Predicting Individual Substance Abuse Vulnerability using Machine Learning Techniques

TL;DR

This paper develops a machine learning-based binary classifier to predict individual vulnerability to substance abuse by analyzing socio-economic factors, aiming for early prevention of relapse and harmful consequences.

Contribution

It introduces a novel approach using socio-economic data and machine learning to identify substance abuse risk, with a focus on feature selection and classifier optimization.

Findings

Logistic regression achieved the highest accuracy with 18 features.

Key socio-economic factors influencing vulnerability were identified.

The classifier can effectively predict individual risk levels.

Abstract

Substance abuse is the unrestrained and detrimental use of psychoactive chemical substances, unauthorized drugs, and alcohol. Continuous use of these substances can ultimately lead a human to disastrous consequences. As patients display a high rate of relapse, prevention at an early stage can be an effective restraint. We therefore propose a binary classifier to identify any individual's present vulnerability towards substance abuse by analyzing subjects' socio-economic environment. We have collected data by a questionnaire which is created after carefully assessing the commonly involved factors behind substance abuse. Pearson's chi-squared test of independence is used to identify key feature variables influencing substance abuse. Later we build the predictive classifiers using machine learning classification algorithms on those variables. Logistic regression classifier trained with 18 features can predict individual vulnerability with the best accuracy.