Computer-aided diagnosis of alcoholism-related EEG signals

U Rajendra Acharya; Vidya S; Shreya Bhat; Hojjat Adeli; Amir Adeli

doi:10.1016/j.yebeh.2014.10.001

Computer-aided diagnosis of alcoholism-related EEG signals

Epilepsy Behav. 2014 Dec:41:257-63. doi: 10.1016/j.yebeh.2014.10.001. Epub 2014 Nov 7.

Authors

U Rajendra Acharya¹, Vidya S¹, Shreya Bhat², Hojjat Adeli³, Amir Adeli⁴

Affiliations

¹ Department of Electronics and Computer Engineering, Ngee Ann Polytechnic, Singapore 599489, Singapore.
² Department of Biomedical Engineering, Manipal Institute of Technology, Manipal, Karnataka 576104, India.
³ Department of Neuroscience, The Ohio State University, Columbus, OH, USA; Department of Biomedical Engineering, The Ohio State University, Columbus, OH, USA; Department of Biomedical Informatics, The Ohio State University, Columbus, OH, USA; Department of Electrical and Computer Engineering, The Ohio State University, Columbus, OH, USA. Electronic address: adeli.1@osu.edu.
⁴ Department of Neurology, The Ohio State University, 470 Hitchcock Hall, 2070 Neil Avenue, Columbus, OH 43210, USA.

PMID: 25461226
DOI: 10.1016/j.yebeh.2014.10.001

Abstract

Alcoholism is a severe disorder that affects the functionality of neurons in the central nervous system (CNS) and alters the behavior of the affected person. Electroencephalogram (EEG) signals can be used as a diagnostic tool in the evaluation of subjects with alcoholism. The neurophysiological interpretation of EEG signals in persons with alcoholism (PWA) is based on observation and interpretation of the frequency and power in their EEGs compared to EEG signals from persons without alcoholism. This paper presents a review of the known features of EEGs obtained from PWA and proposes that the impact of alcoholism on the brain can be determined by computer-aided analysis of EEGs through extracting the minute variations in the EEG signals that can differentiate the EEGs of PWA from those of nonaffected persons. The authors advance the idea of automated computer-aided diagnosis (CAD) of alcoholism by employing the EEG signals. This is achieved through judicious combination of signal processing techniques such as wavelet, nonlinear dynamics, and chaos theory and pattern recognition and classification techniques. A CAD system is cost-effective and efficient and can be used as a decision support system by physicians in the diagnosis and treatment of alcoholism especially those who do not specialize in alcoholism or neurophysiology. It can also be of great value to rehabilitation centers to assess PWA over time and to monitor the impact of treatment aimed at minimizing or reversing the effects of the disease on the brain. A CAD system can be used to determine the extent of alcoholism-related changes in EEG signals (low, medium, high) and the effectiveness of therapeutic plans.

Keywords: Alcoholism; CAD; EEG; Feature; Nonclinical; Nonlinear.

Publication types

Review

MeSH terms

Alcoholism / diagnosis*
Diagnosis, Computer-Assisted / methods*
Electroencephalography / methods*
Humans