Dataset Information

Bayesian methods for nonignorable dropout in joint models in smoking cessation studies.

ABSTRACT: Inference on data with missingness can be challenging, particularly if the knowledge that a measurement was unobserved provides information about its distribution. Our work is motivated by the Commit to Quit II study, a smoking cessation trial that measured smoking status and weight change as weekly outcomes. It is expected that dropout in this study was informative and that patients with missed measurements are more likely to be smoking, even after conditioning on their observed smoking and weight history. We jointly model the categorical smoking status and continuous weight change outcomes by assuming normal latent variables for cessation and by extending the usual pattern mixture model to the bivariate case. The model includes a novel approach to sharing information across patterns through a Bayesian shrinkage framework to improve estimation stability for sparsely observed patterns. To accommodate the presumed informativeness of the missing data in a parsimonious manner, we model the unidentified components of the model under a non-future dependence assumption and specify departures from missing at random through sensitivity parameters, whose distributions are elicited from a subject-matter expert.

SUBMITTER: Gaskins JT

PROVIDER: S-EPMC5663304 | biostudies-literature | 2016

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Bayesian methods for nonignorable dropout in joint models in smoking cessation studies.

Gaskins J T JT Daniels M J MJ Marcus B H BH

Journal of the American Statistical Association 20160101 516

Inference on data with missingness can be challenging, particularly if the knowledge that a measurement was unobserved provides information about its distribution. Our work is motivated by the Commit to Quit II study, a smoking cessation trial that measured smoking status and weight change as weekly outcomes. It is expected that dropout in this study was informative and that patients with missed measurements are more likely to be smoking, even after conditioning on their observed smoking and wei ...[more]

PMID: 29104333

Similar Datasets

Project description:IntroductionWe compared smoking cessation outcomes between those who used a pharmacist-led community-based smoking cessation intervention and those who did not, prior to total joint replacement (TJR) surgery. Also, we examined intervention characteristics (e.g. number/duration of sessions attended, recommended therapy) and smoking cessation outcomes.MethodsThis prospective evaluation was nested within a comparative study from a centralized clinic that prepares over 3000 patients annually for TJR and focused on participants referred to the community-based smoking cessation program preoperatively. Pharmacists offered an individualized evidence-based intervention and collected visit, duration and intervention data. Smoking cessation, the primary outcome, was ascertained independently of participating pharmacists at 6 weeks post-operative using exhaled CO monitoring and at 6 months post-recruitment via telephone interview.ResultsOf 286 eligible candidates, 104 agreed to participate, with one subsequently withdrawing (n=103). At 6 weeks post-operatively, 66/103 (64%) participants returned for study re-assessment while 63/103 (61%) participants completed the post-recruitment interview at 6 months; non-respondents to study follow-up were considered smokers. Of 103 participants, 58 (56%) consulted with a pharmacist; those who did not consult a pharmacist (n=45) were slightly younger (p=0.02) with significantly higher CO level (p=0.02) on study entry. Validated 7-day point prevalence abstinence (PPA) at 6 weeks post-operative was 11/58 (19%) in pharmacist-compliant participants compared to 2/45 (4%) in non-compliant participants (p=0.04). At 6 months post-recruitment, 19/58 (33%) pharmacistcompliant participants self-reported a 7-day PPA compared to 2/45 (4%) by non-compliant participants (p<0.001). For pharmacist-compliant participants, 33/58 (54%) saw the pharmacist 4 times; the mean overall pharmacist time was 71.8±24.4 minutes/patient with 26/58 (45%) and 19/58 (33%) prescribed nicotine replacement therapy and varenicline, respectively, and 13/58 (22%) not using medication; post hoc analysis suggested varenicline was marginally more effective for smoking cessation than no medication (p=0.04).ConclusionsCommunity-based pharmacist-led smoking cessation programs are an effective addition to usual preoperative care for smokers awaiting elective TJR. Using existing community resources led to higher smoking cessation rates in smokers waiting for TJR relative to those not using these resources.

