Identifying Risk Factors for Drug Use in an Iranian Treatment Sample: A Prediction Approach Using Decision Trees

Alireza Amirabadizadeh, Hossein Nezami, Michael G. Vaughn, Samaneh Nakhaee, Omid Mehrpour

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Introduction and aim: Substance abuse exacts considerable social and health care burdens throughout the world. The aim of this study was to create a prediction model to better identify risk factors for drug use. Design and Methods: A prospective cross-sectional study was conducted in South Khorasan Province, Iran. Of the total of 678 eligible subjects, 70% (n: 474) were randomly selected to provide a training set for constructing decision tree and multiple logistic regression (MLR) models. The remaining 30% (n: 204) were employed in a holdout sample to test the performance of the decision tree and MLR models. Predictive performance of different models was analyzed by the receiver operating characteristic (ROC) curve using the testing set. Independent variables were selected from demographic characteristics and history of drug use. Results: For the decision tree model, the sensitivity and specificity for identifying people at risk for drug abuse were 66% and 75%, respectively, while the MLR model was somewhat less effective at 60% and 73%. Key independent variables in the analyses included first substance experience, age at first drug use, age, place of residence, history of cigarette use, and occupational and marital status. Discussion and Conclusion: While study findings are exploratory and lack generalizability they do suggest that the decision tree model holds promise as an effective classification approach for identifying risk factors for drug use. Convergent with prior research in Western contexts is that age of drug use initiation was a critical factor predicting a substance use disorder.

Original languageEnglish
Pages (from-to)1030-1040
Number of pages11
JournalSubstance Use and Misuse
Volume53
Issue number6
DOIs
Publication statusPublished - 2018 May 12

Fingerprint

Decision Trees
drug use
Logistic Models
Pharmaceutical Preparations
Substance-Related Disorders
logistics
regression
Marital Status
occupational status
Iran
place of residence
ROC Curve
Tobacco Products
drug abuse
marital status
cross-sectional study
substance abuse
Cross-Sectional Studies
performance
Demography

All Science Journal Classification (ASJC) codes

  • Medicine (miscellaneous)
  • Health(social science)
  • Public Health, Environmental and Occupational Health
  • Psychiatry and Mental health

Cite this

Amirabadizadeh, Alireza ; Nezami, Hossein ; Vaughn, Michael G. ; Nakhaee, Samaneh ; Mehrpour, Omid. / Identifying Risk Factors for Drug Use in an Iranian Treatment Sample : A Prediction Approach Using Decision Trees. In: Substance Use and Misuse. 2018 ; Vol. 53, No. 6. pp. 1030-1040.
@article{bcf5f798353a4bc1a4f504fbc33a40bf,
title = "Identifying Risk Factors for Drug Use in an Iranian Treatment Sample: A Prediction Approach Using Decision Trees",
abstract = "Introduction and aim: Substance abuse exacts considerable social and health care burdens throughout the world. The aim of this study was to create a prediction model to better identify risk factors for drug use. Design and Methods: A prospective cross-sectional study was conducted in South Khorasan Province, Iran. Of the total of 678 eligible subjects, 70{\%} (n: 474) were randomly selected to provide a training set for constructing decision tree and multiple logistic regression (MLR) models. The remaining 30{\%} (n: 204) were employed in a holdout sample to test the performance of the decision tree and MLR models. Predictive performance of different models was analyzed by the receiver operating characteristic (ROC) curve using the testing set. Independent variables were selected from demographic characteristics and history of drug use. Results: For the decision tree model, the sensitivity and specificity for identifying people at risk for drug abuse were 66{\%} and 75{\%}, respectively, while the MLR model was somewhat less effective at 60{\%} and 73{\%}. Key independent variables in the analyses included first substance experience, age at first drug use, age, place of residence, history of cigarette use, and occupational and marital status. Discussion and Conclusion: While study findings are exploratory and lack generalizability they do suggest that the decision tree model holds promise as an effective classification approach for identifying risk factors for drug use. Convergent with prior research in Western contexts is that age of drug use initiation was a critical factor predicting a substance use disorder.",
author = "Alireza Amirabadizadeh and Hossein Nezami and Vaughn, {Michael G.} and Samaneh Nakhaee and Omid Mehrpour",
year = "2018",
month = "5",
day = "12",
doi = "10.1080/10826084.2017.1392981",
language = "English",
volume = "53",
pages = "1030--1040",
journal = "Substance Use and Misuse",
issn = "1082-6084",
publisher = "Informa Healthcare",
number = "6",

