Time-series network analysis for detecting cardiac autonomic neuropathy using RR interval data

Chandan Karmakar; Ahsan Khandoker; Herbert Jelinek; Marimuthu Palaniswami

Time-series network analysis for detecting cardiac autonomic neuropathy using RR interval data

Chandan Karmakar
, Ahsan Khandoker
, Herbert Jelinek
, Marimuthu Palaniswami

Biomedical Engineering & Biotechnology

University of Melbourne

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Cardiovascular autonomic neuropathy (CAN) is highly prevalent and a serious complication in patients with diabetes mellitus. In this study, we investigate the effect of changing the degree and data length on network properties (transition asymmetry and network efficiency) to differentiate negative CAN (NCAN) subjects from definite CAN (DCAN). Forty-one patients with Type 2 diabetes mellitus were included in the study: 15 patients had definite CAN (DCAN), whilst the remaining 26 were negative for CAN (NCAN), being without clinical signs and symptoms of CAN. Symbolic Aggregate approximation (SAX) was used as the discretization procedure to convert the heart rate variability (HRV) time-series signal to network. The optimal degree (m) and data length (n) were found to be m_opt = 270 and n_opt = 200 respectively with leave-one-out accuracy of 85.37% using transition asymmetry (A(G)) and network efficiency (EF) indexes. Both, A(G) and EF indexes are found to be a potential parameter for detecting CAN in diabetes.

Original language	British English
Title of host publication	Computing in Cardiology 2013, CinC 2013
Pages	97-100
Number of pages	4
State	Published - 2013
Event	2013 40th Computing in Cardiology Conference, CinC 2013 - Zaragoza, Spain Duration: 22 Sep 2013 → 25 Sep 2013

Publication series

Name	Computing in Cardiology
Volume	40
ISSN (Print)	2325-8861
ISSN (Electronic)	2325-887X

Conference

Conference	2013 40th Computing in Cardiology Conference, CinC 2013
Country/Territory	Spain
City	Zaragoza
Period	22/09/13 → 25/09/13

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

OpenUrl availability

Full text

Cite this

@inproceedings{0b80c878533c4f10b074ab3a7e021612,

title = "Time-series network analysis for detecting cardiac autonomic neuropathy using RR interval data",

abstract = "Cardiovascular autonomic neuropathy (CAN) is highly prevalent and a serious complication in patients with diabetes mellitus. In this study, we investigate the effect of changing the degree and data length on network properties (transition asymmetry and network efficiency) to differentiate negative CAN (NCAN) subjects from definite CAN (DCAN). Forty-one patients with Type 2 diabetes mellitus were included in the study: 15 patients had definite CAN (DCAN), whilst the remaining 26 were negative for CAN (NCAN), being without clinical signs and symptoms of CAN. Symbolic Aggregate approximation (SAX) was used as the discretization procedure to convert the heart rate variability (HRV) time-series signal to network. The optimal degree (m) and data length (n) were found to be mopt = 270 and nopt = 200 respectively with leave-one-out accuracy of 85.37\% using transition asymmetry (A(G)) and network efficiency (EF) indexes. Both, A(G) and EF indexes are found to be a potential parameter for detecting CAN in diabetes.",

author = "Chandan Karmakar and Ahsan Khandoker and Herbert Jelinek and Marimuthu Palaniswami",

year = "2013",

language = "British English",

isbn = "9781479908844",

series = "Computing in Cardiology",

pages = "97--100",

booktitle = "Computing in Cardiology 2013, CinC 2013",

note = "2013 40th Computing in Cardiology Conference, CinC 2013 ; Conference date: 22-09-2013 Through 25-09-2013",

}

TY - GEN

T1 - Time-series network analysis for detecting cardiac autonomic neuropathy using RR interval data

AU - Karmakar, Chandan

AU - Khandoker, Ahsan

AU - Jelinek, Herbert

AU - Palaniswami, Marimuthu

PY - 2013

Y1 - 2013

N2 - Cardiovascular autonomic neuropathy (CAN) is highly prevalent and a serious complication in patients with diabetes mellitus. In this study, we investigate the effect of changing the degree and data length on network properties (transition asymmetry and network efficiency) to differentiate negative CAN (NCAN) subjects from definite CAN (DCAN). Forty-one patients with Type 2 diabetes mellitus were included in the study: 15 patients had definite CAN (DCAN), whilst the remaining 26 were negative for CAN (NCAN), being without clinical signs and symptoms of CAN. Symbolic Aggregate approximation (SAX) was used as the discretization procedure to convert the heart rate variability (HRV) time-series signal to network. The optimal degree (m) and data length (n) were found to be mopt = 270 and nopt = 200 respectively with leave-one-out accuracy of 85.37% using transition asymmetry (A(G)) and network efficiency (EF) indexes. Both, A(G) and EF indexes are found to be a potential parameter for detecting CAN in diabetes.

AB - Cardiovascular autonomic neuropathy (CAN) is highly prevalent and a serious complication in patients with diabetes mellitus. In this study, we investigate the effect of changing the degree and data length on network properties (transition asymmetry and network efficiency) to differentiate negative CAN (NCAN) subjects from definite CAN (DCAN). Forty-one patients with Type 2 diabetes mellitus were included in the study: 15 patients had definite CAN (DCAN), whilst the remaining 26 were negative for CAN (NCAN), being without clinical signs and symptoms of CAN. Symbolic Aggregate approximation (SAX) was used as the discretization procedure to convert the heart rate variability (HRV) time-series signal to network. The optimal degree (m) and data length (n) were found to be mopt = 270 and nopt = 200 respectively with leave-one-out accuracy of 85.37% using transition asymmetry (A(G)) and network efficiency (EF) indexes. Both, A(G) and EF indexes are found to be a potential parameter for detecting CAN in diabetes.

UR - https://www.scopus.com/pages/publications/84894155607

M3 - Conference contribution

AN - SCOPUS:84894155607

SN - 9781479908844

T3 - Computing in Cardiology

SP - 97

EP - 100

BT - Computing in Cardiology 2013, CinC 2013

T2 - 2013 40th Computing in Cardiology Conference, CinC 2013

Y2 - 22 September 2013 through 25 September 2013

ER -

Time-series network analysis for detecting cardiac autonomic neuropathy using RR interval data

Abstract

Publication series

Conference

UN SDGs

OpenUrl availability

Other files and links

Fingerprint

Cite this