Addiction is a brain disorder characterized by repeated use of drugs, or repetitive engagement in behavior such as gambling, despite harm to self and others. It can be also classified into substance and non-substance addiction (e.g., behavioral addiction) and both types of addiction are associated with severe health, economic and social consequences. Over the last few decades, significant progress has been made in understanding the behavioral and neurological mechanisms of addiction. However, effective clinical diagnosis and treatment options still remain a great challenge. Machine Learning, including various algorithms such as supervised learning, unsupervised learning, reinforcement learning, etc., has gained increasing interest with applications in many fields. For the quantitative analysis of data recorded from different modalities in addiction studies, such as fMRI, EEG, fNIRS, as well as behavioral tests data, machine learning algorithms have shown outstanding power in discriminating and predicting human behaviors from complex data resources, compared to traditional statistical analysis methods. This offers a promising solution in combining behavioral, neuroimaging, and lab test data for additional diagnosis and treatment outcome evaluation.
This Research Topic will be served as a platform for researchers to share and discuss the applications of the machine learning framework in addiction research, with a focus on neuroimaging data. We expect this collection of articles to further advance our understanding of the neural mechanisms, etiology, objective diagnosis criteria, prevention, and treatment strategies for addictive behaviors and substance dependence disorders.
We welcome contributions focusing on the application of machine learning methods in experimental, clinical, and therapeutic research relating to substance addiction and non-substance addiction, including but are not limited to alcohol, drugs, nicotine, etc. abuse and behavioral addictions such as gaming/gambling, shopping, internet, smartphone, etc. Contributions to this Research Topic should fall into one of the following sub-themes:
• Potential biomarkers in addiction diagnosis and treatment
• Brain network related to cue reactivity, impulsivity, and cognitive control
• The brain pathways that regulate responses to substance or non-substance related rewards
• Impact of psychological and environmental risk factors on treatment outcomes for substance or non-substance addiction.
• New approaches (pharmacological therapy, behavioral and psychological therapies, rTMS, etc. ) for the treatment of addiction.
• Brain networks that mediate craving or relapse in patients undergoing treatment for substance or non-substance addiction
Addiction is a brain disorder characterized by repeated use of drugs, or repetitive engagement in behavior such as gambling, despite harm to self and others. It can be also classified into substance and non-substance addiction (e.g., behavioral addiction) and both types of addiction are associated with severe health, economic and social consequences. Over the last few decades, significant progress has been made in understanding the behavioral and neurological mechanisms of addiction. However, effective clinical diagnosis and treatment options still remain a great challenge. Machine Learning, including various algorithms such as supervised learning, unsupervised learning, reinforcement learning, etc., has gained increasing interest with applications in many fields. For the quantitative analysis of data recorded from different modalities in addiction studies, such as fMRI, EEG, fNIRS, as well as behavioral tests data, machine learning algorithms have shown outstanding power in discriminating and predicting human behaviors from complex data resources, compared to traditional statistical analysis methods. This offers a promising solution in combining behavioral, neuroimaging, and lab test data for additional diagnosis and treatment outcome evaluation.
This Research Topic will be served as a platform for researchers to share and discuss the applications of the machine learning framework in addiction research, with a focus on neuroimaging data. We expect this collection of articles to further advance our understanding of the neural mechanisms, etiology, objective diagnosis criteria, prevention, and treatment strategies for addictive behaviors and substance dependence disorders.
We welcome contributions focusing on the application of machine learning methods in experimental, clinical, and therapeutic research relating to substance addiction and non-substance addiction, including but are not limited to alcohol, drugs, nicotine, etc. abuse and behavioral addictions such as gaming/gambling, shopping, internet, smartphone, etc. Contributions to this Research Topic should fall into one of the following sub-themes:
• Potential biomarkers in addiction diagnosis and treatment
• Brain network related to cue reactivity, impulsivity, and cognitive control
• The brain pathways that regulate responses to substance or non-substance related rewards
• Impact of psychological and environmental risk factors on treatment outcomes for substance or non-substance addiction.
• New approaches (pharmacological therapy, behavioral and psychological therapies, rTMS, etc. ) for the treatment of addiction.
• Brain networks that mediate craving or relapse in patients undergoing treatment for substance or non-substance addiction
