Using a data science approach to predict cocaine use frequency from depressive symptoms

Robert Suchting, Jessica N. Vincent, Scott D Lane, Charles Green, Joy M Schmitz, Margaret C Wardle

Research output: Contribution to journalArticle

Abstract

Background: Depressive symptoms may contribute to cocaine use. However, tests of the relationship between depression and severity of cocaine use have produced mixed results, possibly due to heterogeneity in individual symptoms of depression. Our goal was to establish which symptoms of depression are most strongly related to frequency of cocaine use (one aspect of severity) in a large sample of current cocaine users. We utilized generalized additive modeling to provide data-driven exploration of the relationships between depressive symptoms and cocaine use, including examination of non-linearity. We hypothesized that symptoms related to anhedonia would demonstrate the strongest relationship to cocaine use. Method: 772 individuals screened for cocaine use disorder treatment studies. To measure depressive symptoms, we used the items of the Beck Depression Inventory, 2nd Edition. Cocaine use frequency was measured as proportion of self-reported days of cocaine use over the last 30 days using the Addiction Severity Index. Results: Models identified 18 significant predictors of past-30-day cocaine use. The strongest predictors were Crying, Pessimism, Changes in Appetite, Indecisiveness, and Loss of Interest. Noteworthy effect sizes were found for specific response options on Suicidal Thoughts, Worthlessness, Agitation, Concentration Difficulty, Tiredness, and Self Dislike items. Conclusions: The strongest predictors did not conform to previously hypothesized “subtypes” of depression. Non-linear relationships between items and use were typical, suggesting BDI-II items may not be monotonically increasing ordinal measures with respect to predicting cocaine use. Qualitative analysis of strongly predictive response options suggested emotional volatility and disregard for the future as important predictors of use.

Original languageEnglish
Pages (from-to)310-317
Number of pages8
JournalDrug and Alcohol Dependence
Volume194
DOIs
StatePublished - Jan 1 2019

Fingerprint

Cocaine
Depression
Anhedonia
Crying
Volatilization
Ego
Appetite
Equipment and Supplies

Keywords

  • Addiction
  • Beck Depression Inventory 2nd Edition
  • Cocaine
  • Depressive symptoms
  • Drug abuse
  • Generalized additive model
  • Machine learning

ASJC Scopus subject areas

  • Toxicology
  • Pharmacology
  • Psychiatry and Mental health
  • Pharmacology (medical)

Cite this

Suchting, R., Vincent, J. N., Lane, S. D., Green, C., Schmitz, J. M., & Wardle, M. C. (2019). Using a data science approach to predict cocaine use frequency from depressive symptoms. Drug and Alcohol Dependence, 194, 310-317. https://doi.org/10.1016/j.drugalcdep.2018.10.029

Using a data science approach to predict cocaine use frequency from depressive symptoms. / Suchting, Robert; Vincent, Jessica N.; Lane, Scott D; Green, Charles; Schmitz, Joy M; Wardle, Margaret C.

In: Drug and Alcohol Dependence, Vol. 194, 01.01.2019, p. 310-317.

Research output: Contribution to journalArticle

Suchting, Robert ; Vincent, Jessica N. ; Lane, Scott D ; Green, Charles ; Schmitz, Joy M ; Wardle, Margaret C. / Using a data science approach to predict cocaine use frequency from depressive symptoms. In: Drug and Alcohol Dependence. 2019 ; Vol. 194. pp. 310-317.
@article{cea27e052f344e9ab71bd6d9e6c1d3f9,
title = "Using a data science approach to predict cocaine use frequency from depressive symptoms",
abstract = "Background: Depressive symptoms may contribute to cocaine use. However, tests of the relationship between depression and severity of cocaine use have produced mixed results, possibly due to heterogeneity in individual symptoms of depression. Our goal was to establish which symptoms of depression are most strongly related to frequency of cocaine use (one aspect of severity) in a large sample of current cocaine users. We utilized generalized additive modeling to provide data-driven exploration of the relationships between depressive symptoms and cocaine use, including examination of non-linearity. We hypothesized that symptoms related to anhedonia would demonstrate the strongest relationship to cocaine use. Method: 772 individuals screened for cocaine use disorder treatment studies. To measure depressive symptoms, we used the items of the Beck Depression Inventory, 2nd Edition. Cocaine use frequency was measured as proportion of self-reported days of cocaine use over the last 30 days using the Addiction Severity Index. Results: Models identified 18 significant predictors of past-30-day cocaine use. The strongest predictors were Crying, Pessimism, Changes in Appetite, Indecisiveness, and Loss of Interest. Noteworthy effect sizes were found for specific response options on Suicidal Thoughts, Worthlessness, Agitation, Concentration Difficulty, Tiredness, and Self Dislike items. Conclusions: The strongest predictors did not conform to previously hypothesized “subtypes” of depression. Non-linear relationships between items and use were typical, suggesting BDI-II items may not be monotonically increasing ordinal measures with respect to predicting cocaine use. Qualitative analysis of strongly predictive response options suggested emotional volatility and disregard for the future as important predictors of use.",
keywords = "Addiction, Beck Depression Inventory 2nd Edition, Cocaine, Depressive symptoms, Drug abuse, Generalized additive model, Machine learning",
author = "Robert Suchting and Vincent, {Jessica N.} and Lane, {Scott D} and Charles Green and Schmitz, {Joy M} and Wardle, {Margaret C}",
year = "2019",
month = "1",
day = "1",
doi = "10.1016/j.drugalcdep.2018.10.029",
language = "English",
volume = "194",
pages = "310--317",
journal = "Drug and Alcohol Dependence",
issn = "0376-8716",
publisher = "Elsevier Ireland Ltd",