}

Identifying Risk Factors for Drug Use in an Iranian Treatment Sample : A Prediction Approach Using Decision Trees. / Amirabadizadeh, Alireza; Nezami, Hossein; Vaughn, Michael G.; Nakhaee, Samaneh; Mehrpour, Omid.

In: Substance Use and Misuse, Vol. 53, No. 6, 12.05.2018, p. 1030-1040.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Identifying Risk Factors for Drug Use in an Iranian Treatment Sample

T2 - A Prediction Approach Using Decision Trees

AU - Amirabadizadeh, Alireza

AU - Nezami, Hossein

AU - Vaughn, Michael G.

AU - Nakhaee, Samaneh

AU - Mehrpour, Omid

PY - 2018/5/12

Y1 - 2018/5/12

N2 - Introduction and aim: Substance abuse exacts considerable social and health care burdens throughout the world. The aim of this study was to create a prediction model to better identify risk factors for drug use. Design and Methods: A prospective cross-sectional study was conducted in South Khorasan Province, Iran. Of the total of 678 eligible subjects, 70% (n: 474) were randomly selected to provide a training set for constructing decision tree and multiple logistic regression (MLR) models. The remaining 30% (n: 204) were employed in a holdout sample to test the performance of the decision tree and MLR models. Predictive performance of different models was analyzed by the receiver operating characteristic (ROC) curve using the testing set. Independent variables were selected from demographic characteristics and history of drug use. Results: For the decision tree model, the sensitivity and specificity for identifying people at risk for drug abuse were 66% and 75%, respectively, while the MLR model was somewhat less effective at 60% and 73%. Key independent variables in the analyses included first substance experience, age at first drug use, age, place of residence, history of cigarette use, and occupational and marital status. Discussion and Conclusion: While study findings are exploratory and lack generalizability they do suggest that the decision tree model holds promise as an effective classification approach for identifying risk factors for drug use. Convergent with prior research in Western contexts is that age of drug use initiation was a critical factor predicting a substance use disorder.

AB - Introduction and aim: Substance abuse exacts considerable social and health care burdens throughout the world. The aim of this study was to create a prediction model to better identify risk factors for drug use. Design and Methods: A prospective cross-sectional study was conducted in South Khorasan Province, Iran. Of the total of 678 eligible subjects, 70% (n: 474) were randomly selected to provide a training set for constructing decision tree and multiple logistic regression (MLR) models. The remaining 30% (n: 204) were employed in a holdout sample to test the performance of the decision tree and MLR models. Predictive performance of different models was analyzed by the receiver operating characteristic (ROC) curve using the testing set. Independent variables were selected from demographic characteristics and history of drug use. Results: For the decision tree model, the sensitivity and specificity for identifying people at risk for drug abuse were 66% and 75%, respectively, while the MLR model was somewhat less effective at 60% and 73%. Key independent variables in the analyses included first substance experience, age at first drug use, age, place of residence, history of cigarette use, and occupational and marital status. Discussion and Conclusion: While study findings are exploratory and lack generalizability they do suggest that the decision tree model holds promise as an effective classification approach for identifying risk factors for drug use. Convergent with prior research in Western contexts is that age of drug use initiation was a critical factor predicting a substance use disorder.

UR - http://www.scopus.com/inward/record.url?scp=85035095376&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85035095376&partnerID=8YFLogxK

U2 - 10.1080/10826084.2017.1392981

DO - 10.1080/10826084.2017.1392981

M3 - Article

C2 - 29172870

AN - SCOPUS:85035095376

VL - 53

SP - 1030

EP - 1040

JO - Substance Use and Misuse

JF - Substance Use and Misuse

SN - 1082-6084

IS - 6

ER -