Missing Data in Alcohol Clinical Trials with Binary Outcomes

Hallgren, Kevin A.; Witkiewitz, Katie; Kranzler, Henry R.; Falk, Daniel E.; Litten, Raye Z.; O’Malley, Stephanie S.; Anton, Raymond F.

doi:10.1111/acer.13106

Cited by 28 publications

(17 citation statements)

References 31 publications

(53 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These analyses also involved a subset of the original sample (participants with chronic pain who were retained after BUP-NLX detoxification and maintenance), so these findings may not generalize to the general population of prescription opioid-dependent adults who seek treatment. A potential concern is the accelerated rate of attrition during the taper phase which led to a steep increase in missing data, although confidence in the results is bolstered by our use of modern estimation procedures that are generally more robust to missing data than alternative approaches (39). The original clinical trial was conducted in community clinics connected to an established clinical trials research network, therefore the frequency and quality of clinical services provided in this study may differ from those typically available to this population.…”

Section: Discussionmentioning

confidence: 99%

Volatility and change in chronic pain severity predict outcomes of treatment for prescription opioid addiction

et al. 2017

View full text Add to dashboard Cite

Background and aims Buprenorphine-naloxone (BUP-NLX) can be used to manage prescription opioid addiction among persons with chronic pain, but post-treatment relapse is common and difficult to predict. This study estimated whether changes in pain over time and pain volatility during BUP-NLX maintenance would predict opioid use during the taper BUP-NLX taper. Design Secondary analysis of a multisite clinical trial for prescription opioid addiction, using data obtained during a 12-week BUP-NLX stabilization and 4-week BUP-NLX taper. Setting Community clinics affiliated with a national clinical trials network in 10 U.S. cities. Participants Subjects with chronic pain who entered the BUP-NLX taper phase (N = 125) with enrollment occurring from June, 2006 to July 2009 (52% male, 88% Caucasian, 31% married). Measurements Outcomes were weekly biologically-verified and self-reported opioid use from the 4-week taper phase. Predictors were estimates of baseline severity, rate of change, and volatility in pain from weekly self-reports during the 12-week maintenance phase. Findings Controlling for baseline pain and treatment condition, increased pain (OR = 2.38, p = .02) and greater pain volatility (OR = 2.43, p = .04) predicted greater odds of positive opioid urine screen during BUP-NLX taper. Increased pain (IRR = 1.40, p = .04) and greater pain volatility (IRR = 1.66, p = .009) also predicted greater frequency of self-reported opioid use. Conclusions Adults with chronic pain receiving outpatient treatment with buprenorphine-naloxone (BUP-NLX) for prescription opioid addiction have elevated risk for opioid use when tapering off of maintenance treatment. Those with relative persistence in pain over time and greater volatility in pain during treatment are less likely to sustain abstinence during BUP-NLX taper.

show abstract

Section: Discussionmentioning

confidence: 99%

Volatility and change in chronic pain severity predict outcomes of treatment for prescription opioid addiction

et al. 2017

View full text Add to dashboard Cite

show abstract

“…Finally, imputing for missing data may produce biased estimates, which depend upon the missingness pattern of the data and the analytic method used to impute missing data. 40–42 Though it is impossible to know the actual reasons for all missing data, sensitivity analyses can provide a test of whether the assumptions of missing completely at random, missing at random, or missing not at random conditions are likely for a given set of analyses. 42 …”

Section: Discussionmentioning

confidence: 99%

Tdap Vaccination Among Healthcare Personnel, Internet Panel Survey, 2012–2014

Srivastav

Black

et al. 2017

American Journal of Preventive Medicine

View full text Add to dashboard Cite

Introduction Healthcare personnel (HCP) are at risk for pertussis infection exposure or transmitting the disease to patients in their work settings. The Advisory Committee on Immunization Practices recommends tetanus toxoid, reduced diphtheria toxoid, and acellular pertussis (Tdap) vaccination for HCP to minimize these risks. This study assessed Tdap vaccination coverage among U.S. HCP by sociodemographic and occupation-related characteristics. Methods The 2012, 2013, and 2014 Internet Panel Surveys were analyzed in 2015 to assess HCP Tdap vaccination. Effective sample sizes for 2012, 2013, and 2014 survey years were 2,038, 1613, and 1633, respectively. Missing values were assigned using multiple imputation. Multivariable logistic regression identified factors independently associated with HCP Tdap vaccination. Statistical measures were calculated with an assumption of random sampling. Results Overall, Tdap vaccination coverage among HCP was 34.8% (95% CI=30.6%, 39.0%); 40.2% (95% CI=36.1%, 44.4%); and 42.4% (95% CI=38.7%, 46.0%) in 2012, 2013, and 2014, respectively. Nurse practitioners/physician’s assistants, physicians, nurses, and HCP working in hospitals and ambulatory care settings had higher Tdap coverage. Having contact with an infant aged ≤6 months and influenza vaccination receipt were associated with increased Tdap vaccination. Non-Hispanic black race/ethnicity, having an associate/bachelor’s degree, being below poverty, non-clinical personnel status, and working in a long-term care setting were associated with decreased Tdap vaccination. Conclusions HCP Tdap vaccination coverage increased during 2012–2014; however, coverage remains low. Vaccination coverage varied widely by healthcare occupation, occupational setting, and sociodemographic characteristics. Evidence-based employer strategies used to increase HCP influenza vaccination, if applied to Tdap, may increase Tdap coverage.

show abstract

“…To address missing data, we used multiple imputation with chained logistic regression equations in all statistical analyses (30), which reduces bias more than other approaches even when some data are not missing at random(31). Twenty imputation sets were generated using Gibbs sampling, incorporating all baseline variables (including baseline SI and SA) to improve prediction accuracy.…”

Section: Methodsmentioning

confidence: 99%

Prediction of Suicide Ideation and Attempt Among Substance-Using Patients in Primary Care

et al. 2017

Self Cite

View full text Add to dashboard Cite

Background Suicide is a major public health concern, particularly among people who use illicit substances and/or non-prescribed medications. Objective The present study prospectively assessed the incidence and predictors of suicidal ideation (SI) and suicide attempt (SA) among such substance-using patients over 12 months after receiving primary care. Design Secondary analysis of data from a randomized clinical trial of screening, brief intervention, and referral to treatment for substance use within seven public, safety-net, primary care clinics. Participants Adults (N=868) who used illicit drugs or non-prescribed medications at least once in the past 90 days prior to the baseline primary care visit and consented to participate. Main Measures At baseline, interviewers assessed demographics, psychiatric symptoms, substance use, psychosocial stressors, treatment service utilization, quality of life, past-month SI, and lifetime SA. Follow-up interviews three, six, nine, and twelve months later assessed past-month SI and any SA since the previous assessment. Key Results Participants reported a high incidence of SI (25.9%) and SA (7.1%) over the year following the baseline primary care visit. In univariate analyses, odds of SI or SA during the one-year follow-up were significantly elevated in patients who were female; lacked a high school diploma; were unemployed; reported depression, anxiety, hallucinations, concentration difficulty, or violent behavior in the past 30 days; used nicotine or stimulants on a daily basis; used the emergency department or mental health services in the past 90 days; reported current quality-of-life impairment in mobility or usual activities; or reported past 30-day SI or any lifetime SA at baseline. In multiple regression analyses, only past 30-day SI, any lifetime SA, past 90-day violent behavior, and current impairment due to anxiety or depression at baseline uniquely predicted SI or SA beyond other variables over the one-year follow-up. Conclusions Results support the need for screening for suicidality among primary care patients who use illicit substances and identify key subgroups of these patients who are at particularly elevated risk for suicidality.

show abstract

Missing Data in Alcohol Clinical Trials with Binary Outcomes

Cited by 28 publications

References 31 publications

Volatility and change in chronic pain severity predict outcomes of treatment for prescription opioid addiction

Volatility and change in chronic pain severity predict outcomes of treatment for prescription opioid addiction

Tdap Vaccination Among Healthcare Personnel, Internet Panel Survey, 2012–2014

Prediction of Suicide Ideation and Attempt Among Substance-Using Patients in Primary Care

Contact Info

Product

Resources

About