Multimodal-based machine learning approach to classify features of internet gaming disorder and alcohol use disorder: A sensor-level and source-level resting-state electroencephalography activity and neuropsychological study

• Published in: Comprehensive psychiatry Vol. 130; p. 152460
• Main Authors: Lee, Ji-Yoon, Song, Myeong Seop, Yoo, So Young, Jang, Joon Hwan, Lee, Deokjong, Jung, Young-Chul, Ahn, Woo-Young, Choi, Jung-Seok
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 01.04.2024; Elsevier Limited; Elsevier
• Subjects: Addictions; Addictive behaviors; alcohol use disorder; Alcoholism - diagnosis; Alcoholism - psychology; Behavior, Addictive - psychology; Brain; Computer & video games; Electroencephalography; electroencephalography (EEG); Humans; Impulsive Behavior; Internet; Internet Addiction Disorder; Internet gaming disorder; Machine learning; Magnetic Resonance Imaging; multimodal; neuropsychological features; Sensors; Video Games - psychology; electroencephalography (EEG); alcohol use disorder; multimodal; Internet gaming disorder; machine learning; neuropsychological features
• ISSN: 0010-440X; 1532-8384
• DOI: 10.1016/j.comppsych.2024.152460

Addictions have recently been classified as substance use disorder (SUD) and behavioral addiction (BA), but the concept of BA is still debatable. Therefore, it is necessary to conduct further neuroscientific research to understand the mechanisms of BA to the same extent as SUD. The present study used machine learning (ML) algorithms to investigate the neuropsychological and neurophysiological aspects of addictions in individuals with internet gaming disorder (IGD) and alcohol use disorder (AUD). We developed three models for distinguishing individuals with IGD from those with AUD, individuals with IGD from healthy controls (HCs), and individuals with AUD from HCs using ML algorithms, including L1-norm support vector machine, random forest, and L1-norm logistic regression (LR). Three distinct feature sets were used for model training: a unimodal-electroencephalography (EEG) feature set combined with sensor- and source-level feature; a unimodal-neuropsychological feature (NF) set included sex, age, depression, anxiety, impulsivity, and general cognitive function, and a multimodal (EEG + NF) feature set. The LR model with the multimodal feature set used for the classification of IGD and AUD outperformed the other models (accuracy: 0.712). The important features selected by the model highlighted that the IGD group had differential delta and beta source connectivity between right intrahemispheric regions and distinct sensor-level EEG activities. Among the NFs, sex and age were the important features for good model performance. Using ML techniques, we demonstrated the neurophysiological and neuropsychological similarities and differences between IGD (a BA) and AUD (a SUD). •The multimodal model with LR outperformed in distinguishing IGD and AUD.•Highlighting neurophysiological and neuropsychological similarities and differences.•IGD had differential delta and beta source connectivity compared with AUD.•IGD exhibited distinct sensor-level EEG activities in contrast to AUD.•IGD and AUD have similar neuropsychological symptoms.