Leveraging blockchain for retraining deep learning architecture in patient-specific arrhythmia classification

Research output: Chapter in Book/Report/Conference proceedingConference contribution

9 Citations (Scopus)

Abstract

Stacked Denoising Autoencoders (SDA) are deep networks which have gained popularity owing to their superior performance in image classification applications, but they haven't been used much in healthcare applications. SDA can be efficiently retrained to adapt to large streams of data, and this property is used in this work to develop a technique for classification of arrhythmias in a patient-specific manner. This approach is particularly useful in continuous remote systems because they gather large amounts of data for longer periods of time. Blockchain is a decentralized distributed ledger which secures transactions with cryptography. It is proposed as an access control manager to securely store and access data required by the classifier during retraining in real-time from an external data storage. This work uses MIT-BIH Arrhythmia database and the results show an increased accuracy for Ventricular Ectopic Beats (VEB) (99.15%) and Supraventricular Ectopic Beats (SVEB) (98.55%), which is higher than the published results of deep networks that are not retrained.

Original languageEnglish (US)
Title of host publication2018 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages393-397
Number of pages5
Volume2018-January
ISBN (Electronic)9781538624050
DOIs
StatePublished - Apr 6 2018
Event2018 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2018 - Las Vegas, United States
Duration: Mar 4 2018Mar 7 2018

Other

Other2018 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2018
CountryUnited States
CityLas Vegas
Period3/4/183/7/18

Fingerprint

Cardiac Arrhythmias
Learning
Ventricular Premature Complexes
Image classification
Information Storage and Retrieval
Access control
Cryptography
Managers
Classifiers
Databases
Delivery of Health Care
Data storage equipment
Deep learning

Keywords

  • Arrhythmia Classification
  • Blockchain
  • Patient Specific
  • Remote Continuous Health Systems
  • Retraining
  • Stacked Denoising Autoencoders

ASJC Scopus subject areas

  • Computer Science Applications
  • Biomedical Engineering
  • Health Informatics

Cite this

Juneja, A., & Marefat, M. M. (2018). Leveraging blockchain for retraining deep learning architecture in patient-specific arrhythmia classification. In 2018 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2018 (Vol. 2018-January, pp. 393-397). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/BHI.2018.8333451

Leveraging blockchain for retraining deep learning architecture in patient-specific arrhythmia classification. / Juneja, Amit; Marefat, Michael Mahmoud.

2018 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2018. Vol. 2018-January Institute of Electrical and Electronics Engineers Inc., 2018. p. 393-397.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Juneja, A & Marefat, MM 2018, Leveraging blockchain for retraining deep learning architecture in patient-specific arrhythmia classification. in 2018 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2018. vol. 2018-January, Institute of Electrical and Electronics Engineers Inc., pp. 393-397, 2018 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2018, Las Vegas, United States, 3/4/18. https://doi.org/10.1109/BHI.2018.8333451
Juneja A, Marefat MM. Leveraging blockchain for retraining deep learning architecture in patient-specific arrhythmia classification. In 2018 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2018. Vol. 2018-January. Institute of Electrical and Electronics Engineers Inc. 2018. p. 393-397 https://doi.org/10.1109/BHI.2018.8333451
Juneja, Amit ; Marefat, Michael Mahmoud. / Leveraging blockchain for retraining deep learning architecture in patient-specific arrhythmia classification. 2018 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2018. Vol. 2018-January Institute of Electrical and Electronics Engineers Inc., 2018. pp. 393-397
@inproceedings{d71963be239b4b6aba349f6ba394b773,
title = "Leveraging blockchain for retraining deep learning architecture in patient-specific arrhythmia classification",
abstract = "Stacked Denoising Autoencoders (SDA) are deep networks which have gained popularity owing to their superior performance in image classification applications, but they haven't been used much in healthcare applications. SDA can be efficiently retrained to adapt to large streams of data, and this property is used in this work to develop a technique for classification of arrhythmias in a patient-specific manner. This approach is particularly useful in continuous remote systems because they gather large amounts of data for longer periods of time. Blockchain is a decentralized distributed ledger which secures transactions with cryptography. It is proposed as an access control manager to securely store and access data required by the classifier during retraining in real-time from an external data storage. This work uses MIT-BIH Arrhythmia database and the results show an increased accuracy for Ventricular Ectopic Beats (VEB) (99.15{\%}) and Supraventricular Ectopic Beats (SVEB) (98.55{\%}), which is higher than the published results of deep networks that are not retrained.",
keywords = "Arrhythmia Classification, Blockchain, Patient Specific, Remote Continuous Health Systems, Retraining, Stacked Denoising Autoencoders",
author = "Amit Juneja and Marefat, {Michael Mahmoud}",
year = "2018",
month = "4",
day = "6",
doi = "10.1109/BHI.2018.8333451",
language = "English (US)",
volume = "2018-January",
pages = "393--397",
booktitle = "2018 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Leveraging blockchain for retraining deep learning architecture in patient-specific arrhythmia classification

AU - Juneja, Amit

AU - Marefat, Michael Mahmoud

PY - 2018/4/6

Y1 - 2018/4/6

N2 - Stacked Denoising Autoencoders (SDA) are deep networks which have gained popularity owing to their superior performance in image classification applications, but they haven't been used much in healthcare applications. SDA can be efficiently retrained to adapt to large streams of data, and this property is used in this work to develop a technique for classification of arrhythmias in a patient-specific manner. This approach is particularly useful in continuous remote systems because they gather large amounts of data for longer periods of time. Blockchain is a decentralized distributed ledger which secures transactions with cryptography. It is proposed as an access control manager to securely store and access data required by the classifier during retraining in real-time from an external data storage. This work uses MIT-BIH Arrhythmia database and the results show an increased accuracy for Ventricular Ectopic Beats (VEB) (99.15%) and Supraventricular Ectopic Beats (SVEB) (98.55%), which is higher than the published results of deep networks that are not retrained.

AB - Stacked Denoising Autoencoders (SDA) are deep networks which have gained popularity owing to their superior performance in image classification applications, but they haven't been used much in healthcare applications. SDA can be efficiently retrained to adapt to large streams of data, and this property is used in this work to develop a technique for classification of arrhythmias in a patient-specific manner. This approach is particularly useful in continuous remote systems because they gather large amounts of data for longer periods of time. Blockchain is a decentralized distributed ledger which secures transactions with cryptography. It is proposed as an access control manager to securely store and access data required by the classifier during retraining in real-time from an external data storage. This work uses MIT-BIH Arrhythmia database and the results show an increased accuracy for Ventricular Ectopic Beats (VEB) (99.15%) and Supraventricular Ectopic Beats (SVEB) (98.55%), which is higher than the published results of deep networks that are not retrained.

KW - Arrhythmia Classification

KW - Blockchain

KW - Patient Specific

KW - Remote Continuous Health Systems

KW - Retraining

KW - Stacked Denoising Autoencoders

UR - http://www.scopus.com/inward/record.url?scp=85050893998&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85050893998&partnerID=8YFLogxK

U2 - 10.1109/BHI.2018.8333451

DO - 10.1109/BHI.2018.8333451

M3 - Conference contribution

AN - SCOPUS:85050893998

VL - 2018-January

SP - 393

EP - 397

BT - 2018 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -