Predictors of smoking cessation outcomes identified by machine learning: A systematic review.
Ontology highlight
ABSTRACT:
SUBMITTER: Bickel WK
PROVIDER: S-EPMC10194042 | biostudies-literature | 2023 Jun
REPOSITORIES: biostudies-literature
Publications
Predictors of smoking cessation outcomes identified by machine learning: A systematic review.
Bickel Warren K WK Tomlinson Devin C DC Craft William H WH Ma Manxiu M Dwyer Candice L CL Yeh Yu-Hua YH Tegge Allison N AN Freitas-Lemos Roberta R Athamneh Liqa N LN
Addiction neuroscience 20230131
This systematic review aims to characterize the utility of machine learning to identify the predictors of smoking cessation outcomes and identify the machine learning methods applied in this area. In the current study, multiple searches occurred through December 9, 2022 in MEDLINE, Science Citation Index, Social Science Citation Index, EMBASE, CINAHL Plus, APA PsycINFO, PubMed, Cochrane Central Register of Controlled Trials, and the IEEE Xplore were performed. Inclusion criteria included various ...[more]
Similar Datasets
Project description:AimsMost cigarette smokers want to quit smoking and more than half make an attempt every year, but less than 10% remain abstinent for at least 6 months. Evidence-based tobacco use treatment improves the likelihood of quitting, but more than two-thirds of individuals relapse when provided even the most robust treatments. Identifying for whom treatment is effective will improve the success of our treatments and perhaps identify strategies for improving current approaches.MethodsTwo cohorts (training: N = 90, validation: N = 71) of cigarette smokers enrolled in group cognitive-behavioral therapy (CBT). Generalized estimating equations were used to identify baseline predictors of outcome, as defined by breath carbon monoxide and urine cotinine. Significant measures were entered as candidate variables to predict quit status. The resulting decision trees were used to predict cessation outcomes in a validation cohort.ResultsIn the training cohort, the decision trees significantly improved on chance classification of smoking status following treatment and at 6-month follow-up. The first split of all decision trees, which was delay discounting, significantly improved on chance classification rates in both the training and validation cohort. Delay discounting emerged as the single best predictor of group CBT treatment response with an average baseline discount rate of ln(k) = -7.1, correctly predicting smoking status of 80% of participants at posttreatment and 81% of participants at follow-up.ConclusionsThis study provides a first step toward personalized care for smoking cessation though future work is needed to identify individuals that are likely to be successful in treatments beyond group CBT.ImplicationsThis study provides a first step toward personalized care for smoking cessation. Using a novel machine-learning approach, baseline measures of clinical and executive functioning are used to predict smoking cessation outcomes following group CBT. A decision point is recommended for the single best predictor of treatment outcomes, delay discounting, to inform future research or clinical practice in an effort to better allocate patients to treatments that are likely to work.
| S-EPMC7297111 | biostudies-literature
Project description:AimsTemperament and impulsivity are powerful predictors of addiction treatment outcomes. However, a comprehensive assessment of these features has not been examined in relation to smoking cessation outcomes.MethodsNaturalistic prospective study. Treatment-seeking smokers (n = 140) were recruited as they engaged in an occupational health clinic providing smoking cessation treatment between 2009 and 2013. Participants were assessed at baseline with measures of temperament (Temperament and Character Inventory), trait impulsivity (Barratt Impulsivity Scale), and cognitive impulsivity (Go/No Go, Delay Discounting and Iowa Gambling Task). The outcome measure was treatment status, coded as "dropout" versus "relapse" versus "abstinence" at 3, 6, and 12 months endpoints. Participants were telephonically contacted and reminded of follow-up face to face assessments at each endpoint. The participants that failed to answer the phone calls or self-reported discontinuation of treatment and failed to attend the upcoming follow-up session were coded as dropouts. The participants that self-reported continuing treatment, and successfully attended the upcoming follow-up session were coded as either "relapse" or "abstinence", based on the results of smoking behavior self-reports cross-validated with co-oximetry hemoglobin levels. Multinomial regression models were conducted to test whether temperament and impulsivity measures predicted dropout and relapse relative to abstinence outcomes.ResultsHigher scores on temperament dimensions of novelty seeking and reward dependence predicted poorer retention across endpoints, whereas only higher scores on persistence predicted greater relapse. Higher scores on the trait dimension of non-planning impulsivity but not performance on cognitive impulsivity predicted poorer retention. Higher non-planning impulsivity and poorer performance in the Iowa Gambling Task predicted greater relapse at 3 and 6 months and 6 months respectively.ConclusionTemperament measures, and specifically novelty seeking and reward dependence, predict smoking cessation treatment retention, whereas persistence, non-planning impulsivity and poor decision-making predict smoking relapse.
| S-EPMC4256301 | biostudies-literature
Project description:Smoking cessation interventions are effective, but they are not easily accessible for all treatment-seeking smokers. Mobile health (mHealth) apps have been used in recent years to overcome some of these limitations. Smoking cessation apps can be used in combination with a face-to-face intervention (FFSC-Apps), or alone as general apps (GSC-Apps). The aims of this review were (1) to examine the effects of FFSC-Apps and GSC-Apps on abstinence, tobacco use, and relapse rates; and (2) to describe their features. A systematic review was conducted following the internationally Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) statement. Of the total 6016 studies screened, 24 were included, of which nine used GSC-Apps and 15 FFSC-Apps. Eight studies reported significant differences between conditions in smoking cessation outcomes, with three of them being in favor of the use of apps, and two between different point-assessments. Concerning Apps features, most GSC-Apps included self-tracking and setting a quit plan, whereas most of the FFSC-Apps included self-tracking and carbon monoxide (CO) measures. Smartphone apps for smoking cessation could be promising tools. However, more research with an adequate methodological quality is needed to determine its effect. Nevertheless, smartphone apps' high availability and attractiveness represent a great opportunity to reach large populations.
| S-EPMC8583115 | biostudies-literature
Project description:Predictors for success in smoking cessation have been studied, but a prediction model capable of providing a success rate for each patient attempting to quit smoking is still lacking. The aim of this study is to develop prediction models using machine learning algorithms to predict the outcome of smoking cessation. Data was acquired from patients underwent smoking cessation program at one medical center in Northern Taiwan. A total of 4875 enrollments fulfilled our inclusion criteria. Models with artificial neural network (ANN), support vector machine (SVM), random forest (RF), logistic regression (LoR), k-nearest neighbor (KNN), classification and regression tree (CART), and naïve Bayes (NB) were trained to predict the final smoking status of the patients in a six-month period. Sensitivity, specificity, accuracy, and area under receiver operating characteristic (ROC) curve (AUC or ROC value) were used to determine the performance of the models. We adopted the ANN model which reached a slightly better performance, with a sensitivity of 0.704, a specificity of 0.567, an accuracy of 0.640, and an ROC value of 0.660 (95% confidence interval (CI): 0.617-0.702) for prediction in smoking cessation outcome. A predictive model for smoking cessation was constructed. The model could aid in providing the predicted success rate for all smokers. It also had the potential to achieve personalized and precision medicine for treatment of smoking cessation.
| S-EPMC7967540 | biostudies-literature
Project description:BACKGROUND: Smoking remains the leading preventable cause of premature deaths. Several pharmacological interventions now exist to aid smokers in cessation. These include Nicotine Replacement Therapy [NRT], bupropion, and varenicline. We aimed to assess their relative efficacy in smoking cessation by conducting a systematic review and meta-analysis. METHODS: We searched 10 electronic medical databases (inception to Sept. 2006) and bibliographies of published reviews. We selected randomized controlled trials [RCTs] evaluating interventions for smoking cessation at 1 year, through chemical confirmation. Our primary endpoint was smoking cessation at 1 year. Secondary endpoints included short-term smoking cessation (approximately 3 months) and adverse events. We conducted random-effects meta-analysis and meta-regression. We compared treatment effects across interventions using head-to-head trials and when these did not exist, we calculated indirect comparisons. RESULTS: We identified 70 trials of NRT versus control at 1 year, Odds Ratio [OR] 1.71, 95% Confidence Interval [CI], 1.55-1.88, P =< 0.0001). This was consistent when examining all placebo-controlled trials (49 RCTs, OR 1.78, 95% CI, 1.60-1.99), NRT gum (OR 1.60, 95% CI, 1.37-1.86) or patch (OR 1.63, 95% CI, 1.41-1.89). NRT also reduced smoking at 3 months (OR 1.98, 95% CI, 1.77-2.21). Bupropion trials were superior to controls at 1 year (12 RCTs, OR1.56, 95% CI, 1.10-2.21, P = 0.01) and at 3 months (OR 2.13, 95% CI, 1.72-2.64). Two RCTs evaluated the superiority of bupropion versus NRT at 1 year (OR 1.14, 95% CI, 0.20-6.42). Varenicline was superior to placebo at 1 year (4 RCTs, OR 2.96, 95% CI, 2.12-4.12, P =< 0.0001) and also at approximately 3 months (OR 3.75, 95% CI, 2.65-5.30). Three RCTs evaluated the effectiveness of varenicline versus bupropion at 1 year (OR 1.58, 95% CI, 1.22-2.05) and at approximately 3 months (OR 1.61, 95% CI, 1.16-2.21). Using indirect comparisons, varenicline was superior to NRT when compared to placebo controls (OR 1.66, 95% CI 1.17-2.36, P = 0.004) or to all controls at 1 year (OR 1.73, 95% CI 1.22-2.45, P = 0.001). This was also the case for 3-month data. Adverse events were not systematically different across studies. CONCLUSION: NRT, bupropion and varenicline all provide therapeutic effects in assisting with smoking cessation. Direct and indirect comparisons identify a hierarchy of effectiveness.
| S-EPMC1764891 | biostudies-other
Project description:IntroductionAddressing tobacco use is an important issue in general health care. In order to improve smoking cessation advice, spirometry values can be displayed to the smoker to demonstrate possible lung function impairment. The estimate of so-called lung age may show a decrease in lung function associated with smoking. It has been suggested that performing spirometry on patients who smoke but are asymptomatic can be a useful way to show the adverse effects of smoking. The aim of this systematic review was to determine if providing spirometry results in combination with smoking cessation counselling can increase smoking cessation rates compared to what is achieved through counselling alone.MethodsIn this systematic review, we included randomized controlled trials (RCTs) evaluating smoking cessation interventions for adult smokers. The systematic search was performed in PubMed, Medline, Cochrane Library, Cinahl, Embase, Amed and PsycInfo.ResultsThe literature search resulted in 946 studies, which, after reading by two independent reviewers, were reduced to seven trials that matched the inclusion criteria. Two RCTs showed significant improvement in smoking cessation when giving patients feedback on spirometry results in combination with smoking cessation counselling, compared to patients who received only smoking cessation counselling. In both studies, the spirometry results were expressed as lung age. In the other five studies no difference was found. Five further published study protocols for ongoing RCT studies in the field have been found, and therefore this systematic overview will likely need to be updated within a few years.ConclusionsFew studies have been undertaken to examine the efficacy of spirometry in increasing smoking quit rates. Studies conducted to date have shown mixed results, and there is currently limited evidence in the literature that smoking cessation counselling that includes feedback from spirometry and a demonstration of lung age promotes quit rates.
| S-EPMC6662778 | biostudies-literature
Project description:Introduction: Rates of tobacco smoking are high in people with schizophrenia with greater difficulty of quitting smoking compared to the general population, which also relate to the increased cardiovascular and cancer risks in this co-occurring disorder. Therefore, effective smoking cessation pharmacotherapies addressing tobacco co-morbidity are imperative.Areas covered: In this review, the authors performed an extensive systematic electronic literature review examining the efficacy and safety of first-line pharmacotherapies for smoking cessation, including varenicline, sustained-release bupropion, and nicotine replacement therapies (NRT) using continuous abstinence rates over 10-12-week periods in smokers with schizophrenia. Twelve trials reporting smoking cessation outcomes using interventions in schizophrenia were included and risk ratio (RR) was used.Expert opinion: Our findings support the efficacy and safety of first-line pharmacotherapies for the treatment of tobacco use disorder in smokers with schizophrenia. Further research on the long-term effectiveness and safety of these agents in community samples is warranted. Smoking cessation pharmacotherapies may warrant the consideration of the emerging use of electronic nicotine delivery systems while neuromodulation techniques also offer promise.
