Key result
Quadratic SVM-based clinical decision support achieves 95% accuracy in detecting alcoholic EEG signals.
Why the study?
Alcohol consumption alters neuronal function detectable by EEG signals, necessitating effective methods to differentiate alcoholic from uninfluenced individuals.
Does a clinical decision support system using Quadratic SVM analysis of EEG signals accurately detect alcoholism?
Does a clinical decision support system using Quadratic SVM analysis of EEG signals accurately detect alcoholism?
A clinical decision support system using Quadratic SVM to analyze EEG signals can detect alcoholism with 95% accuracy.
Answers are grounded in this paper and cite their sources.
May support EEG-based screening tools for alcohol effects; leaves open prospective clinical validation before adoption.
Alcoholism is an adverse situation that changes the functioning of important part of nervous system which is neuron. This changes the functional behavior of alcoholic person. The diagnosis of this state is done with the help of EEG signals which gets modified with the electrical activity of the brain. The EEG data sets used in this paper are taken from the University of California at Irvine, Irvine, knowledge discovery and databases. A review on how the EEG signals get affected by the consumption of alcohol and the extraction of features from these signals help to differentiate alcoholic and uninfluenced people with the help of graphical user interface (GUI) is presented in this paper. GUI is an interface that showcases the features extracted from the raw EEG data and classifies the two different classes. This is achieved with the help of sample entropy, approximate entropy, mean, and standard deviation of raw EEG data collected from the electrodes frontal polar, frontal, and central. This GUI system is economical and efficient which is used as a proper clinical decision support system by clinicians and also helps rehabilitation centres in getting to know about the subject. Quadratic SVM gives a highest accuracy of 95% for the detection of alcoholic EEG signal.
No takes yet. Share an insight, caveat, or question.
Narasimhan et al. (2018) studied Alcoholism. Quadratic SVM using EEG features was evaluated on Detection of alcoholic EEG signal. A clinical decision support system using a Quadratic SVM classifier on EEG features achieved a 95% accuracy for the detection of alcoholic EEG signals.
Synapse has enriched 10 related papers. Consider them for comparative context: