MétaCan
Menu
Back to cohort
Record W2983958955 · doi:10.1093/ntr/ntz211

Toward Precision Medicine for Smoking Cessation: Developing a Neuroimaging-Based Classification Algorithm to Identify Smokers at Higher Risk for Relapse

2019· article· en· W2983958955 on OpenAlexafffund
David W. Frank, Paul M. Cinciripini, Menton M. Deweese, Maher Karam‐Hage, George Kypriotakis, Caryn Lerman, Jason D. Robinson, Rachel F. Tyndale, Damon J. Vidrine, Francesco Versace

Bibliographic record

VenueNicotine & Tobacco Research · 2019
Typearticle
Languageen
FieldMedicine
TopicSmoking Behavior and Cessation
Canadian institutionsUniversity of TorontoCentre for Addiction and Mental Health
FundersNational Cancer InstituteNational Institute on Drug AbuseCanadian Institutes of Health ResearchNational Institutes of Health
KeywordsAbstinenceNeuroimagingSmoking cessationAddictionMedicineClinical psychologyDiscriminant function analysisPsychological interventionPsychiatryPsychologyAlgorithmInternal medicineMachine learningPathologyComputer science

Abstract

fetched live from OpenAlex

INTRODUCTION: By improving our understanding of the neurobiological mechanisms underlying addiction, neuroimaging research is helping to identify new targets for personalized treatment interventions. When trying to quit, smokers with larger electrophysiological responses to cigarette-related, compared with pleasant, stimuli ("C > P") are more likely to relapse than smokers with the opposite brain reactivity profile ("P > C"). AIM AND METHOD: The goal was to (1) build a classification algorithm to identify smokers characterized by P > C or C > P neuroaffective profiles and (2) validate the algorithm's classification outcomes in an independent data set where we assessed both smokers' electrophysiological responses at baseline and smoking abstinence during a quit attempt. We built the classification algorithm applying discriminant function analysis on the event-related potentials evoked by emotional images in 180 smokers. RESULTS: The predictive validity of the classifier showed promise in an independent data set that included new data from 177 smokers interested in quitting; the algorithm classified 111 smokers as P > C and 66 as C > P. The overall abstinence rate was low; 15 individuals (8.5% of the sample) achieved CO-verified 12-month abstinence. Although individuals classified as P > C were nearly 2.5 times more likely to be abstinent than smokers classified as C > P (12 vs. 3, or 11% vs. 4.5%), this result was nonsignificant, preliminary, and in need of confirmation in larger trials. CONCLUSION: These results suggest that psychophysiological techniques have the potential to advance our knowledge of the neurobiological underpinnings of nicotine addiction and improve clinical applications. However, larger sample sizes are necessary to reliably assess the predictive ability of our algorithm. IMPLICATIONS: We assessed the clinical relevance of a neuroimaging-based classification algorithm on an independent sample of smokers enrolled in a smoking cessation trial and found those with the tendency to attribute more relevance to rewards than cues were nearly 2.5 times more likely to be abstinent than smokers with the opposite brain reactivity profile (11% vs. 4.5%). Although this result was not statistically significant, it suggests our neuroimaging-based classification algorithm can potentially contribute to the development of new precision medicine interventions aimed at treating substance use disorders. Regardless, these findings are still preliminary and in need of confirmation in larger trials.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.004
metaresearch head score (Gemma)0.002
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: Observational
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.149
Threshold uncertainty score0.995

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0040.002
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.203
GPT teacher head0.454
Teacher spread0.251 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designObservational
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations17
Published2019
Admission routes2
Has abstractyes

Explore more

Same venueNicotine & Tobacco ResearchSame topicSmoking Behavior and CessationFrench-language works237,207