Detecting Parkinson's Disease from Electroencephalogram Signals: An Explainable Machine Learning Approach

Mohammod Abdul Motin; Mufti Mahmud; David J. Brown

doi:10.1109/AICT55583.2022.10013589

Detecting Parkinson's Disease from Electroencephalogram Signals: An Explainable Machine Learning Approach

Mohammod Abdul Motin^*, Mufti Mahmud, David J. Brown

^*Corresponding author for this work

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

12 Scopus citations

Abstract

Parkinson's disease (PD) is the second most common neurological disorder. It is characterised by stiffness, rigidity, tremor, freezing gait and postural instability. PD is monitored clinically by expert neurologists by visually inspecting upper and lower limb movements, speech, gait and facial expressions. This is time-consuming, error-prone and requires an expert neurologist to perform these manual inspections. The electroencephalogram (EEG) is a non-invasive method of monitoring brain activity. This work proposes an EEG-based automated PD monitoring technique. PD was identified using explainable machine learning classifiers based on 31 features extracted from EEG signals. To distinguish PD from healthy controls, the support vector machine classifier with a polynomial kernel achieves 87.10% accuracy, 93.33% sensitivity and 81.25% specificity.

Original language	English
Title of host publication	16th IEEE International Conference on Application of Information and Communication Technologies, AICT 2022 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781665451628
DOIs	https://doi.org/10.1109/AICT55583.2022.10013589
State	Published - 2022
Externally published	Yes
Event	16th IEEE International Conference on Application of Information and Communication Technologies, AICT 2022 - Washington, United States Duration: 12 Oct 2022 → 14 Oct 2022

Publication series

Name	16th IEEE International Conference on Application of Information and Communication Technologies, AICT 2022 - Proceedings

Conference

Conference	16th IEEE International Conference on Application of Information and Communication Technologies, AICT 2022
Country/Territory	United States
City	Washington
Period	12/10/22 → 14/10/22

Bibliographical note

Publisher Copyright:
© 2022 IEEE.

Keywords

Automated classification
Electroencephalogram
Explainable artificial intelligence
Neurological disorder
Parkinson's disease

ASJC Scopus subject areas

Artificial Intelligence
Computer Networks and Communications
Computer Science Applications
Computer Vision and Pattern Recognition
Information Systems
Health Informatics
Information Systems and Management

Access to Document

10.1109/AICT55583.2022.10013589

Cite this

Motin, M. A., Mahmud, M., & Brown, D. J. (2022). Detecting Parkinson's Disease from Electroencephalogram Signals: An Explainable Machine Learning Approach. In 16th IEEE International Conference on Application of Information and Communication Technologies, AICT 2022 - Proceedings (16th IEEE International Conference on Application of Information and Communication Technologies, AICT 2022 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/AICT55583.2022.10013589

Motin, Mohammod Abdul ; Mahmud, Mufti ; Brown, David J. / Detecting Parkinson's Disease from Electroencephalogram Signals : An Explainable Machine Learning Approach. 16th IEEE International Conference on Application of Information and Communication Technologies, AICT 2022 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2022. (16th IEEE International Conference on Application of Information and Communication Technologies, AICT 2022 - Proceedings).

@inproceedings{a6965cfe4633413ab9489cf4e6b0f0ff,

title = "Detecting Parkinson's Disease from Electroencephalogram Signals: An Explainable Machine Learning Approach",

abstract = "Parkinson's disease (PD) is the second most common neurological disorder. It is characterised by stiffness, rigidity, tremor, freezing gait and postural instability. PD is monitored clinically by expert neurologists by visually inspecting upper and lower limb movements, speech, gait and facial expressions. This is time-consuming, error-prone and requires an expert neurologist to perform these manual inspections. The electroencephalogram (EEG) is a non-invasive method of monitoring brain activity. This work proposes an EEG-based automated PD monitoring technique. PD was identified using explainable machine learning classifiers based on 31 features extracted from EEG signals. To distinguish PD from healthy controls, the support vector machine classifier with a polynomial kernel achieves 87.10\% accuracy, 93.33\% sensitivity and 81.25\% specificity.",

keywords = "Automated classification, Electroencephalogram, Explainable artificial intelligence, Neurological disorder, Parkinson's disease",

author = "Motin, \{Mohammod Abdul\} and Mufti Mahmud and Brown, \{David J.\}",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 16th IEEE International Conference on Application of Information and Communication Technologies, AICT 2022 ; Conference date: 12-10-2022 Through 14-10-2022",