}

TY - JOUR

T1 - Using a data science approach to predict cocaine use frequency from depressive symptoms

AU - Suchting, Robert

AU - Vincent, Jessica N.

AU - Lane, Scott D

AU - Green, Charles

AU - Schmitz, Joy M

AU - Wardle, Margaret C

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Background: Depressive symptoms may contribute to cocaine use. However, tests of the relationship between depression and severity of cocaine use have produced mixed results, possibly due to heterogeneity in individual symptoms of depression. Our goal was to establish which symptoms of depression are most strongly related to frequency of cocaine use (one aspect of severity) in a large sample of current cocaine users. We utilized generalized additive modeling to provide data-driven exploration of the relationships between depressive symptoms and cocaine use, including examination of non-linearity. We hypothesized that symptoms related to anhedonia would demonstrate the strongest relationship to cocaine use. Method: 772 individuals screened for cocaine use disorder treatment studies. To measure depressive symptoms, we used the items of the Beck Depression Inventory, 2nd Edition. Cocaine use frequency was measured as proportion of self-reported days of cocaine use over the last 30 days using the Addiction Severity Index. Results: Models identified 18 significant predictors of past-30-day cocaine use. The strongest predictors were Crying, Pessimism, Changes in Appetite, Indecisiveness, and Loss of Interest. Noteworthy effect sizes were found for specific response options on Suicidal Thoughts, Worthlessness, Agitation, Concentration Difficulty, Tiredness, and Self Dislike items. Conclusions: The strongest predictors did not conform to previously hypothesized “subtypes” of depression. Non-linear relationships between items and use were typical, suggesting BDI-II items may not be monotonically increasing ordinal measures with respect to predicting cocaine use. Qualitative analysis of strongly predictive response options suggested emotional volatility and disregard for the future as important predictors of use.

AB - Background: Depressive symptoms may contribute to cocaine use. However, tests of the relationship between depression and severity of cocaine use have produced mixed results, possibly due to heterogeneity in individual symptoms of depression. Our goal was to establish which symptoms of depression are most strongly related to frequency of cocaine use (one aspect of severity) in a large sample of current cocaine users. We utilized generalized additive modeling to provide data-driven exploration of the relationships between depressive symptoms and cocaine use, including examination of non-linearity. We hypothesized that symptoms related to anhedonia would demonstrate the strongest relationship to cocaine use. Method: 772 individuals screened for cocaine use disorder treatment studies. To measure depressive symptoms, we used the items of the Beck Depression Inventory, 2nd Edition. Cocaine use frequency was measured as proportion of self-reported days of cocaine use over the last 30 days using the Addiction Severity Index. Results: Models identified 18 significant predictors of past-30-day cocaine use. The strongest predictors were Crying, Pessimism, Changes in Appetite, Indecisiveness, and Loss of Interest. Noteworthy effect sizes were found for specific response options on Suicidal Thoughts, Worthlessness, Agitation, Concentration Difficulty, Tiredness, and Self Dislike items. Conclusions: The strongest predictors did not conform to previously hypothesized “subtypes” of depression. Non-linear relationships between items and use were typical, suggesting BDI-II items may not be monotonically increasing ordinal measures with respect to predicting cocaine use. Qualitative analysis of strongly predictive response options suggested emotional volatility and disregard for the future as important predictors of use.

KW - Addiction

KW - Beck Depression Inventory 2nd Edition

KW - Cocaine

KW - Depressive symptoms

KW - Drug abuse

KW - Generalized additive model

KW - Machine learning

UR - http://www.scopus.com/inward/record.url?scp=85056896565&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85056896565&partnerID=8YFLogxK

U2 - 10.1016/j.drugalcdep.2018.10.029

DO - 10.1016/j.drugalcdep.2018.10.029

M3 - Article

VL - 194

SP - 310

EP - 317

JO - Drug and Alcohol Dependence

T2 - Drug and Alcohol Dependence

JF - Drug and Alcohol Dependence

SN - 0376-8716

ER -