Using a data science approach to predict cocaine use frequency from depressive symptoms
•Most of the items from the BDI-II are nonlinearly related to cocaine use severity.•Prior research has not explored the nonlinear nature of these relationships.•Findings support use of machine learning algorithms to understand drug abuse data.•Best predictors of cocaine use were emotional volatility...
Gespeichert in:
| Veröffentlicht in: | Drug and alcohol dependence 2019-01, Vol.194, p.310-317 |
|---|---|
| Hauptverfasser: | , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 317 |
|---|---|
| container_issue | |
| container_start_page | 310 |
| container_title | Drug and alcohol dependence |
| container_volume | 194 |
| creator | Suchting, Robert Vincent, Jessica N. Lane, Scott D. Green, Charles E. Schmitz, Joy M. Wardle, Margaret C. |
| description | •Most of the items from the BDI-II are nonlinearly related to cocaine use severity.•Prior research has not explored the nonlinear nature of these relationships.•Findings support use of machine learning algorithms to understand drug abuse data.•Best predictors of cocaine use were emotional volatility and disregard for future.•Future interventions may target these depressive symptoms.
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.
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.
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.
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. |
| doi_str_mv | 10.1016/j.drugalcdep.2018.10.029 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_6317336</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0376871618308093</els_id><sourcerecordid>2176702710</sourcerecordid><originalsourceid>FETCH-LOGICAL-c533t-b460d779dfd8f0585775484933577f0724d3ee25659f26352555775494632a2c3</originalsourceid><addsrcrecordid>eNqFkU1PGzEQhq0KVELgLyBLPW_wx9revSAVREulSFxAHC3Hng2OsuvF3o2Uf49DQmhP9cWjmWfeGftFCFMyo4TK69XMxXFp1tZBP2OEVjk9I6z-hia0UnVBSClP0IRwJYtKUXmGzlNakXxkTb6jM05KxYSiE_TynHy3xAY7MxicrIfOAjZ9H4Oxr3gIuI_gvB2wDdb4DvCYADcR3sZMbnMUWpy3iJCS3wBO27YfQpsu0Glj1gkuD_cUPf-6f7p7KOaPv__c_ZwXVnA-FItSEqdU7RpXNURUQilRVmXNeY4aoljpOAATUtQNk1wwIT6QupScGWb5FN3sdftx0YKz0A3RrHUffWviVgfj9b-Vzr_qZdhoyaniXGaBHweBGPKb0qBXYYxd3lkzqqQiTFGSqWpP2RhSitAcJ1Cid5bolf6yRO8s2VWyJbn16u8Nj42fHmTgdg9A_qeNh6gPNjgfwQ7aBf__Ke8WtaJh</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2176702710</pqid></control><display><type>article</type><title>Using a data science approach to predict cocaine use frequency from depressive symptoms</title><source>Applied Social Sciences Index & Abstracts (ASSIA)</source><source>MEDLINE</source><source>Elsevier ScienceDirect Journals</source><creator>Suchting, Robert ; Vincent, Jessica N. ; Lane, Scott D. ; Green, Charles E. ; Schmitz, Joy M. ; Wardle, Margaret C.</creator><creatorcontrib>Suchting, Robert ; Vincent, Jessica N. ; Lane, Scott D. ; Green, Charles E. ; Schmitz, Joy M. ; Wardle, Margaret C.</creatorcontrib><description>•Most of the items from the BDI-II are nonlinearly related to cocaine use severity.•Prior research has not explored the nonlinear nature of these relationships.•Findings support use of machine learning algorithms to understand drug abuse data.•Best predictors of cocaine use were emotional volatility and disregard for future.•Future interventions may target these depressive symptoms.
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.
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.
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.
