Prediction of craving across studies: A commentary on conceptual and methodological considerations when using data-driven methods

Stephanie Antons ^1,2,3, Sarah W Yip ^4,5, Cheryl M Lacadie ⁶

¹1General Psychology: Cognition, Faculty of Computer Science, University of Duisburg-Essen, Duisburg, Germany.
²2Center for Behavioral Addiction Research (CeBAR), Center for Translational Neuro- and Behavioral Sciences, University Hospital Essen, University of Duisburg-Essen, Germany.
³3Erwin L. Hahn Institute for Magnetic Resonance Imaging, Essen, Germany.
⁴4Department of Psychiatry, Yale University School of Medicine, New Haven, CT, USA.
⁵5Child Study Center, Yale University School of Medicine, New Haven, CT, USA.
⁶6Department of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, CT, USA.
⁷7Department of Radiology, Athinoula. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Charlestown, MA, USA.
⁸8Department of Radiology, Harvard Medical School, Boston, MA, USA.
⁹9Department of Neuroscience, Yale University School of Medicine, New Haven, CT, USA.
¹⁰10Connecticut Council on Problem Gambling, Wethersfield, CT, USA.
¹¹11Connecticut Mental Health Center, New Haven, CT, USA.
¹²12Wu Tsai Institute, Yale University, New Haven, CT, USA.

⁰1General Psychology: Cognition, Faculty of Computer Science, University of Duisburg-Essen, Duisburg, Germany.

Journal of Behavioral Addictions +

|

October 2, 2024

View abstract on PubMed

Summary

This study reviews how brain connectivity predicts craving in addiction and addictive behaviors. It consolidates findings to model functional connectivity

Area Of Science

Neuroscience
Addiction Research
Computational Psychiatry

Background

Craving is a key symptom in substance use disorders and addictive behaviors.
Neural mechanisms underlying craving are extensively studied.
Connectome-based predictive modeling (CBPM) is emerging for predicting craving.

Purpose Of The Study

To compare, contrast, and consolidate findings from four studies using CBPM to predict craving.
To develop a theoretical model of functional connectivity-craving relationships.
To analyze methodological and conceptual variations across studies.

Main Methods

Review and synthesis of four existing studies employing connectome-based predictive modeling.
Comparative analysis of study methodologies, samples, and craving conceptualizations.
Development of a theoretical model integrating findings on functional connectivity and craving.

Main Results

Four studies utilized CBPM to predict craving related to substance use, addictive behaviors, and food.
Significant heterogeneity was observed in methods, samples, and definitions of craving across studies.
A theoretical model was derived to explain functional connectivity-craving relationships.

Conclusions

Connectome-based predictive modeling shows promise in understanding craving mechanisms.
Standardization of methods and conceptual clarity are needed for future research.
The derived model offers a framework for future investigations into brain connectivity and craving.

Keywords:

cue-reactivity fMRI functional connectivity machine learning urge

Related Concept Videos

Drug Abuse and Addiction: Pharmacological Phenomena

Drug dependence, abuse, and addiction are complex phenomena that can precipitate various abnormal states. Physical dependence refers to a state of pharmacological adaptation to a drug. This adaptation often results in tolerance—a reduced response to the drug after repeated administrations. When the drug use is abruptly stopped, withdrawal symptoms occur due to the body's need to readjust from the pharmacologically induced imbalance. However, tolerance and withdrawal symptoms do not...