CNNED ECG Artifact Removal for Continuous CPR Defibrillation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current automated external defibrillators (AEDs) require interruptions in cardiopulmonary resuscitation (CPR) for reliable analysis, leading to delays in delivering electrical shocks, which decreases survival probability during shockable cardiac arrhythmias like ventricular fibrillation.

Innovation Solution

A system utilizing a Convolutional Neural Network-based Encoder-Decoder (CNNED) structure to remove CPR artifacts from electrocardiogram (ECG) signals in real-time, allowing for continuous CPR and immediate shock delivery by distinguishing between shockable and non-shockable rhythms without interrupting CPR.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If CPR is interrupted for ECG analysis, then measurement precision of ECG signal is improved, but loss of time increases and productivity decreases

Engineering Contradiction:

ImproveECG signal analysis accuracyVSAvoidtime delay in shock delivery

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent introduces an intermediary signal processing system that uses adaptive filtering and template matching to separate the ECG signal from CPR artifacts. This intermediary processing layer allows continuous CPR to proceed while simultaneously extracting clean ECG signals for analysis, eliminating the need to interrupt CPR for signal acquisition.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces the mechanical interruption of CPR (physical stopping of compressions) with a signal processing approach. Instead of mechanically stopping the CPR to get a clean signal, the system uses digital signal processing techniques to filter artifacts and extract the ECG signal continuously, substituting a mechanical solution with an electronic/software-based one.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Reliability

If CPR is interrupted for reliable ECG analysis, then reliability of defibrillation decision is improved, but productivity decreases

Engineering Contradiction:

Improvedefibrillation decision accuracyVSAvoidspeed of treatment delivery

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The patent implements preliminary action by continuously processing and analyzing ECG signals during CPR without interruption. The system performs real-time artifact removal and rhythm analysis concurrently with ongoing CPR, rather than waiting until CPR is stopped. This allows the defibrillation decision to be prepared in advance with high reliability while CPR continues uninterrupted.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent maintains continuity of useful action by allowing CPR to proceed uninterrupted while simultaneously performing ECG analysis. The signal processing system operates continuously alongside the CPR, extracting diagnostic information without breaking the therapeutic action. This ensures both the reliability of analysis and the productivity of continuous blood flow maintenance.

Inventive Principle:

Principle #20Continuity of useful action

3Productivity

If CPR is continuously performed, then productivity is improved, but measurement precision of ECG signal deteriorates due to artifacts

Engineering Contradiction:

Improvecontinuous blood flow maintenanceVSAvoidECG signal quality

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The patent applies the extraction principle by separating the ECG signal from the CPR artifacts through adaptive filtering and template subtraction. The system identifies and removes the artifact components generated by chest compressions, extracting the underlying cardiac electrical activity. This allows continuous CPR to proceed while obtaining clean ECG measurements for accurate rhythm analysis.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The patent introduces an intermediary signal processing layer that acts as a mediator between the noisy ECG signal during CPR and the clean signal needed for analysis. The adaptive filter and template matching algorithms serve as intermediaries that transform the artifact-contaminated signal into a usable diagnostic signal, enabling continuous CPR with reliable measurement precision.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS20240342496A1Cardiopulmonary resuscitation, treatment, and analysis

Publication Date: 2024.10.17 UNIV OF CONNECTICUT

AI summary

An apparatus for treating a person having cardiac arrest includes a processor and a lead in communication with the processor, the lead being configured to receive a segment of electrocardiogram (ECG) data from the person while undergoing cardiopulmonary resuscitation (CPR). The apparatus also includes a non-transitory computer-readable medium having: a first Convolutional Neural Network-based Encoder-Decoder (CNNED) structure to reduce artifacts due to the CPR; a second CNNED structure cascaded with the first CNNED structure to further reduce artifacts; and instructions to determine a first arrhythmia classification using the first CNNED structure, determine a second arrhythmia classification using the second CNNED structure in response to the first arrhythmia classification indicating a shockable arrhythmia event; and transmit a signal to apply a defibrillation shock to the person in response to the first arrhythmia classification and the second arrhythmia classification indicating a shockable arrhythmia of the person.