Computer-aided diagnosis of Parkinson's disease using complex-valued neural networks and mRMR feature selection algorithm

Musa Peker, Baha Şen, Dursun Delen

Research output: Contribution to journalArticle

29 Citations (Scopus)

Abstract

Parkinson's disease (PD) is a neurological disorder which has a significant social and economic impact. PD is diagnosed by clinical observation and evaluations, coupled with a PD rating scale. However, these methods may be insufficient, especially in the initial phase of the disease. The processes are tedious and time-consuming, and hence systems that can automatically offer a diagnosis are needed. In this study, a novel method for the diagnosis of PD is proposed. Biomedical sound measurements obtained from continuous phonation samples were used as attributes. First, a minimum redundancy maximum relevance (mRMR) attribute selection algorithm was applied for the identification of the effective attributes. After conversion to a complex number, the resulting attributes are presented as input data to the complex-valued artificial neural network (CVANN). The proposed novel system might be a powerful tool for effective diagnosis of PD.

Original languageEnglish
Pages (from-to)281-302
Number of pages22
JournalJournal of Healthcare Engineering
Volume6
Issue number3
DOIs
StatePublished - 1 Aug 2015
Externally publishedYes

Fingerprint

Computer aided diagnosis
Redundancy
Parkinson Disease
Feature extraction
Neural networks
Phonation
Acoustic variables measurement
Nervous System Diseases
Economics
Observation

Keywords

  • Classification
  • Complex-valued neural network
  • Computer aided diagnosis
  • Mrmr feature selection method
  • Parkinson's disease

Cite this

@article{927e21cf4e544d318d8f6bdf17297c3e,
title = "Computer-aided diagnosis of Parkinson's disease using complex-valued neural networks and mRMR feature selection algorithm",
abstract = "Parkinson's disease (PD) is a neurological disorder which has a significant social and economic impact. PD is diagnosed by clinical observation and evaluations, coupled with a PD rating scale. However, these methods may be insufficient, especially in the initial phase of the disease. The processes are tedious and time-consuming, and hence systems that can automatically offer a diagnosis are needed. In this study, a novel method for the diagnosis of PD is proposed. Biomedical sound measurements obtained from continuous phonation samples were used as attributes. First, a minimum redundancy maximum relevance (mRMR) attribute selection algorithm was applied for the identification of the effective attributes. After conversion to a complex number, the resulting attributes are presented as input data to the complex-valued artificial neural network (CVANN). The proposed novel system might be a powerful tool for effective diagnosis of PD.",
keywords = "Classification, Complex-valued neural network, Computer aided diagnosis, Mrmr feature selection method, Parkinson's disease",
author = "Musa Peker and Baha Şen and Dursun Delen",
year = "2015",
month = "8",
day = "1",
doi = "10.1260/2040-2295.6.3.281",
language = "English",
volume = "6",
pages = "281--302",
journal = "Journal of Healthcare Engineering",
issn = "2040-2295",
publisher = "Hindawi Limited",
number = "3",

}

Computer-aided diagnosis of Parkinson's disease using complex-valued neural networks and mRMR feature selection algorithm. / Peker, Musa; Şen, Baha; Delen, Dursun.

In: Journal of Healthcare Engineering, Vol. 6, No. 3, 01.08.2015, p. 281-302.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Computer-aided diagnosis of Parkinson's disease using complex-valued neural networks and mRMR feature selection algorithm

AU - Peker, Musa

AU - Şen, Baha

AU - Delen, Dursun

PY - 2015/8/1

Y1 - 2015/8/1

N2 - Parkinson's disease (PD) is a neurological disorder which has a significant social and economic impact. PD is diagnosed by clinical observation and evaluations, coupled with a PD rating scale. However, these methods may be insufficient, especially in the initial phase of the disease. The processes are tedious and time-consuming, and hence systems that can automatically offer a diagnosis are needed. In this study, a novel method for the diagnosis of PD is proposed. Biomedical sound measurements obtained from continuous phonation samples were used as attributes. First, a minimum redundancy maximum relevance (mRMR) attribute selection algorithm was applied for the identification of the effective attributes. After conversion to a complex number, the resulting attributes are presented as input data to the complex-valued artificial neural network (CVANN). The proposed novel system might be a powerful tool for effective diagnosis of PD.

AB - Parkinson's disease (PD) is a neurological disorder which has a significant social and economic impact. PD is diagnosed by clinical observation and evaluations, coupled with a PD rating scale. However, these methods may be insufficient, especially in the initial phase of the disease. The processes are tedious and time-consuming, and hence systems that can automatically offer a diagnosis are needed. In this study, a novel method for the diagnosis of PD is proposed. Biomedical sound measurements obtained from continuous phonation samples were used as attributes. First, a minimum redundancy maximum relevance (mRMR) attribute selection algorithm was applied for the identification of the effective attributes. After conversion to a complex number, the resulting attributes are presented as input data to the complex-valued artificial neural network (CVANN). The proposed novel system might be a powerful tool for effective diagnosis of PD.

KW - Classification

KW - Complex-valued neural network

KW - Computer aided diagnosis

KW - Mrmr feature selection method

KW - Parkinson's disease

UR - http://www.scopus.com/inward/record.url?scp=84958643361&partnerID=8YFLogxK

U2 - 10.1260/2040-2295.6.3.281

DO - 10.1260/2040-2295.6.3.281

M3 - Article

C2 - 26753436

AN - SCOPUS:84958643361

VL - 6

SP - 281

EP - 302

JO - Journal of Healthcare Engineering

JF - Journal of Healthcare Engineering

SN - 2040-2295

IS - 3

ER -