Ventilator Breath Variability Detection via Spectral Entropy

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current mechanical ventilators do not effectively monitor and analyze breathing variability, a critical metric for predicting success in mechanical ventilation and detecting respiratory irregularities, which can indicate various pathological conditions.

Innovation Solution

A system and method for acquiring, calculating, and displaying breath variability metrics, including Spectral Energy and Spectral Entropy, to visually depict and automatically identify irregularities in patient respiratory data, using integrated sensors and algorithms to provide clinicians with insights into respiratory patterns and potential abnormalities.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If mechanical ventilators monitor and analyze breathing variability using spectral entropy calculations, then diagnostic precision and early detection of respiratory irregularities improve, but device complexity and computational requirements increase

Engineering Contradiction:

Improvebreathing variability detectionVSAvoidsystem complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent segments the respiratory signal into discrete breaths and further divides each breath into phases (inspiration, expiration) for separate spectral analysis. This segmentation allows complex variability detection to be broken down into manageable computational steps, improving measurement precision without overwhelming system complexity

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system performs preliminary actions by pre-processing respiratory signals to extract breath-by-breath parameters before conducting spectral entropy calculations. This preliminary extraction of flow rates, volumes, and timing parameters simplifies the subsequent variability analysis and reduces real-time computational burden

Inventive Principle:

Principle #10Preliminary action

2Measurement precision

If spectral entropy is calculated from resampled spectral energy to quantify breath variability, then measurement precision of respiratory irregularities improves, but computational time and processing complexity increase

Engineering Contradiction:

Improvebreath variability quantificationVSAvoidcomputational time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent implements periodic action by calculating spectral entropy at regular intervals (e.g., every minute or per breath cycle) rather than continuously. This periodic computation maintains measurement precision for detecting respiratory irregularities while significantly reducing overall computational time and processing load

Inventive Principle:

Principle #19Periodic action

Solution Approach 2:

The system applies partial action by focusing spectral entropy calculations only on relevant frequency bands and breath phases that contain diagnostic information. This selective analysis achieves sufficient measurement precision without the computational overhead of analyzing the entire signal spectrum continuously

Inventive Principle:

Principle #16Partial or excessive action

3Reliability

If breath variability metrics are continuously monitored and displayed in graphical form, then early detection of respiratory irregularities improves, but information processing load and display complexity increase

Engineering Contradiction:

Improverespiratory irregularity detectionVSAvoiddata processing load

Core Design Contradiction:

ReliabilityVSLoss of information

Solution Approach 1:

The patent extracts and displays only the most clinically relevant breath variability metrics (spectral entropy values, trend lines, and anomaly markers) rather than presenting all raw spectral data. This extraction approach maintains reliability for detecting respiratory irregularities while reducing information processing load and simplifying the graphical display for clinicians

Inventive Principle:

Principle #2Taking out (Extraction)

Data Source

PatentUS20250017488A1System and methods for automatically identifying a breath variability event from patient respiratory data associated with a mechanical ventilator

Publication Date: 2025.01.16 BREAS MEDICAL AB

AI summary

A system and method are provided for identifying breath variability events from patient respiratory data obtained during the operation of a mechanical ventilator. The ventilator monitors and saves patient respiratory data during operation. The method includes extracting treatment parameters from a ventilation prescription, and using the treatment parameters to determine an Epoch size and a frequency band for analysis. An input signal (flow or pressure) is extracted from the patient data and from the input signal at least one parameter is extracted and analyzed. A Spectral Energy (Es) of the input signal is determined based on the signal parameter, an Epoch size and a frequency band and a Spectral Entropy (SE) is determined based on the Spectral Energy (Es). The Spectral Entropy may then be displayed in graphical form to identify breath variability events over the Epoch size. The method may further classify the type and degree of the events.