Analysis reveals machine learning can classify neurobehavioral patterns in EEG data from gambling tasks, suggesting potential for early detection of gaming addiction.
Key Points
Classification accuracy reached 93%, indicating promising potential for identifying gaming addiction through EEG signals and behavioral patterns.
Participants were assessed using the Iowa Gambling Task, providing a cognitive framework to examine decision-making influenced by gaming addiction.
EEG-based biomarkers were extracted using techniques like Fast Fourier Transform and Wavelet Transforms to enhance the feature set for machine learning models.
The findings suggest a replicable method for diagnosing neurobehavioral risks associated with gaming disorders, with a focus on ethical data handling and methodological transparency.