Predicting smoking cessation, reduction and relapse six months after using the Stop-Tabac app for smartphones: a machine learning analysis
Bibliographic record
Abstract
BACKGROUND: An analysis of predictors of smoking behaviour among users of smoking cessation apps can provide useful information beyond what is already known about predictors in other contexts. Therefore, the aim of the present study was to identify the best predictors of smoking cessation, smoking reduction and relapse six months after starting to use the smartphone app Stop-Tabac. METHOD: Secondary analysis of 5293 daily smokers from Switzerland and France who participated in a randomised trial testing the effectiveness of this app in 2020, with follow-up at one and six months. Machine learning algorithms were used to analyse the data. The analyses for smoking cessation included only the 1407 participants who responded after six months; the analysis for smoking reduction included only the 673 smokers at 6-month follow-up; and the analysis for relapse at 6 months included only the 502 individuals who had quit smoking after one month. RESULTS: Smoking cessation after 6 months was predicted by the following factors (in this order): tobacco dependence, motivation to quit smoking, frequency of app use and its perceived usefulness, and nicotine medication use. Among those who were still smoking at follow-up, reduction in cigarettes/day was predicted by tobacco dependence, nicotine medication use, frequency of app use and its perceived usefulness, and e-cigarette use. Among those who had quit smoking after one month, relapse after six months was predicted by intention to quit, frequency of app use, perceived usefulness of the app, level of dependence and nicotine medication use. CONCLUSION: Using machine learning algorithms, we identified independent predictors of smoking cessation, smoking reduction and relapse. Studies on the predictors of smoking behavior among users of smoking cessation apps may provide useful insights for the future development of these apps and future experimental studies. CLINICAL TRIAL REGISTRATION: ISRCTN Registry: ISRCTN11318024, 17 May 2018. http://www.isrctn.com/ISRCTN11318024 .
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.004 | 0.010 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
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".