EEG, EMG, ECG, and respiratory activity, using Riemannian and statistical distances to determine deviations from a reference state, reducing noise and improving detection accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If single-modal analysis of physiological data is used, then device complexity is reduced, but measurement precision and reliability deteriorate due to false alarms and inadequate characterization

Engineering Contradiction:
Improvecomplexity of signal processingVSAvoiddetection accuracy
Core Design Contradiction:
Device complexityVSMeasurement precision

Solution Approach 1:

The patent combines multiple physiological signals (EEG, EMG, ECG, respiratory activity) into a unified analysis framework. By merging these different modalities of data, the system achieves more accurate detection of respiratory distress while maintaining manageable complexity through integrated processing.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The monitoring system is designed to handle multiple types of physiological signals simultaneously, making it a multi-functional device that can detect various aspects of respiratory status. This universal approach improves measurement precision without requiring separate dedicated systems for each signal type.

Inventive Principle:
Principle #6Universality (Multi-functionality)

2Measurement precision

If multiple types of physiological signals are analyzed separately, then measurement precision improves, but device complexity increases due to need for multiple sensors and complex processing

Engineering Contradiction:
Improvecharacterization accuracyVSAvoidnumber of sensors and processing steps
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent merges multiple physiological signal analyses into a single integrated system. Rather than using separate systems for each signal type, the invention combines EEG, EMG, ECG, and respiratory signal processing into one unified monitoring device that correlates all signals simultaneously.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The system uses correlation analysis as an intermediary mechanism to integrate multiple physiological signals. By computing correlations between different signal types, the system achieves comprehensive characterization without requiring complex separate processing pathways for each signal.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Reliability

If complex signal processing is applied to confirm physiological changes, then reliability improves, but productivity decreases due to extended processing time

Engineering Contradiction:
Improveconfirmation of physiological changeVSAvoidreal-time detection speed
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The patent replaces complex sequential signal processing with correlation-based analysis that can be computed more efficiently. By substituting traditional multi-step confirmation procedures with correlation calculations across multiple signals, the system maintains reliability while improving processing speed for real-time detection.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentEP4412517B1Multimodal method for detecting a change in a patient's physiological condition and device for monitoring a patient so as to implement such a method
Publication Date: 2025.12.03 INST NAT DE LA SANTE & DE LA RECHERCHE MEDICALE (INSERM)
  • EP4412517B1 patent drawingFigure 1~2a
  • EP4412517B1 patent drawingFigure 2b
  • EP4412517B1 patent drawingFigure 3

AI summary

The invention relates to a method for detecting a change in a patient's physiological condition with respect to a reference physiological condition. The method is based on a multimodal analysis that involves measurements of electroencephalography signals S1 from the patient and at least one other physiological signal SN+1 (N ≥ 1) from the patient. Based on these measurements, the invention proposes calculating distances di(m) associated with the electroencephalography measurements and with the measurements of the other physiological signals and fusing these data, the data having previously undergone a certain number of mathematical processing operations. In the context of the invention, the fused data may be assigned a weighting coefficient chosen according to one or more a priori or a posteriori criteria.