Machine learning models struggled to predict who would respond to cannabis use disorder treatment
Using data from a multi-site clinical trial, machine learning and traditional models achieved only modest accuracy in predicting cannabis use disorder treatment response, suggesting better predictors are needed.
Quick Facts
What This Study Found
Both multivariable logistic regression and machine learning models (random forest, gradient boosting) had limited ability to classify CUD treatment responders versus non-responders. Prediction accuracy was modest, indicating that commonly measured variables do not strongly predict treatment response.
Key Numbers
Multi-site clinical trial data used. Multiple machine learning approaches tested (random forest, gradient boosting, logistic regression). All achieved modest classification accuracy for treatment response.
How They Did This
Secondary analysis of a National Drug Abuse Treatment Clinical Trials Network multi-site outpatient trial. Adult CUD patients were assessed with multivariable logistic regression and machine learning models (random forest, gradient boosting) to predict treatment response.
Why This Research Matters
CUD treatments have limited efficacy overall. If clinicians could identify who will respond to which treatment approach, they could personalize care and improve outcomes. This study shows current predictive tools fall short.
The Bigger Picture
Precision medicine for substance use disorders lags behind other fields. The inability to predict treatment response for CUD suggests either better biomarkers are needed or that treatment response depends on factors not typically measured in clinical trials.
What This Study Doesn't Tell Us
Secondary analysis limited to variables collected in the original trial. Treatment was a specific multi-component protocol that may not generalize. Machine learning models can overfit to training data. Modest sample sizes may limit model performance.
Questions This Raises
- ?Would biological markers (genetics, neuroimaging) improve prediction accuracy?
- ?Are there treatment-matching variables that differ from treatment-response variables?
Trust & Context
- Key Stat:
- All prediction models achieved only modest accuracy for CUD treatment response
- Evidence Grade:
- Secondary analysis of a well-conducted multi-site trial with appropriate statistical methods. Limited by available variables and inherent prediction difficulty.
- Study Age:
- Published 2023.
- Original Title:
- Who responds to a multi-component treatment for cannabis use disorder? Using multivariable and machine learning models to classify treatment responders and non-responders.
- Published In:
- Addiction (Abingdon, England), 118(10), 1965-1974 (2023)
- Authors:
- Tomko, Rachel L(11), Wolf, Bethany J(3), McClure, Erin A(11), Carpenter, Matthew J, Magruder, Kathryn M, Squeglia, Lindsay M, Gray, Kevin M
- Database ID:
- RTHC-04984
Evidence Hierarchy
Frequently Asked Questions
Can we predict who will benefit from cannabis use disorder treatment?
Not well, according to this study. Even with advanced machine learning techniques, prediction accuracy was modest. This suggests that the variables typically measured in clinical settings (demographics, use history, co-occurring conditions) do not capture the full picture of what makes someone respond to treatment.
Why is predicting treatment response important?
If clinicians could identify likely responders before treatment begins, they could match patients to the most effective interventions, allocate intensive resources to those who need them most, and spare others from ineffective treatments.
Read More on RethinkTHC
- 30-days-without-weed
- 420-sober-survival-guide
- 6-months-sober-weed-what-to-expect
- 90-days-no-weed
- CBT-cannabis-recovery
- benefits-of-quitting-weed
- boredom-after-quitting-weed
- boredom-after-quitting-weed-nothing-fun
- cannabis-dependence-physical-psychological-addiction-science
- cannabis-perception-vs-evidence-gap
- cannabis-relapse-cycle-pattern
- cannabis-use-disorder-test
- cold-turkey-vs-taper-quit-weed
- creativity-without-weed-quitting-artist-musician
- cross-addiction-quit-weed-start-drinking
- dating-sober-after-quitting-weed
- exercise-quitting-weed-anxiety-brain
- grieving-quitting-weed-loss
- help-someone-quit-weed
- hobbies-after-quitting-weed
- how-to-quit-weed
- identity-after-quitting-weed
- is-weed-addictive
- is-weed-addictive-science
- journaling-weed-withdrawal
- leaving-stoner-culture-identity
- marijuana-anonymous-SMART-recovery-compare
- meditation-mindfulness-weed-withdrawal
- money-saved-quitting-weed-calculator
- one-year-sober-weed
- partner-still-smokes-weed
- partner-still-smokes-weed-quitting
- pink-cloud-sobriety-cannabis
- quit-weed-cold-turkey
- quit-weed-or-cut-back-which-is-better
- quit-weed-regret-went-back
- quitting-weed-20s
- quitting-weed-30s
- quitting-weed-after-years
- quitting-weed-and-alcohol
- quitting-weed-creativity
- quitting-weed-during-crisis-divorce-job-loss
- quitting-weed-exercise
- quitting-weed-face-changes-skin
- quitting-weed-grief-loss-coping
- quitting-weed-legal-state
- quitting-weed-success-stories
- quitting-weed-triggers-environment
- quitting-weed-weight-loss-gain
- rehab-for-weed-addiction-necessary
- relapsed-smoking-weed-what-to-do
- relapsed-weed
- should-i-quit-weed
- signs-of-cannabis-use-disorder
- sober-music-festival-concert-without-weed
- supplements-weed-withdrawal
- telling-friends-quitting-weed
- weed-relapse-prevention-plan
- weed-relapse-why-it-happens
- weed-ritual-replacement
- weed-ruined-relationships
- weed-social-media-triggers-quit
- weed-vape-pen-addiction
Cite This Study
https://rethinkthc.com/research/RTHC-04984APA
Tomko, Rachel L; Wolf, Bethany J; McClure, Erin A; Carpenter, Matthew J; Magruder, Kathryn M; Squeglia, Lindsay M; Gray, Kevin M. (2023). Who responds to a multi-component treatment for cannabis use disorder? Using multivariable and machine learning models to classify treatment responders and non-responders.. Addiction (Abingdon, England), 118(10), 1965-1974. https://doi.org/10.1111/add.16226
MLA
Tomko, Rachel L, et al. "Who responds to a multi-component treatment for cannabis use disorder? Using multivariable and machine learning models to classify treatment responders and non-responders.." Addiction (Abingdon, 2023. https://doi.org/10.1111/add.16226
RethinkTHC
RethinkTHC Research Database. "Who responds to a multi-component treatment for cannabis use..." RTHC-04984. Retrieved from https://rethinkthc.com/research/tomko-2023-who-responds-to-a
Access the Original Study
Study data sourced from PubMed, a service of the U.S. National Library of Medicine, National Institutes of Health.
This study breakdown was produced by the RethinkTHC research team. We analyze and report published research findings without making health recommendations. All interpretations are based solely on the published abstract and study data.