| S-EPMC7183430 | biostudies-literature
Project description:Tobacco use is the leading cause of preventable disease and death in the USA. However, limited data exists regarding smoking cessation mobile app quality and intervention effectiveness. Innovative and scalable interventions are needed to further alleviate the public health implications of tobacco addiction. The proliferation of the smartphone and the advent of mobile phone health interventions have made treatment more accessible than ever. The purpose of this review was to examine the relation between published scientific literature and available commercial smartphone health apps for smoking cessation to identify the percentage of scientifically supported apps that were commercially available to consumers and to determine how many of the top commercially available apps for smoking cessation were supported by the published scientific literature. Adhering to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, apps were reviewed in four phases: (1) identified apps from the scientific literature, (2) searched app stores for apps identified in the literature, (3) identified top apps available in leading app stores, and (4) determined which top apps available in stores had scientific support. Seven articles identified six apps with some level of scientific support, three (50%) were available in at least one app store. Conversely, among the top 50 apps suggested by each of the leading app stores, only two (4%) had any scientific support. While half of the scientifically vetted apps remain available to consumers, they are difficult to find among the many apps that are identified through app store searches.
| S-EPMC5526818 | biostudies-literature
Project description:Understanding the factors that influence smoking cessation among young people is crucial for planning targeted cessation approaches. The objective of this review was to comprehensively summarize evidence for predictors of different smoking cessation related behaviors among young people from currently available systematic reviews. We searched six databases and reference lists of the included articles for studies published up to October 20, 2023. All systematic reviews summarizing predictors of intention to quit smoking, quit attempts, or smoking abstinence among people aged 10-35 years were included. We excluded reviews on effectiveness of smoking cessation intervention; smoking prevention and other smoking behaviors; cessation of other tobacco products use, dual use, and polysubstance use. We categorized the identified predictors into 5 different categories for 3 overlapping age groups. JBI critical appraisal tool and GRADE-CERqual approach were used for quality and certainty assessment respectively. A total of 11 systematic reviews were included in this study; all summarized predictors of smoking abstinence/quit attempts and two also identified predictors of intention to quit smoking. Seven reviews had satisfactory critical appraisal score and there was minimal overlapping between the reviews. We found 4 'possible' predictors of intention to quit smoking and 119 predictors of smoking abstinence/quit attempts. Most of these 119 predictors were applicable for ~10-29 years age group. We had moderate confidence on the 'probable', 'possible', 'insufficient evidence', and 'inconsistent direction' predictors and low confidence on the 'probably unrelated' factors. The 'probable' predictors include a wide variety of socio-demographic factors, nicotine dependence, mental health, attitudes, behavioral and psychological factors, peer and family related factors, and jurisdictional policies. These predictors can guide improvement of existing smoking cessation interventions or planning of new targeted intervention programs. Other predictors as well as predictors of intention to quit smoking need to be further investigated among adolescents and young adults separately.
| S-EPMC10927074 | biostudies-literature
Project description:ContextRecent data suggest that the onset of cigarette smoking is now more likely during young adulthood than adolescence. Additionally, the landscape of delivering smoking-cessation interventions has changed in the past decade, with the emergence of mobile phone and web-based approaches. The objective of this study is to update a 2010 systematic review of smoking-cessation interventions for U.S. young adults (aged 18-24 years).Evidence acquisitionElectronic searches were conducted in CINAHL, the Cochrane Library, Embase, PsycINFO, PubMed, Scopus, and Sociological Abstracts to identify eligible interventions from August 31, 2009 through July 17, 2019. Two independent coders critically evaluated the methodology and findings of all retrieved articles. Data analysis was conducted in 2019.Evidence synthesisA total of 17 RCTs and 1 nonrandomized study were added to the original 14 studies meeting the inclusion criteria for this review; these studies varied with respect to sample size, intervention, assessed outcomes, and smoking measures. Of the new studies, 3 increased cessation in the short term, 2 at 6 months, and 1 had short-term effects on cigarette reduction. Pooled analyses supported the use of interventions employing social cognitive theory, quitline counseling, and text message programs for short-term cessation in young adults.ConclusionsOf 32 included studies, 9 demonstrated efficacy of smoking cessation or reduction in U.S. young adults. There were no eligible pharmacologic interventions included in this review. Findings support the promise of 3 approaches for young adult cessation not included in the prior review: text message interventions, sustained quit-and-win contests, and multiple behavior interventions.
| S-EPMC7453837 | biostudies-literature