Development of a Novel Convolution Neural Network for Arrhythmia Classification

NCT03662802 | Completed

• 1 other identifier: 027527
• Study Type: observational
• Target: 25,458
• Locations: 1 country
• Sites: 1

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.

Conditions

Arrhythmias, Cardiac; Cardiac Arrest; Cardiac Arrythmias

Keywords

artificial intelligence; machine learning; neural network; cardiac arrhythmia; ECG; EKG

Outcome Measures

Primary Outcomes (1)

• Diagnostic Accuracy

  American Heart Association ECG Performance Criteria

  1 YEAR

Study Arms (1)

ECG Data

Coded data including; wavelengths, amplitude, intervals, timing, frequence

Other: Neural Network Classifier

Interventions

Neural Network Classifier OTHER

The convolutional neural network is configured to receive an electrocardiogram segment as an input and to generate an output indicative of whether the received electrocardiogram segment represents a cardiac arrhythmia. No specific features of the electrocardiogram are identified to the convolutional neural network, and the received electrocardiogram segment is not filtered, transformed, or processed prior to reception by the algorithm. The algorithm is trained in a similar manner - the electrocardiogram segments are the sole input to the convolutional neural network.

ECG Data

Eligibility Criteria

• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Child (0-17), Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

Individuals undergoing a 12-lead ECG or Holter/Event monitoring

You may qualify if:

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

You may not qualify if:

• None

Sponsors & Collaborators

• Scripps Clinic: lead

Study Sites (1)

Scripps Clinic

San Diego, California, 92037, United States

Location

Related Publications (14)

• Johnson KW, Torres Soto J, Glicksberg BS, Shameer K, Miotto R, Ali M, Ashley E, Dudley JT. Artificial Intelligence in Cardiology. J Am Coll Cardiol. 2018 Jun 12;71(23):2668-2679. doi: 10.1016/j.jacc.2018.03.521.

  PMID: 29880128 BACKGROUND

• Kiranyaz S, Ince T, Gabbouj M. Real-Time Patient-Specific ECG Classification by 1-D Convolutional Neural Networks. IEEE Trans Biomed Eng. 2016 Mar;63(3):664-75. doi: 10.1109/TBME.2015.2468589. Epub 2015 Aug 14.

  PMID: 26285054 BACKGROUND

• Bhavnani SP, Parakh K, Atreja A, Druz R, Graham GN, Hayek SS, Krumholz HM, Maddox TM, Majmudar MD, Rumsfeld JS, Shah BR. 2017 Roadmap for Innovation-ACC Health Policy Statement on Healthcare Transformation in the Era of Digital Health, Big Data, and Precision Health: A Report of the American College of Cardiology Task Force on Health Policy Statements and Systems of Care. J Am Coll Cardiol. 2017 Nov 28;70(21):2696-2718. doi: 10.1016/j.jacc.2017.10.018. No abstract available.

  PMID: 29169478 RESULT

• Bhavnani SP, Narula J, Sengupta PP. Mobile technology and the digitization of healthcare. Eur Heart J. 2016 May 7;37(18):1428-38. doi: 10.1093/eurheartj/ehv770. Epub 2016 Feb 11.

  PMID: 26873093 RESULT

• Vandendriessche B, Abas M, Dick TE, Loparo KA, Jacono FJ. A Framework for Patient State Tracking by Classifying Multiscalar Physiologic Waveform Features. IEEE Trans Biomed Eng. 2017 Dec;64(12):2890-2900. doi: 10.1109/TBME.2017.2684244. Epub 2017 Mar 17.

  PMID: 28328498 RESULT

• Arvanaghi R, Daneshvar S, Seyedarabi H, Goshvarpour A. Fusion of ECG and ABP signals based on wavelet transform for cardiac arrhythmias classification. Comput Methods Programs Biomed. 2017 Nov;151:71-78. doi: 10.1016/j.cmpb.2017.08.013. Epub 2017 Aug 24.