Project description:Although text-messaging interventions are effective for smoking cessation, few target teens in the USA and little is known about their effectiveness. The purpose of this manuscript is to examine correlates of dropout, response to smoking status prompts, and abstinence rates among subscribers of SmokeFreeTeen, a free, publicly available text-messaging smoking cessation intervention sponsored by the National Cancer Institute's SmokeFree.Gov initiative, on quit day through 1 month follow-up. In a sample of teens (N = 2,685), aged 13-19, we examined demographics, smoking frequency, cigarettes smoked per day, prequit intervention time (i.e., maximum of 14 days of prequit day preparation), and number of quit attempts as correlates of response and abstinence rates among program initiators (i.e., participants who reached quit day but dropped out on or before intervention end) and completers (i.e., participants who reached quit day and completed the intervention). We also conducted Cox regression analysis of time from quit day to dropout by daily and nondaily smoking status. Two-thirds (n = 1,733, 64.54%) dropped out before the intervention ended, with dropout rates peaking on quit day (n = 289, 13.10%). Response rate to smoking status prompts remained below 30% throughout the intervention. At intervention end and 1 month follow-up, abstinence was 2.63% and 2.55% among program initiators, whereas abstinence was 6.09% and 6.01% among program completers. Dropout, response, and abstinence rates did not consistently differ by subscriber characteristics. Prequit time was associated with decreased likelihood of dropping out (adjusted hazards ratio: 0.94, confidence interval [CI]: 0.93-0.95), responding to smoking status prompts (adjusted odds ratio [aOR]: 0.94, CI: 0.92-0.96), and being abstinent (aOR: 0.96, CI: 0.93-0.99) on quit day. Two or more quit attempts were associated with increased response (aOR: 1.61, CI: 1.16-2.23) and abstinence (aOR: 1.91, CI: 1.25-2.92) rates on Day 7. In a first assessment of SmokeFreeTeen outcomes, we document high dropouts and low response and abstinence rates. SmokeFreeTeen produced abstinence rates lower than comparable text-messaging interventions targeting teens and young adults. Improving SmokeFreeTeen's reach, engagement, and effectiveness is needed.

Project description:BackgroundResearch on risk factors for neuropsychiatric adverse events (NAEs) in smoking cessation with pharmacotherapy is scarce. We aimed to identify predictors and develop a prediction model for risk of NAEs in smoking cessation with medications using Bayesian regularization.MethodsBayesian regularization was implemented by applying two shrinkage priors, Horseshoe and Laplace, to generalized linear mixed models on data from 1203 patients treated with nicotine patch, varenicline or placebo. Two predictor models were considered to separate summary scores and item scores in the psychosocial instruments. The summary score model had 19 predictors or 26 dummy variables and the item score model 51 predictors or 58 dummy variables. A total of 18 models were investigated.ResultsAn item score model with Horseshoe prior and 7 degrees of freedom was selected as the final model upon model comparison and assessment. At baseline, smokers reporting more abnormal dreams or nightmares had 16% greater odds of experiencing NAEs during treatment (regularized odds ratio (rOR) = 1.16, 95% credible interval (CrI) = 0.95 - 1.56, posterior probability P(rOR > 1) = 0.90) while those with more severe sleep problems had 9% greater odds (rOR = 1.09, 95% CrI = 0.95 - 1.37, P(rOR > 1) = 0.85). The prouder a person felt one week before baseline resulted in 13% smaller odds of having NAEs (rOR = 0.87, 95% CrI = 0.71 - 1.02, P(rOR < 1) = 0.94). Odds of NAEs were comparable across treatment groups. The final model did not perform well in the test set.ConclusionsWorse sleep-related symptoms reported at baseline resulted in 85%-90% probability of being more likely to experience NAEs during smoking cessation with pharmacotherapy. Treatment for sleep disturbance should be incorporated in smoking cessation program for smokers with sleep disturbance at baseline. Bayesian regularization with Horseshoe prior permits including more predictors in a regression model when there is a low number of events per variable.

Dataset Information

Bayesian methods for nonignorable dropout in joint models in smoking cessation studies.

Publications

Bayesian methods for nonignorable dropout in joint models in smoking cessation studies.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets