Beyond cocaine and heroin use: a stacking ensemble-based framework for predicting the likelihood of subsequent substance use disorder using demographics and personality traits

Abstract

Heroin and cocaine addiction is a global health issue that can result in death. These substances have the ability to change cognitive functions and impulsive behavior control. This study explores the relationship between heroin and cocaine use and the development of additional psychoactive substance addictions, such as cannabis and nicotine. It also investigates whether lighter drug use, like cannabis, leads to heavier drug use. Using subsets of heroin, cocaine, and cannabis data for neural network model training, stacking ensemble learning is employed to uncover these connections. These models predict the risk of subsequent substance abuse based on the history of heroin, cocaine, or cannabis abuse, incorporating demographic factors and personality traits. Results reveal significant impacts: Heroin abuse substantially increases the risk of cannabis and nicotine use (F-scores of 0.95 and 0.94, respectively). Cocaine abuse shows an even stronger association (Accuracy: 0.88) and can lead to heroin and cannabis use. Additionally, cannabis use is linked to subsequent cocaine use. These results have important implications for precision medicine, emphasizing the importance of personalized medications in preventing subsequent addiction development.

KEYWORDS:

• Addiction
• machine learning
• substance use disorder
• ensemble learning
• stacking ensemble
• neural networks

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Notes on contributors

Amina Bouhadja

Amina Bouhadja is a Ph.D. student at the University of Skikda. She is a member of the LICUS Laboratory at the same university. She obtained her Master's Degree in Software Engineering and applications at the University of 20 Août Skikda. Her interests are Artificial Intelligence, Machine Learning, Addiction Research, Psychiatry, Substance use Disorders and Behavioral Disorders.

Abdelkrim Bouramoul

Abdelkrim Bouramoul serves as a full Professor within the Computer Science Department at Constantine 2 University in Algeria. Simultaneously, He is also an active researcher within the MISC Laboratory at the same institution. In April 2017, he achieved his HDR (Habilitation to Supervise Research) from Constantine 2 University, complementing his PhD in Computer Science, which he earned jointly from the University of Paris 11 in France and Constantine 2 University in Algeria in September 2011. Professor Bouramoul has a substantial body of work, including publications in prominent international journals and conferences. His primary research pursuits encompass Artificial Intelligence, Affective Computing, Virtual and Augmented Reality, Information Retrieval, and Visualization within the expansive realm of Big Data.