NCT03662802: AI-ECG

Development of a Novel Convolution Neural Network for Arrhythmia Classification

Completed Last updated 6 November 2020

What this trial tests

trial testing Neural Network Classifier in Arrhythmias, Cardiac in 25,458 participants. Completed in 1 October 2020.

Timeline

1 October 2018

Primary endpoint
1 March 2020

1 October 2020

Quick facts

Lead sponsor	Scripps Clinic
Status	Completed
Study type	OBSERVATIONAL
Enrollment	25,458
Start date	1 October 2018
Primary completion	1 March 2020
Estimated completion	1 October 2020
Sites	1 location across United States

Drugs / interventions tested

• Neural Network Classifier

Conditions studied

• Arrhythmias, Cardiac — all drugs for Arrhythmias, Cardiac →
• Cardiac Arrest — all drugs for Cardiac Arrest →
• Cardiac Arrythmias — all drugs for Cardiac Arrythmias →

Sponsor

Scripps Clinic

Who can join

Eligibility, any sex, with Arrhythmias, Cardiac or Cardiac Arrest. Patients with the condition only — healthy volunteers not accepted.

Sponsor's own description

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.

Publications & conference data

2 peer-reviewed publications reference this trial (live from Europe PMC):

1. Early diagnosis and better rhythm management to improve outcomes in patients with atrial fibrillation: the 8th AFNET/EHRA consensus conference.
   Schnabel RB, Marinelli EA, Arbelo E, Boriani G, et al · · 2023 · cited 131× · PMID 35894842 · DOI 10.1093/europace/euac062
2. Convolution Neural Network Algorithm for Shockable Arrhythmia Classification Within a Digitally Connected Automated External Defibrillator.
   Shen CP, Freed BC, Walter DP, Perry JC, et al · · 2023 · cited 11× · PMID 36942628 · DOI 10.1161/jaha.122.026974