Key result
A 3D Convolutional Neural Network using effective connectivity matrices from the brain's Default Mode Network achieved an accuracy of 87.85% in 5-fold cross-validation and 100% in a separate testing set for diagnosing Alcohol Use Disorder.
Why the study?
Conventional DSM criteria for diagnosing Alcohol Use Disorder are subjective and potentially misleading, highlighting the need for an objective diagnostic assessment scheme.
Does a 3D-CNN using EEG effective connectivity in the Default Mode Network improve the objective diagnosis of Alcohol Use Disorder?
Case-Control (n=62)
Yes
Does a 3D-CNN using EEG effective connectivity in the Default Mode Network improve the objective diagnosis of Alcohol Use Disorder?
Effect estimate: Accuracy 87.85%
A 3D-CNN using EEG effective connectivity in the Default Mode Network can accurately classify Alcohol Use Disorder patients from healthy controls, providing a potential objective diagnostic tool.
EEG connectivity-based 3D-CNN yields high AUD classification accuracy; hypothesis-generating and requires larger prospective validation before clinical adoption.
Alcohol Use Disorder (AUD) is a chronic relapsing brain disease characterized by excessive alcohol use, loss of control over alcohol intake, and negative emotional states under no alcohol consumption. The key factor in successful treatment of AUD is the accurate diagnosis for better medical and therapy management. Conventionally, for individuals to be diagnosed with AUD, certain criteria as outlined in the Diagnostic and Statistical Manual of Mental Disorders (DSM) should be met. However, this process is subjective in nature and could be misleading due to memory problems and dishonesty of some AUD patients. In this paper, an assessment scheme for objective diagnosis of AUD is proposed. For this purpose, EEG recording of 31 healthy controls and 31 AUD patients are used for the calculation of effective connectivity (EC) between the various regions of the brain Default Mode Network (DMN). The EC is estimated using partial directed coherence (PDC) which are then used as input to a 3D Convolutional Neural Network (CNN) for binary classification of AUD cases. Using 5-fold cross validation, the classification of AUD vs. HC effective connectivity matrices using the proposed 3D-CNN gives an accuracy of 87.85 ± 4.64 %. For further validation, 32 and 30 subjects are randomly selected for training and testing, respectively, giving 100% correct classification of all the testing subjects.
No takes yet. Share an insight, caveat, or question.
Khan et al. (2021) conducted a case-control in Alcohol Use Disorder (n=62). 3D-CNN based on DMN Effective Connectivity vs. Healthy Controls was evaluated on Classification accuracy of AUD vs. HC (Accuracy 87.85%). A 3D Convolutional Neural Network using effective connectivity matrices from the brain's Default Mode Network achieved an accuracy of 87.85% in 5-fold cross-validation and 100% in a separate testing set for diagnosing Alcohol Use Disorder.
Synapse has enriched 2 closely related papers on similar clinical questions. Consider them for comparative context: