Including long- and short-term data in blinded sample size recalculation for binary endpoints

Estimation of sample size in clinical trials requires knowledge of parameters that involve the treatment effect and variability, which are usually uncertain to medical researchers. The recent release within the European Union of a Note for Guidance from the Commission for Proprietary Medical Products (CPMP) highlights the importance of this issue. Most previous papers considered the case of continuous response variables that assume a normal distribution; some regarded the portion up to the interim stage as an 'internal pilot study' and required unblinding. In this paper, our concern is with the case of binary response variables, which is more difficult than the normal case since the mean and variance are not distinct parameters. We offer a design with a simple stratification strategy that enables us to verify and update the assumption of the response rates given initially in the protocol. The design provides a method to re-estimate the sample size based on interim data while preserving the trial's blinding. An illustrative numerical example and simulation results show slight effect on the type I error rate and the decision making characteristics on sample size adjustment.

<h3>Introduction</h3> Endoscopic balloon dilatation (EBD) is a recognised treatment for symptomatic Crohn’s strictures. Several case studies report its short term and long term efficacy. A systematic analysis of the literature is needed to define overall efficacy and inform future study design. The primary objective was to examine symptomatic response, technical response and adverse events of EBD. The impact of stricture characteristics on outcome was also explored. <h3>Method</h3> A systematic search was performed in accordance with PRISMA guidelines. The quality of individual studies was assessed using the Newcastle-Ottawa Scale. The results were expressed as a per patient analysis using the proportion of patients within a group and a per study analysis using pooled event rates across studies. The random effects model was expressed as forest plots and summative statistics. Heterogeneity across studies was assessed numerically (I²). The mean value of pooled outcomes was used to create two groups (&lt; or ≥ the pooled mean event rate [PMER]), to compare the effect of the proportion of patients within each group (e.g. stricture activity and type) on outcome. <h3>Results</h3> Twenty-five studies were included: 1089 patients and 2664 dilatations. The grade for quality ranged from 2 to 6. The proportion of patients with symptomatic and technical response was 63.9% (393/615) and 92.6% (403/435) respectively. The proportion of patients with perforation was 2.6% (18/700). The PMER for symptomatic response was 74.8% (95% CI: 69.9–79.3%; I2: 0%), technical response was 90.6% (95% CI: 87.8–92.8%; I2: 11.7%), complications was 6.4% (95% CI: 5.0–8.2; I2: 4.0%), and perforation was 3% (95% CI: 2.2–4.0%; I2: 0%). The proportion of patients with active strictures demonstrating a &lt; PMER and ≥ PMER for symptomatic response was 73% vs 60% respectively. The proportion of patients with active strictures demonstrating a ≥ PMER and &lt; PMER for perforation was 62% and 36% respectively. The proportion of patients with anastomotic strictures demonstrating a &lt; PMER and ≥ PMER for technical response was 83% and 75% respectively. <h3>Conclusion</h3> EBD for symptomatic Crohn’s strictures shows high efficacy with a low complication rate. Efficacy may be affected by active inflammation and previous surgery. Variation exists in the quality of reporting of the studies. Further well designed comparative studies capturing differential effects of stricture types are needed. <h3>Disclosure of interest</h3> None Declared.

Need for equivalence testing of efficacy of alternative antibiotics for treatment of pertussis.

Estimating sample size is an integral requirement in the planning stages of quantitative studies. However, although abundant literature is available that describes techniques for calculating sample size, many are in-depth and have varying degrees of complexity. To provide an overview of four basic parameters that underpin the determination of sample size and to explain sample-size estimation for three study designs common in nursing research. Researchers can estimate basic sample size if they have a comprehension of four parameters, such as significance level, power, effect size, and standard deviation (for continuous data) or event rate (for dichotomous data). In this paper, these parameters are applied to determine sample size for the following well-established study designs: a comparison of two independent means, the paired mean study design and a comparison of two proportions. An informed choice of parameter values to input into estimates of sample size enables the researcher to derive the minimum sample size required with sufficient power to detect a meaningful effect. An understanding of the parameters provides the foundation from which to generalise to more complex size estimates. It also enables more informed entry of required parameters into sample size software. Underpinning the concept of evidence-based practice in nursing and midwifery is the application of findings that are statistically sound. Researchers with a good understanding of parameters, such as significance level, power, effect size, standard deviation and event rate, are enabled to calculate an informed sample size estimation and to report more clearly the rationale for applying any particular parameter value in sample size determination.

INTRODUCTION: Multiple studies have suggested that Celiac disease (CD) may be associated with microscopic colitis (MC); however, most of these studies were limited by their small sample size or the main scope of interest. Hence, we aimed to analyze the previously published literature on this association to determine the extent and significance of this relationship. METHODS: A systemic review was conducted in PUBMED, Embase, PubMed Central and ScienceDirect databases from inception through May 2020. Effect estimates from the individual studies were extracted and combined using the random effect, generic inverse variance method of DerSimonian and Laird and a pooled odds ratio (OR) and event rates were calculated. Forest plots were generated, and publication bias was assessed for using conventional techniques. RESULTS: Fifteen studies with a total of 4640 patients with MC were included in this Analysis. CD was significantly associated with MC (OR 6.221, 95% CI, 3.828–10.108, P < 0.005). The pooled event rate for MC in patients with CD was 6.7% (4.4%–10.0%, P < 0.005), while the pooled event rate for celiac disease in patients with MC was 7.7% (4.6%–12.6%, P < 0.005). CD was prevalent in both types of MC; 5.4% (1.3%–20%, P < 0.005) in collagenous colitis and 9.1% (4.5%–17.3%, P < 005) in lymphocytic colitis. We found no publication bias as assessed by the funnel plots and Egger’s regression asymmetry test. CONCLUSION: Our meta-analysis confirms a statistically significant association between CD and MC, with a high prevalence of CD in both types of MC. Gastroenterologists should be wary of this association when evaluating patients with either disease, particularly in patients with a sub-optimal response to first line therapy.Figure 1.: Forrest plot, pooled OR for the association between celiac disease and microscopic colitis.

When designing a clinical trial, a number of design features including the sample size have to be decided upon. The sample size calculation usually requires some discussion of relevant effect sizes and information about nuisance parameters such as standard deviations or overall event rates, with nuisance parameters being estimated from previous studies. Using a novel endpoint or moving into a new indication, no or only very limited information might be available and the sample size calculation is therefore subject to considerable uncertainty. Internal pilot study designs that allow sample size reestimation midcourse of the ongoing study have been proposed to make trials more robust to misspecifications of nuisance parameters in the planning phase. In this article we present the design of a recently completed randomized active controlled trial in dermatology as a case study. Furthermore, we demonstrate how type I error rate control can be achieved when testing for noninferiority and explore operating characteristics such as power and sample size distributions through simulations motivated by the case study. Finally, relevant regulatory guidelines on sample size reestimation are referred to.

ABSTRACTWe consider clinical trials with a binary composite endpoint where the trial is successful when a significant result is achieved for the composite or one prespecified main component. Appropriate sample size planning is challenging in this situation, as in addition to the Type I error rate, power, and target difference the overall event rates and the correlation between the test statistics have to be defined. Reliable estimates of these quantities, however, are usually hard to obtain and therefore there is a high risk to not achieve the intended power in a fixed sample size design. In this article, we propose an internal pilot study design where the nuisance parameters are estimated in a blinded way at an interim stage and where the sample size is then revised accordingly. We investigate the characteristics of the proposed design with respect to the actual Type I error rate, power, and sample size. The application of this design is illustrated by a clinical trial example.

This manuscript consists of two topics. Firstly, we explore the utility of internal pilot study (IPS) approach for reestimating sample size at an interim stage when a reliable estimate of the nuisance shape parameter of the Weibull distribution for modeling survival data is unavailable during the planning phase of a study. Although IPS approach can help rescue the study power, it is noted that the adjusted sample size can be as much as twice the initially planned sample size, which may put substantial practical constraints to continue the study. Secondly, we discuss Bayesian predictive probability for conducting interim analyses to obtain preliminary evidence of efficacy or futility of an experimental treatment warranting early termination of a clinical trial. In the context of single-arm clinical trials with time-to-event endpoints following Weibull distribution, we present the calculation of the Bayesian predictive probability when the shape parameter of the Weibull distribution is unknown. Based on the data accumulated at the interim, we propose two approaches which rely on the posterior mode or the entire posterior distribution of the shape parameter. To account for uncertainty in the shape parameter, it is recommended to incorporate its entire posterior distribution in our calculation.