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.</description><identifier>ISSN: 0376-8716</identifier><identifier>EISSN: 1879-0046</identifier><identifier>DOI: 10.1016/j.drugalcdep.2018.10.029</identifier><identifier>PMID: 30472571</identifier><language>eng</language><publisher>Ireland: Elsevier B.V</publisher><subject>Addiction ; Addictions ; Adult ; Anhedonia ; Appetite ; Beck Depression Inventory 2nd Edition ; Cocaine ; Cocaine-Related Disorders - epidemiology ; Cocaine-Related Disorders - psychology ; Crying ; Data Interpretation, Statistical ; Data Science ; Decision making ; Depression - etiology ; Depression - psychology ; Depressive symptoms ; Drug abuse ; Drug addiction ; Female ; Generalized additive model ; Hedonic response ; Heterogeneity ; Humans ; Linearity ; Machine Learning ; Male ; Mathematical models ; Mental depression ; Middle Aged ; Models, Theoretical ; Narcotics ; Nonlinearity ; Pessimism ; Predictive Value of Tests ; Psychiatric Status Rating Scales ; Qualitative analysis ; Qualitative research ; Severity ; Signs and symptoms ; Subtypes ; Suicidal ideation ; Suicide ; Volatility</subject><ispartof>Drug and alcohol dependence, 2019-01, Vol.194, p.310-317</ispartof><rights>2018 Elsevier B.V.</rights><rights>Copyright © 2018 Elsevier B.V. All rights reserved.</rights><rights>Copyright Elsevier Science Ltd. Jan 1, 2019</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c533t-b460d779dfd8f0585775484933577f0724d3ee25659f26352555775494632a2c3</citedby><cites>FETCH-LOGICAL-c533t-b460d779dfd8f0585775484933577f0724d3ee25659f26352555775494632a2c3</cites><orcidid>0000-0001-6071-6105 ; 0000-0002-2822-3754</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.sciencedirect.com/science/article/pii/S0376871618308093$$EHTML$$P50$$Gelsevier$$H</linktohtml><link.rule.ids>230,314,776,780,881,3537,27901,27902,30976,65306</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/30472571$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Suchting, Robert</creatorcontrib><creatorcontrib>Vincent, Jessica N.</creatorcontrib><creatorcontrib>Lane, Scott D.</creatorcontrib><creatorcontrib>Green, Charles E.</creatorcontrib><creatorcontrib>Schmitz, Joy M.</creatorcontrib><creatorcontrib>Wardle, Margaret C.</creatorcontrib><title>Using a data science approach to predict cocaine use frequency from depressive symptoms</title><title>Drug and alcohol dependence</title><addtitle>Drug Alcohol Depend</addtitle><description>•Most of the items from the BDI-II are nonlinearly related to cocaine use severity.•Prior research has not explored the nonlinear nature of these relationships.•Findings support use of machine learning algorithms to understand drug abuse data.•Best predictors of cocaine use were emotional volatility and disregard for future.•Future interventions may target these depressive symptoms.
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.
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.
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.
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.</description><subject>Addiction</subject><subject>Addictions</subject><subject>Adult</subject><subject>Anhedonia</subject><subject>Appetite</subject><subject>Beck Depression Inventory 2nd Edition</subject><subject>Cocaine</subject><subject>Cocaine-Related Disorders - epidemiology</subject><subject>Cocaine-Related Disorders - psychology</subject><subject>Crying</subject><subject>Data Interpretation, Statistical</subject><subject>Data Science</subject><subject>Decision making</subject><subject>Depression - etiology</subject><subject>Depression - psychology</subject><subject>Depressive symptoms</subject><subject>Drug abuse</subject><subject>Drug addiction</subject><subject>Female</subject><subject>Generalized additive model</subject><subject>Hedonic response</subject><subject>Heterogeneity</subject><subject>Humans</subject><subject>Linearity</subject><subject>Machine Learning</subject><subject>Male</subject><subject>Mathematical models</subject><subject>Mental depression</subject><subject>Middle Aged</subject><subject>Models, Theoretical</subject><subject>Narcotics</subject><subject>Nonlinearity</subject><subject>Pessimism</subject><subject>Predictive Value of Tests</subject><subject>Psychiatric Status Rating Scales</subject><subject>Qualitative analysis</subject><subject>Qualitative research</subject><subject>Severity</subject><subject>Signs and symptoms</subject><subject>Subtypes</subject><subject>Suicidal ideation</subject><subject>Suicide</subject><subject>Volatility</subject><issn>0376-8716</issn><issn>1879-0046</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><sourceid>EIF</sourceid><sourceid>7QJ</sourceid><recordid>eNqFkU1PGzEQhq0KVELgLyBLPW_wx9revSAVREulSFxAHC3Hng2OsuvF3o2Uf49DQmhP9cWjmWfeGftFCFMyo4TK69XMxXFp1tZBP2OEVjk9I6z-hia0UnVBSClP0IRwJYtKUXmGzlNakXxkTb6jM05KxYSiE_TynHy3xAY7MxicrIfOAjZ9H4Oxr3gIuI_gvB2wDdb4DvCYADcR3sZMbnMUWpy3iJCS3wBO27YfQpsu0Glj1gkuD_cUPf-6f7p7KOaPv__c_ZwXVnA-FItSEqdU7RpXNURUQilRVmXNeY4aoljpOAATUtQNk1wwIT6QupScGWb5FN3sdftx0YKz0A3RrHUffWviVgfj9b-Vzr_qZdhoyaniXGaBHweBGPKb0qBXYYxd3lkzqqQiTFGSqWpP2RhSitAcJ1Cid5bolf6yRO8s2VWyJbn16u8Nj42fHmTgdg9A_qeNh6gPNjgfwQ7aBf__Ke8WtaJh</recordid><startdate>20190101</startdate><enddate>20190101</enddate><creator>Suchting, Robert</creator><creator>Vincent, Jessica N.</creator><creator>Lane, Scott D.</creator><creator>Green, Charles E.</creator><creator>Schmitz, Joy M.</creator><creator>Wardle, Margaret C.</creator><general>Elsevier B.V</general><general>Elsevier Science Ltd</general><scope>CGR</scope><scope>CUY</scope><scope>CVF</scope><scope>ECM</scope><scope>EIF</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7QJ</scope><scope>7TK</scope><scope>7U7</scope><scope>C1K</scope><scope>K9.</scope><scope>NAPCQ</scope><scope>5PM</scope><orcidid>https://orcid.org/0000-0001-6071-6105</orcidid><orcidid>https://orcid.org/0000-0002-2822-3754</orcidid></search><sort><creationdate>20190101</creationdate><title>Using a data science approach to predict cocaine use frequency from depressive symptoms</title><author>Suchting, Robert ; Vincent, Jessica N. ; Lane, Scott D. ; Green, Charles E. ; Schmitz, Joy M. ; Wardle, Margaret C.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c533t-b460d779dfd8f0585775484933577f0724d3ee25659f26352555775494632a2c3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Addiction</topic><topic>Addictions</topic><topic>Adult</topic><topic>Anhedonia</topic><topic>Appetite</topic><topic>Beck Depression Inventory 2nd Edition</topic><topic>Cocaine</topic><topic>Cocaine-Related Disorders - epidemiology</topic><topic>Cocaine-Related Disorders - psychology</topic><topic>Crying</topic><topic>Data Interpretation, Statistical</topic><topic>Data Science</topic><topic>Decision making</topic><topic>Depression - etiology</topic><topic>Depression - psychology</topic><topic>Depressive symptoms</topic><topic>Drug abuse</topic><topic>Drug addiction</topic><topic>Female</topic><topic>Generalized additive model</topic><topic>Hedonic response</topic><topic>Heterogeneity</topic><topic>Humans</topic><topic>Linearity</topic><topic>Machine Learning</topic><topic>Male</topic><topic>Mathematical models</topic><topic>Mental depression</topic><topic>Middle Aged</topic><topic>Models, Theoretical</topic><topic>Narcotics</topic><topic>Nonlinearity</topic><topic>Pessimism</topic><topic>Predictive Value of Tests</topic><topic>Psychiatric Status Rating Scales</topic><topic>Qualitative analysis</topic><topic>Qualitative research</topic><topic>Severity</topic><topic>Signs and symptoms</topic><topic>Subtypes</topic><topic>Suicidal ideation</topic><topic>Suicide</topic><topic>Volatility</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Suchting, Robert</creatorcontrib><creatorcontrib>Vincent, Jessica N.</creatorcontrib><creatorcontrib>Lane, Scott D.</creatorcontrib><creatorcontrib>Green, Charles E.</creatorcontrib><creatorcontrib>Schmitz, Joy M.</creatorcontrib><creatorcontrib>Wardle, Margaret C.</creatorcontrib><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>Applied Social Sciences Index & Abstracts (ASSIA)</collection><collection>Neurosciences Abstracts</collection><collection>Toxicology Abstracts</collection><collection>Environmental Sciences and Pollution Management</collection><collection>ProQuest Health & Medical Complete (Alumni)</collection><collection>Nursing & Allied Health Premium</collection><collection>PubMed Central (Full Participant titles)</collection><jtitle>Drug and alcohol dependence</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Suchting, Robert</au><au>Vincent, Jessica N.</au><au>Lane, Scott D.</au><au>Green, Charles E.</au><au>Schmitz, Joy M.</au><au>Wardle, Margaret C.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Using a data science approach to predict cocaine use frequency from depressive symptoms</atitle><jtitle>Drug and alcohol dependence</jtitle><addtitle>Drug Alcohol Depend</addtitle><date>2019-01-01</date><risdate>2019</risdate><volume>194</volume><spage>310</spage><epage>317</epage><pages>310-317</pages><issn>0376-8716</issn><eissn>1879-0046</eissn><abstract>•Most of the items from the BDI-II are nonlinearly related to cocaine use severity.•Prior research has not explored the nonlinear nature of these relationships.•Findings support use of machine learning algorithms to understand drug abuse data.•Best predictors of cocaine use were emotional volatility and disregard for future.•Future interventions may target these depressive symptoms.
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.
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.
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.
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.</abstract><cop>Ireland</cop><pub>Elsevier B.V</pub><pmid>30472571</pmid><doi>10.1016/j.drugalcdep.2018.10.029</doi><tpages>8</tpages><orcidid>https://orcid.org/0000-0001-6071-6105</orcidid><orcidid>https://orcid.org/0000-0002-2822-3754</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0376-8716 |
| ispartof | Drug and alcohol dependence, 2019-01, Vol.194, p.310-317 |
| issn | 0376-8716 1879-0046 |
| language | eng |
| recordid | cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_6317336 |
| source | Applied Social Sciences Index & Abstracts (ASSIA); MEDLINE; Elsevier ScienceDirect Journals |
| subjects | Addiction Addictions Adult Anhedonia Appetite Beck Depression Inventory 2nd Edition Cocaine Cocaine-Related Disorders - epidemiology Cocaine-Related Disorders - psychology Crying Data Interpretation, Statistical Data Science Decision making Depression - etiology Depression - psychology Depressive symptoms Drug abuse Drug addiction Female Generalized additive model Hedonic response Heterogeneity Humans Linearity Machine Learning Male Mathematical models Mental depression Middle Aged Models, Theoretical Narcotics Nonlinearity Pessimism Predictive Value of Tests Psychiatric Status Rating Scales Qualitative analysis Qualitative research Severity Signs and symptoms Subtypes Suicidal ideation Suicide Volatility |
| title | Using a data science approach to predict cocaine use frequency from depressive symptoms |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-08T17%3A23%3A58IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_pubme&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Using%20a%20data%20science%20approach%20to%20predict%20cocaine%20use%20frequency%20from%20depressive%20symptoms&rft.jtitle=Drug%20and%20alcohol%20dependence&rft.au=Suchting,%20Robert&rft.date=2019-01-01&rft.volume=194&rft.spage=310&rft.epage=317&rft.pages=310-317&rft.issn=0376-8716&rft.eissn=1879-0046&rft_id=info:doi/10.1016/j.drugalcdep.2018.10.029&rft_dat=%3Cproquest_pubme%3E2176702710%3C/proquest_pubme%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2176702710&rft_id=info:pmid/30472571&rft_els_id=S0376871618308093&rfr_iscdi=true |