year = "2022",

doi = "10.1109/AICT55583.2022.10013589",

language = "English",

series = "16th IEEE International Conference on Application of Information and Communication Technologies, AICT 2022 - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "16th IEEE International Conference on Application of Information and Communication Technologies, AICT 2022 - Proceedings",

address = "United States",

}

Motin, MA, Mahmud, M & Brown, DJ 2022, Detecting Parkinson's Disease from Electroencephalogram Signals: An Explainable Machine Learning Approach. in 16th IEEE International Conference on Application of Information and Communication Technologies, AICT 2022 - Proceedings. 16th IEEE International Conference on Application of Information and Communication Technologies, AICT 2022 - Proceedings, Institute of Electrical and Electronics Engineers Inc., 16th IEEE International Conference on Application of Information and Communication Technologies, AICT 2022, Washington, United States, 12/10/22. https://doi.org/10.1109/AICT55583.2022.10013589

Detecting Parkinson's Disease from Electroencephalogram Signals: An Explainable Machine Learning Approach. / Motin, Mohammod Abdul; Mahmud, Mufti; Brown, David J.
16th IEEE International Conference on Application of Information and Communication Technologies, AICT 2022 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2022. (16th IEEE International Conference on Application of Information and Communication Technologies, AICT 2022 - Proceedings).

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

TY - GEN

T1 - Detecting Parkinson's Disease from Electroencephalogram Signals

T2 - 16th IEEE International Conference on Application of Information and Communication Technologies, AICT 2022

AU - Motin, Mohammod Abdul

AU - Mahmud, Mufti

AU - Brown, David J.

PY - 2022

Y1 - 2022

N2 - Parkinson's disease (PD) is the second most common neurological disorder. It is characterised by stiffness, rigidity, tremor, freezing gait and postural instability. PD is monitored clinically by expert neurologists by visually inspecting upper and lower limb movements, speech, gait and facial expressions. This is time-consuming, error-prone and requires an expert neurologist to perform these manual inspections. The electroencephalogram (EEG) is a non-invasive method of monitoring brain activity. This work proposes an EEG-based automated PD monitoring technique. PD was identified using explainable machine learning classifiers based on 31 features extracted from EEG signals. To distinguish PD from healthy controls, the support vector machine classifier with a polynomial kernel achieves 87.10% accuracy, 93.33% sensitivity and 81.25% specificity.

AB - Parkinson's disease (PD) is the second most common neurological disorder. It is characterised by stiffness, rigidity, tremor, freezing gait and postural instability. PD is monitored clinically by expert neurologists by visually inspecting upper and lower limb movements, speech, gait and facial expressions. This is time-consuming, error-prone and requires an expert neurologist to perform these manual inspections. The electroencephalogram (EEG) is a non-invasive method of monitoring brain activity. This work proposes an EEG-based automated PD monitoring technique. PD was identified using explainable machine learning classifiers based on 31 features extracted from EEG signals. To distinguish PD from healthy controls, the support vector machine classifier with a polynomial kernel achieves 87.10% accuracy, 93.33% sensitivity and 81.25% specificity.

KW - Automated classification

KW - Electroencephalogram

KW - Explainable artificial intelligence

KW - Neurological disorder

KW - Parkinson's disease

UR - http://www.scopus.com/inward/record.url?scp=85147541796&partnerID=8YFLogxK

U2 - 10.1109/AICT55583.2022.10013589

DO - 10.1109/AICT55583.2022.10013589

M3 - Conference contribution

AN - SCOPUS:85147541796

T3 - 16th IEEE International Conference on Application of Information and Communication Technologies, AICT 2022 - Proceedings

BT - 16th IEEE International Conference on Application of Information and Communication Technologies, AICT 2022 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 12 October 2022 through 14 October 2022

ER -

Motin MA, Mahmud M, Brown DJ. Detecting Parkinson's Disease from Electroencephalogram Signals: An Explainable Machine Learning Approach. In 16th IEEE International Conference on Application of Information and Communication Technologies, AICT 2022 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2022. (16th IEEE International Conference on Application of Information and Communication Technologies, AICT 2022 - Proceedings). doi: 10.1109/AICT55583.2022.10013589

Detecting Parkinson's Disease from Electroencephalogram Signals: An Explainable Machine Learning Approach

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this