Our objectives were primarily to review the published literature on complications in neuromuscular scoliosis (NMS) surgery and secondarily, by means of a meta-analysis, to determine the overall pooled rates (PR) of various complications associated with NMS surgery. PubMed and Embase databases were searched for studies reporting the outcomes and complications of NMS surgery, published from 1997 to May 2011. We focused on NMS as defined by the Scoliosis Research Society's classification. We measured the pooled estimate of the overall complication rates (PR) using a random effects meta-analytic model. This model considers both intra- and inter-study variation in calculating PR. Systematic review and meta-analysis were performed for 68 cohort and case-control studies with a total of 15,218 NMS patients. Pulmonary complications were the most reported (PR = 22.71 %) followed by implant complications (PR = 12.51 %), infections (PR = 10.91 %), neurological complications (PR = 3.01 %) and pseudoarthrosis (PR = 1.88 %). Revision, removal and extension of implant had highest PR (7.87 %) followed by malplacement of the pedicle screws (4.81 %). Rates of individual studies have moderate to high variability. The studies were heterogeneous in methodology and outcome types, which are plausible explanations for the variability; sensitivity analysis with respect to age at surgery, sample size, publication year and diagnosis could also partly explain this variability. In regard to surgical complications affiliated with various surgical techniques in NMS, the level of evidence of published literature ranges between 2+ to 2-; the subsequent recommendations are level C. NMS patients have diverse and high complication rates after scoliosis surgery. High PRs of complications warrant more attention from the surgical community. Although the PR of all complications are affected by heterogeneity, they nevertheless provide valuable insights into the impact of methodological settings (sample size), patient characteristics (age at surgery), and continual advances in patient care on complication rates.

Motivated by a recent symptom management trial to simultaneously assess multiple binary endpoints for cancer chemotherapy, we extend the univariate McNemar test to multivariate cases for doubly blinded clinical trials with matched pairs. We propose a general method to test noninferiority or equivalence. The method employs the intersection-union principle on the marginal score statistics to obtain an asymptotic α-level test. Power formula and sample size calculation are provided by a simple numerical method that accounts for the correlation structure among the endpoints. We further consider sample size re-estimation through internal pilot study. To avoid the need of unblinding for doubly blinded trials, we also propose a blinded approach for nuisance parameter estimation. The effectiveness of the proposed methods is demonstrated by simulation studies. Application to the cancer chemotherapy trial is illustrated.

SummaryObjectiveTo perform a systematic review and meta‐analysis of real‐world evidence for the use of low‐frequency repetitive transcranial magnetic stimulation (rTMS) in the treatment of drug‐resistant epilepsy.MethodsWe systematically searched PubMed, Scopus, Medline, and clinicaltrials.gov for all relevant articles. Relevant patient and stimulation predictors as well as seizure outcomes were assessed. For studies with and without individual participant data (IPD), the primary outcomes were the rate of “favorable response” (reduction in seizure frequency ≥50%) and pooled event rate of mean reduction in seizure frequency, respectively. Outcomes were assessed with comparative statistics and random‐effects meta‐analysis models.ResultsOf 3,477 identified articles, 12 met eligibility and were included in this review. We were able to obtain IPD for 5 articles constituting 34 participants. Univariate analysis on IPD identified greater favorable response event rates between participants with temporal seizure focus versus extratemporal (50% vs. 14%, p = 0.045) and between participants who were stimulated with a figure‐8 coil versus other types (47% vs. 0%, p = 0.01). We also performed study‐level meta‐analysis on the remaining 7 studies without IPD, which included 212 participants. The pooled mean event rate of 50% seizure reduction using low‐frequency rTMS was 30% (95% confidence interval [CI] 12–57%). Sensitivity analysis revealed that studies with a mean age ≤21 years and studies using targeted stimulation had the highest seizure reduction rates compared to studies with a mean age >21 years (69% vs. 18%) and not using a targeted stimulation (47% vs. 14–20%). Moreover, we identified high interstudy heterogeneity, moderate study bias, and high publication bias.SignificanceReal‐world evidence suggests that low‐frequency rTMS using a figure‐8 coil may be an effective therapy for the treatment of drug‐resistant epilepsy in pediatric patients. This meta‐analysis can inform the design and expedite recruitment of a subsequent randomized clinical trial.

