A nanowatt real-time cardiac autonomic neuropathy detector

Temesghen Tekeste, Hani Saleh, Baker Mohammad, Ahsan Khandoker, Herbert Jelinek, Mohammed Ismail

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

This paper presents an electrocardiogram (ECG) processor on chip for full ECG feature extraction and cardiac autonomic neuropathy (CAN) classification. Full ECG extraction is performed using absolute value curve length transform (A-CLT) for QRSpeak detection and using low-pass differentiation for other ECG features such as QRSon, QRSoff, Pwave, and Twave. The proposed QRS detector attained a sensitivity of 99.37% and predictivity of 99.38%. The extracted QRSpeak to QRSpeak intervals (RR intervals) along with QT intervals enable CAN severity detection, which is a cardiac arrhythmia usually seen in diabetic patients leading to increased risk of sudden cardiac death. This paper presents the first hardware real-time implementation of CAN severity detector that is based on RR variability and QT variability analysis. RR variability metrics are based on mean RR interval and root mean square of standard differences of the RR intervals. The proposed architecture was implemented in 65-nm technology and consumed 75 nW only at 0.6 V, when operating at 250 Hz. Ultralow power dissipation of the system enables it to be integrated into wearable healthcare devices.

Original languageEnglish
Pages (from-to)739-750
Number of pages12
JournalIEEE Transactions on Biomedical Circuits and Systems
Volume12
Issue number4
Early online date12 Jul 2018
DOIs
Publication statusPublished - 01 Aug 2018

Fingerprint

Electrocardiography
Detectors
Feature extraction
Energy dissipation
Hardware

Cite this

Tekeste, Temesghen ; Saleh, Hani ; Mohammad, Baker ; Khandoker, Ahsan ; Jelinek, Herbert ; Ismail, Mohammed. / A nanowatt real-time cardiac autonomic neuropathy detector. In: IEEE Transactions on Biomedical Circuits and Systems. 2018 ; Vol. 12, No. 4. pp. 739-750.
@article{f2d2a903eaa2482faf8b3bd3cb2d8d70,
title = "A nanowatt real-time cardiac autonomic neuropathy detector",
abstract = "This paper presents an electrocardiogram (ECG) processor on chip for full ECG feature extraction and cardiac autonomic neuropathy (CAN) classification. Full ECG extraction is performed using absolute value curve length transform (A-CLT) for QRSpeak detection and using low-pass differentiation for other ECG features such as QRSon, QRSoff, Pwave, and Twave. The proposed QRS detector attained a sensitivity of 99.37{\%} and predictivity of 99.38{\%}. The extracted QRSpeak to QRSpeak intervals (RR intervals) along with QT intervals enable CAN severity detection, which is a cardiac arrhythmia usually seen in diabetic patients leading to increased risk of sudden cardiac death. This paper presents the first hardware real-time implementation of CAN severity detector that is based on RR variability and QT variability analysis. RR variability metrics are based on mean RR interval and root mean square of standard differences of the RR intervals. The proposed architecture was implemented in 65-nm technology and consumed 75 nW only at 0.6 V, when operating at 250 Hz. Ultralow power dissipation of the system enables it to be integrated into wearable healthcare devices.",
keywords = "Cardiac autonomic neuropathy, Detectors, ECG features, Electrocardiography, Entropy, Feature extraction, Heart rate variability, QTVI, Random access memory, Transforms, ultra low power, variability, wearable sensors",
author = "Temesghen Tekeste and Hani Saleh and Baker Mohammad and Ahsan Khandoker and Herbert Jelinek and Mohammed Ismail",
note = "Includes bibliographical references.",
year = "2018",
month = "8",
day = "1",
doi = "10.1109/TBCAS.2018.2833624",
language = "English",
volume = "12",
pages = "739--750",
journal = "IEEE Transactions on Biomedical Circuits and Systems",
issn = "1932-4545",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
number = "4",

}

A nanowatt real-time cardiac autonomic neuropathy detector. / Tekeste, Temesghen; Saleh, Hani; Mohammad, Baker; Khandoker, Ahsan; Jelinek, Herbert; Ismail, Mohammed.

In: IEEE Transactions on Biomedical Circuits and Systems, Vol. 12, No. 4, 01.08.2018, p. 739-750.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A nanowatt real-time cardiac autonomic neuropathy detector

AU - Tekeste, Temesghen

AU - Saleh, Hani

AU - Mohammad, Baker

AU - Khandoker, Ahsan

AU - Jelinek, Herbert

AU - Ismail, Mohammed

N1 - Includes bibliographical references.

PY - 2018/8/1

Y1 - 2018/8/1

N2 - This paper presents an electrocardiogram (ECG) processor on chip for full ECG feature extraction and cardiac autonomic neuropathy (CAN) classification. Full ECG extraction is performed using absolute value curve length transform (A-CLT) for QRSpeak detection and using low-pass differentiation for other ECG features such as QRSon, QRSoff, Pwave, and Twave. The proposed QRS detector attained a sensitivity of 99.37% and predictivity of 99.38%. The extracted QRSpeak to QRSpeak intervals (RR intervals) along with QT intervals enable CAN severity detection, which is a cardiac arrhythmia usually seen in diabetic patients leading to increased risk of sudden cardiac death. This paper presents the first hardware real-time implementation of CAN severity detector that is based on RR variability and QT variability analysis. RR variability metrics are based on mean RR interval and root mean square of standard differences of the RR intervals. The proposed architecture was implemented in 65-nm technology and consumed 75 nW only at 0.6 V, when operating at 250 Hz. Ultralow power dissipation of the system enables it to be integrated into wearable healthcare devices.

AB - This paper presents an electrocardiogram (ECG) processor on chip for full ECG feature extraction and cardiac autonomic neuropathy (CAN) classification. Full ECG extraction is performed using absolute value curve length transform (A-CLT) for QRSpeak detection and using low-pass differentiation for other ECG features such as QRSon, QRSoff, Pwave, and Twave. The proposed QRS detector attained a sensitivity of 99.37% and predictivity of 99.38%. The extracted QRSpeak to QRSpeak intervals (RR intervals) along with QT intervals enable CAN severity detection, which is a cardiac arrhythmia usually seen in diabetic patients leading to increased risk of sudden cardiac death. This paper presents the first hardware real-time implementation of CAN severity detector that is based on RR variability and QT variability analysis. RR variability metrics are based on mean RR interval and root mean square of standard differences of the RR intervals. The proposed architecture was implemented in 65-nm technology and consumed 75 nW only at 0.6 V, when operating at 250 Hz. Ultralow power dissipation of the system enables it to be integrated into wearable healthcare devices.

KW - Cardiac autonomic neuropathy

KW - Detectors

KW - ECG features

KW - Electrocardiography

KW - Entropy

KW - Feature extraction

KW - Heart rate variability

KW - QTVI

KW - Random access memory

KW - Transforms

KW - ultra low power

KW - variability

KW - wearable sensors

UR - http://www.scopus.com/inward/record.url?scp=85049945039&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85049945039&partnerID=8YFLogxK

U2 - 10.1109/TBCAS.2018.2833624

DO - 10.1109/TBCAS.2018.2833624

M3 - Article

C2 - 30010586

AN - SCOPUS:85049945039

VL - 12

SP - 739

EP - 750

JO - IEEE Transactions on Biomedical Circuits and Systems

JF - IEEE Transactions on Biomedical Circuits and Systems

SN - 1932-4545

IS - 4

ER -