Automated diagnosis of depression electroencephalograph signals using linear prediction coding and higher order spectra features

G. Muralidhar Bairy, Oh Shu Lih, Yuki Hagiwara, Subha D. Puthankattil, Oliver Faust, U. C. Niranjan, U. Rajendra Acharya

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Depression is a mental disorder that negatively affects the day to day activities of a patient. Diagnosing depression is of paramount importance to reduce suffering for the patient and support network. Electroencephalograph (EEG) signal variations can indicate neurological diseases associated with mental trauma. EEG being a non-invasive technique, is widely used to analyse various brain disorders. However, to detect and interpret the minute signal changes a computer-aided diagnosis (CAD) system is developed. Higher order statistic based parameters, such as variance, kurtosis, normalized kurtosis, skewness, normalized skewness is extracted from the linear predictive coding (LPC) residuals. Seven different feature ranking methods are used to test and rank the extracted features. Feature ranking using Receiver Operating Characteristic (ROC) gave the best classification accuracy of 94.30%, the sensitivity of 91.46% and specificity of 97.45% using a bag tree classifier.

Original languageEnglish
Pages (from-to)1857-1862
Number of pages6
JournalJournal of Medical Imaging and Health Informatics
Volume7
Issue number8
DOIs
Publication statusPublished - 01-12-2017

Fingerprint

Depression
Brain Diseases
Mental Disorders
ROC Curve
Sensitivity and Specificity
Wounds and Injuries

All Science Journal Classification (ASJC) codes

  • Radiology Nuclear Medicine and imaging
  • Health Informatics

Cite this

Bairy, G. Muralidhar ; Lih, Oh Shu ; Hagiwara, Yuki ; Puthankattil, Subha D. ; Faust, Oliver ; Niranjan, U. C. ; Acharya, U. Rajendra. / Automated diagnosis of depression electroencephalograph signals using linear prediction coding and higher order spectra features. In: Journal of Medical Imaging and Health Informatics. 2017 ; Vol. 7, No. 8. pp. 1857-1862.
@article{9c932a55bf8d4578b4bbecef992acab3,
title = "Automated diagnosis of depression electroencephalograph signals using linear prediction coding and higher order spectra features",
abstract = "Depression is a mental disorder that negatively affects the day to day activities of a patient. Diagnosing depression is of paramount importance to reduce suffering for the patient and support network. Electroencephalograph (EEG) signal variations can indicate neurological diseases associated with mental trauma. EEG being a non-invasive technique, is widely used to analyse various brain disorders. However, to detect and interpret the minute signal changes a computer-aided diagnosis (CAD) system is developed. Higher order statistic based parameters, such as variance, kurtosis, normalized kurtosis, skewness, normalized skewness is extracted from the linear predictive coding (LPC) residuals. Seven different feature ranking methods are used to test and rank the extracted features. Feature ranking using Receiver Operating Characteristic (ROC) gave the best classification accuracy of 94.30{\%}, the sensitivity of 91.46{\%} and specificity of 97.45{\%} using a bag tree classifier.",
author = "Bairy, {G. Muralidhar} and Lih, {Oh Shu} and Yuki Hagiwara and Puthankattil, {Subha D.} and Oliver Faust and Niranjan, {U. C.} and Acharya, {U. Rajendra}",
year = "2017",
month = "12",
day = "1",
doi = "10.1166/jmihi.2017.2204",
language = "English",
volume = "7",
pages = "1857--1862",
journal = "Journal of Medical Imaging and Health Informatics",
issn = "2156-7018",
publisher = "American Scientific Publishers",
number = "8",

}

Automated diagnosis of depression electroencephalograph signals using linear prediction coding and higher order spectra features. / Bairy, G. Muralidhar; Lih, Oh Shu; Hagiwara, Yuki; Puthankattil, Subha D.; Faust, Oliver; Niranjan, U. C.; Acharya, U. Rajendra.

In: Journal of Medical Imaging and Health Informatics, Vol. 7, No. 8, 01.12.2017, p. 1857-1862.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Automated diagnosis of depression electroencephalograph signals using linear prediction coding and higher order spectra features

AU - Bairy, G. Muralidhar

AU - Lih, Oh Shu

AU - Hagiwara, Yuki

AU - Puthankattil, Subha D.

AU - Faust, Oliver

AU - Niranjan, U. C.

AU - Acharya, U. Rajendra

PY - 2017/12/1

Y1 - 2017/12/1

N2 - Depression is a mental disorder that negatively affects the day to day activities of a patient. Diagnosing depression is of paramount importance to reduce suffering for the patient and support network. Electroencephalograph (EEG) signal variations can indicate neurological diseases associated with mental trauma. EEG being a non-invasive technique, is widely used to analyse various brain disorders. However, to detect and interpret the minute signal changes a computer-aided diagnosis (CAD) system is developed. Higher order statistic based parameters, such as variance, kurtosis, normalized kurtosis, skewness, normalized skewness is extracted from the linear predictive coding (LPC) residuals. Seven different feature ranking methods are used to test and rank the extracted features. Feature ranking using Receiver Operating Characteristic (ROC) gave the best classification accuracy of 94.30%, the sensitivity of 91.46% and specificity of 97.45% using a bag tree classifier.

AB - Depression is a mental disorder that negatively affects the day to day activities of a patient. Diagnosing depression is of paramount importance to reduce suffering for the patient and support network. Electroencephalograph (EEG) signal variations can indicate neurological diseases associated with mental trauma. EEG being a non-invasive technique, is widely used to analyse various brain disorders. However, to detect and interpret the minute signal changes a computer-aided diagnosis (CAD) system is developed. Higher order statistic based parameters, such as variance, kurtosis, normalized kurtosis, skewness, normalized skewness is extracted from the linear predictive coding (LPC) residuals. Seven different feature ranking methods are used to test and rank the extracted features. Feature ranking using Receiver Operating Characteristic (ROC) gave the best classification accuracy of 94.30%, the sensitivity of 91.46% and specificity of 97.45% using a bag tree classifier.

UR - http://www.scopus.com/inward/record.url?scp=85032882497&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85032882497&partnerID=8YFLogxK

U2 - 10.1166/jmihi.2017.2204

DO - 10.1166/jmihi.2017.2204

M3 - Article

VL - 7

SP - 1857

EP - 1862

JO - Journal of Medical Imaging and Health Informatics

JF - Journal of Medical Imaging and Health Informatics

SN - 2156-7018

IS - 8

ER -