Considerations of sample size in medical research

The Need for Large Clinical Studies in Perioperative Medicine

Background: This study aims to describe COVID-19–related clinical outcomes after immunotherapies (ICIs) for cancer patients. Methods: In this meta-analysis, we searched databases to collect data that addressed outcomes after immunotherapies (ICIs) during the COVID-19 pandemic. The primary endpoint was COVID-19–related mortality. Secondary endpoints included COVID-related hospital readmission, emergency room (ER) visits, opportunistic infections, respiratory complications, need for ventilation, and thrombo-embolic events. Pooled event rates (PERs) were calculated and a meta-regression analysis was performed. Results: A total of 262 studies were identified. Twenty-two studies with a total of forty-four patients were eligible. The PER of COVID-19–related mortality was 39.73%, while PERs of COVID-19–related ER visits, COVID-19–related pulmonary complications, and COVID-19–related ventilator needs were 40.75%, 40.41%, and 34.92%, respectively. The PER of opportunistic infections was 34.92%. The PERs of the use of antivirals, antibiotics, steroids, prophylactic anticoagulants, and convalescent plasma were 62.12%, 57.12%, 51.36%, 41.90%, and 26.48%, respectively. There was a trend toward an association between previous respiratory diseases and COVID-19–related mortality. Conclusion: The rates of COVID-19–related mortality, ER visits, pulmonary complications, need for a ventilator, and opportunistic infections are still high after ICIs during the COVID-19 pandemic. There was a trend toward an association between previous respiratory diseases and COVID-19–related mortality.

AngioVac is a new device for filtering intravascular thrombi and emboli. Publications on the device are limited and underpowered to objectively estimate its safety and efficacy. We aimed to overcome this by performing a meta-analysis on the results of AngioVac for treating venous thromboses and endocardial vegetations. A systematic literature review was performed to identify all articles reporting cardiac vegetation and/or thrombosis extraction using AngioVac. Endpoints were successful removal, operative mortality, conversion to open surgery, hospital stay, recurrent thromboembolism, and follow-up mortality. Random effect model was used, and pooled event rates (PERs) and incidence rate (IR) were calculated. A total of 42 studies with 182 patients (81 vegetation and 101 thrombosis) were included. Overall mean follow-up times were 3.1 and 0.7 years in vegetation and thrombosis patients, respectively. The PERs for successful removal were 74.5 (confidence interval [CI]: 48.2-90.2), 80.5 (CI: 70.0-88.0), and 32.4 (CI: 17.0-52.8) in vegetation, right atrial/caval venous thrombi, and pulmonary emboli (PE) patients, respectively. The PERs for operative mortalities were 14.6 (CI: 7.7-25.8), 14.8 (CI: 8.5-24.5), and 32.3 (CI: 15.1-56.3), respectively. The PERs for conversion to open surgery were 25.0 (CI: 9.3-51.9) and 12.3 (CI: 5.4-25.6) in vegetation and thrombosis patients, respectively. The IR of recurrent thromboembolism was 0.18 per person per year (PPY) (CI: 0.00-14.69) in vegetation and 0.19 PPY (CI: 0.08-0.48) in thrombosis patients. IR of follow-up mortality was 0.37 PPY (CI: 0.11-1.21) in thrombosis patients. AngioVac is a viable option for extracting right-sided vegetations and right atrial/caval venous thrombi. Rates of successful extraction and mortality are significantly worse for PE.