A novel machine learning-based method to quantify the effect of transcranial direct current stimulation on opioid users.

Background: Opioid addiction is a major public health concern, associated with numerous health and social problems. Conventional diagnostic methods for addiction have notable limitations, highlighting the need for alternative approaches.

Methods: This study investigates the use of electroencephalography (EEG) signals in conjunction with transcranial direct current stimulation (tDCS) for the diagnosis and treatment of opioid addiction. Thirty-six male patients undergoing methadone maintenance treatment were recruited and randomly assigned to three groups: Group A received left anodal/right cathodal tDCS ($n=12$), Group B received right anodal/left cathodal tDCS ($n=12$), and Group C received sham stimulation ($n=12$). EEG recordings were obtained from all participants before and after tDCS, as well as from 24 healthy controls. Machine learning techniques were applied to develop an optimized algorithm capable of distinguishing between healthy and addicted individuals by selectively analyzing addiction-affected EEG channels, thereby reducing processing time and costs.

Results: The proposed method achieved a diagnostic accuracy of 94.30%. In addition, the effects of tDCS on craving reduction were assessed using EEG signals, psychological questionnaires, and blood biomarkers. Significant reductions in craving levels were observed in Groups A and B.

Conclusion: These findings suggest that tDCS can be an effective intervention for reducing craving in patients with opioid addiction.