  PMID: 28947007 RESULT

• Figuera C, Irusta U, Morgado E, Aramendi E, Ayala U, Wik L, Kramer-Johansen J, Eftestol T, Alonso-Atienza F. Machine Learning Techniques for the Detection of Shockable Rhythms in Automated External Defibrillators. PLoS One. 2016 Jul 21;11(7):e0159654. doi: 10.1371/journal.pone.0159654. eCollection 2016.

  PMID: 27441719 RESULT

• Li Q, Rajagopalan C, Clifford GD. Ventricular fibrillation and tachycardia classification using a machine learning approach. IEEE Trans Biomed Eng. 2014 Jun;61(6):1607-13. doi: 10.1109/TBME.2013.2275000. Epub 2013 Jul 26.

  PMID: 23899591 RESULT

• Lyon A, Minchole A, Martinez JP, Laguna P, Rodriguez B. Computational techniques for ECG analysis and interpretation in light of their contribution to medical advances. J R Soc Interface. 2018 Jan;15(138):20170821. doi: 10.1098/rsif.2017.0821.

  PMID: 29321268 RESULT

• Mjahad A, Rosado-Munoz A, Bataller-Mompean M, Frances-Villora JV, Guerrero-Martinez JF. Ventricular Fibrillation and Tachycardia detection from surface ECG using time-frequency representation images as input dataset for machine learning. Comput Methods Programs Biomed. 2017 Apr;141:119-127. doi: 10.1016/j.cmpb.2017.02.010. Epub 2017 Feb 10.

  PMID: 28241963 RESULT

• Xiong Z, Nash MP, Cheng E, Fedorov VV, Stiles MK, Zhao J. ECG signal classification for the detection of cardiac arrhythmias using a convolutional recurrent neural network. Physiol Meas. 2018 Sep 24;39(9):094006. doi: 10.1088/1361-6579/aad9ed.

  PMID: 30102248 RESULT

• Fan X, Yao Q, Cai Y, Miao F, Sun F, Li Y. Multiscaled Fusion of Deep Convolutional Neural Networks for Screening Atrial Fibrillation From Single Lead Short ECG Recordings. IEEE J Biomed Health Inform. 2018 Nov;22(6):1744-1753. doi: 10.1109/JBHI.2018.2858789. Epub 2018 Aug 7.

  PMID: 30106699 RESULT

• Warrick PA, Nabhan Homsi M. Ensembling convolutional and long short-term memory networks for electrocardiogram arrhythmia detection. Physiol Meas. 2018 Oct 30;39(11):114002. doi: 10.1088/1361-6579/aad386.

  PMID: 30010088 RESULT

• Shen CP, Freed BC, Walter DP, Perry JC, Barakat AF, Elashery ARA, Shah KS, Kutty S, McGillion M, Ng FS, Khedraki R, Nayak KR, Rogers JD, Bhavnani SP. Convolution Neural Network Algorithm for Shockable Arrhythmia Classification Within a Digitally Connected Automated External Defibrillator. J Am Heart Assoc. 2023 Apr 18;12(8):e026974. doi: 10.1161/JAHA.122.026974. Epub 2023 Mar 21.

  PMID: 36942628 DERIVED

MeSH Terms

Conditions

Arrhythmias, Cardiac; Heart Arrest

Condition Hierarchy (Ancestors)

Heart Diseases; Cardiovascular Diseases; Pathologic Processes; Pathological Conditions, Signs and Symptoms

Study Officials

• Sanjeev Bhavnani, MD

  Scripps Clinic Medical Group

  PRINCIPAL INVESTIGATOR

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: OTHER
• Target Duration: 1 Year
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Principal Investigator - Healthcare Innovation

Study Record Dates

• First Submitted: September 5, 2018
• First Posted: September 7, 2018
• Study Start: October 1, 2018
• Primary Completion: March 1, 2020
• Study Completion: October 1, 2020
• Last Updated: November 6, 2020

Record last verified: 2020-11

Data Sharing

• IPD Sharing: Will not share

Locations

US (1)