Development of a Novel Convolution Neural Network for Arrhythmia Classification

Completed

• Conditions: Arrhythmias, Cardiac; Cardiac Arrest; Cardiac Arrythmias
• Interventions: Other: Neural Network Classifier

• Registration Number: NCT03662802
• Lead Sponsor: Scripps Clinic

Brief Summary

Identifying the correct arrhythmia at the time of a clinic event including cardiac arrest is of high priority to patients, healthcare organizations, and to public health. Recent developments in artificial intelligence and machine learning are providing new opportunities to rapidly and accurately diagnose cardiac arrhythmias and for how new mobile health and cardiac telemetry devices are used in patient care. The current investigation aims to validate a new artificial intelligence statistical approach called 'convolution neural network classifier' and its performance to different arrhythmias diagnosed on 12-lead ECGs and single-lead Holter/event monitoring. These arrhythmias include; atrial fibrillation, supraventricular tachycardia, AV-block, asystole, ventricular tachycardia and ventricular fibrillation, and will be benchmarked to the American Heart Association performance criteria (95% one-sided confidence interval of 67-92% based on arrhythmia type). In order to do so, the study approach is to create a large ECG database of de-identified raw ECG data, and to train the neural network on the ECG data in order to improve the diagnostic accuracy.

Detailed Description

Not available

Study Timeline

• Study First Submitted: 2018-09-05
• Study First Submitted QC: 2018-09-05
• Study First Posted: 2018-09-07
• Study Start: 2018-10-01
• Primary Completion: 2020-03-01
• Study Completion: 2020-10-01
• Status Verified: 2020-11
• Last Update Submitted: 2020-11-04
• Last Update Posted: 2020-11-06

Recruitment & Eligibility

• Status: COMPLETED
• Sex: All
• Target Recruitment: 25458

Inclusion Criteria

• All ECG data compiled from 12-lead ECG, single, and multiple lead databases

Exclusion Criteria

• None

Study & Design

• Study Type: OBSERVATIONAL
• Study Design: Not specified

Arm && Interventions

Group	Intervention	Description
ECG Data	Neural Network Classifier	Coded data including; wavelengths, amplitude, intervals, timing, frequence

Primary Outcome Measures

Name	Time	Method
Diagnostic Accuracy	1 YEAR	American Heart Association ECG Performance Criteria

Trial Locations

Locations (1)

Scripps Clinic; 🇺🇸 San Diego, California, United States