An automated drug dependence detection system based on EEG

• Published in: Computers in biology and medicine 2023-05, Vol.158, p.106853-106853, Article 106853
• Main Authors: Marvi, Nasimeh, Haddadnia, Javad, Fayyazi Bordbar, Mohammad Reza
• Format: Article
• Language: English
• Subjects: Accuracy; Algorithms; Biomarkers; Brain damage; Brain injury; Brain research; Classification; Complexity; Data analysis; Dependence; Design; Diagnostic aid system; Drug abuse; Drug dependence; Drug development; Dynamic characteristics; EEG; Electroencephalography; Electroencephalography - methods; ENTR; Entropy; Functional anatomy; Heroin; Humans; Medical diagnosis; Multidrug abusers; Neural networks; Nonlinear analysis; Recording equipment; Recurrence quantification analysis; Signal Processing, Computer-Assisted; Statistical analysis; Structure-function relationships; Support Vector Machine; Support vector machines; Time series; Urine
• ISSN: 0010-4825; 1879-0534
• DOI: 10.1016/j.compbiomed.2023.106853

Substance abuse causes damage to the brain structure and function. This research aim is to design an automated drug dependence detection system based on EEG signals in a Multidrug (MD) abuser. EEG signals were recorded from participants categorized into MD-dependents (n = 10) and Healthy Control (HC) (n = 12). The Recurrence Plot investigates the dynamic characteristics of the EEG signal. The entropy index (ENTR) measured from the Recurrence Quantification Analysis was considered the complexity index of the delta, theta, alpha, beta, gamma, and all-band EEG signals. Statistical analysis was performed by t-test. The support vector machine technique was used for the data classification. The results show decreased ENTR indices in the delta, alpha, beta, gamma, and all-band EEG signal and increased theta band in MD abusers compared to the HC group. That indicated the reduction of complexity in the delta, alpha, beta, gamma, and all-band EEG signals in the MD group. Additionally, the SVM classifier distinguished the MD group from the HC group with 90% accuracy, 89.36% sensitivity, 90.7% specificity, and 89.8% F1 score. The nonlinear analysis of brain data was used to build an automatic diagnostic aid system that could identify HC people apart from those who abuse MD. •Investigate the change in brain signal complexity with the Recurrence Quantification Analysis method.•A decrease in brain complexity in the multidrug dependence group compared to the Healthy Control.•Design an automated drug dependence detection system for multidrug dependence detection.