Probability of success and group sequential designs.

In this article, I extend the use of probability of success calculations, previously developed for fixed sample size studies to group sequential designs (GSDs) both for studies planned to be analyzed by standard frequentist techniques or Bayesian approaches. The structure of GSDs lends itself to sequential learning which in turn allows us to consider how knowledge about the result of an interim analysis can influence our assessment of the study's probability of success. In this article, I build on work by Temple and Robertson who introduced the idea of conditional probability of success, an idea which I also treated in a recent monograph.

On implementing Jeffreys' substitution likelihood for Bayesian inference concerning the medians of unknown distributions.

When statisticians are uncertain as to which parametric statistical model to use to analyse experimental data, they will often resort to a non-parametric approach. The purpose of this paper is to provide insight into a simple approach to take when it is unclear as to the appropriate parametric model and plan to conduct a Bayesian analysis. I introduce an approximate, or substitution likelihood, first proposed by Harold Jeffreys in 1939 and show how to implement the approach combined with both a non-informative and an informative prior to provide a random sample from the posterior distribution of the median of the unknown distribution. The first example I use to demonstrate the approach is a within-patient bioequivalence design and then show how to extend the approach to a parallel group design.

The epidemiology of paediatric burn injuries in Johannesburg, South Africa.

BACKGROUND: Children remain the most common victim of burns in Sub-Saharan Africa. This study describes the epidemiology of paediatric burn injury among patients admitted to Chris Hani Baragwanath Academic Hospital. METHODS: Hospital based cross-sectional, prospective study. RESULTS: 509 patients were admitted to the unit over a 12-month period, with 482 patients included for baseline analysis. 50% of admitted patients were between 15 and 47 months with a median age of 25 months. 58% of participants were male. The predominant mechanism of injury was scalding (84%), in the winter season (32%). The most common site of burn was upper limb (75%). 63% of all admissions received first aid. Among those who received first aid, a described first aid method was provided in 74% of the cases. 226 out of 482 participants (47%) provided sociodemographic information. Access to basic amenities was high, with most admissions coming from households with access to electricity (91%). 90% of caregivers held at least a high school leaving certificate. Migrant caregivers made 19% of the caregivers, which was four times the proportion of foreign nationals counted in the national census. Most admissions (79%) were referrals from other centres as opposed to walk-ins. Severe burns were associated with thermal mechanism of injury, multiple burn sites, and receiving first aid prior to admission. CONCLUSION: Children under two years of age and children of minority groups are at greatest risk for burn injury and should therefore be targeted for injury prevention strategies and education on appropriate first aid. LEVEL OF EVIDENCE: According to the Journal of pediatric Surgery, this research corresponds to Level II evidence as a prospective study with less than 80% follow-up.

Voyaging through the paediatric surgical maze: A multi-centre analysis of inter-hospital referrals to Johannesburg, South Africa.

INTRODUCTION: Paediatric surgery is a centralised service that is provided at only three public sector hospitals in Johannesburg, South Africa. These centres receive an overwhelming number of referrals from over fifty lower-level hospitals. The aim of this study was to analyse referrals to these specialist centres in order to quantify the unmet referred burden of disease and to identify ways in which paediatric surgical access in the region can be improved. METHODS: A prospective descriptive study was conducted over a 1-year period (01/06/21-31/05/22). All inter-hospital referrals from lower-level hospitals to the three Johannesburg-based specialist centres were analysed. RESULTS: 2394 unique referrals to 3 hospitals were recorded. Five main diagnoses were responsible for 68% of all referrals: neonatal surgical conditions, burns, acute abdomen/bowel obstruction, trauma and symptomatic hernias. 59.7% of all referred patients met criteria for emergency transfer to a specialist unit. 26.7% of these patients, however, were unable to be transferred owing to a lack of bedspace at specialist centres. Transferred patients experienced significant time delays between referral and arrival. Four lower-level hospitals have been identified as possible sites for service expansion. CONCLUSION: A large unmet paediatric surgical burden of disease has been identified. Lower-level hospitals have been identified that may be suitable for the implementation of decentralisation efforts to improve access to paediatric surgery within the region. LEVEL OF EVIDENCE: V.

Globalization in Pediatric Surgical Training: The Benefit of an International Fellowship in a Low-to-Middle-Income Country Academic Hospital.

OBJECTIVE: A relative oversupply of pediatric surgeons led to increasing difficulties in surgical training in high-income countries (HIC), popularizing international fellowships in low-to-middle-income countries (LMIC). The aim of this study was to evaluate the benefit of an international fellowship in an LMIC for the training of pediatric surgery trainees from HICs. METHODS: We retrospectively reviewed and compared the prospectively maintained surgical logbooks of international pediatric surgical trainees who completed a fellowship at Chris Hani Baragwanath Academic Hospital in the last 10 years. We analyzed the number of surgeries, type of involvement, and level of supervision in the operations. Data are provided in mean differences between South Africa and the respective home country. RESULTS: Seven fellows were included. Operative experience was higher in South Africa in general (Δx̅ = 381; 95% confidence interval [CI]: 236-656; p < 0.0001) and index cases (Δx̅ = 178; 95% CI: 109-279; p < 0.0001). In South Africa, fellows performed more index cases unsupervised (Δx̅ = 71; 95% CI: 42-111; p < 0.0001), but a similar number under supervision (Δx̅ = -1; 95% CI: -25-24; p = 0.901). Fellows were exposed to more surgical procedures in each pediatric surgical subspecialty. CONCLUSION: An international fellowship in a high-volume subspecialized unit in an LMIC can be highly beneficial for HIC trainees, allowing exposure to higher caseload, opportunity to operate independently, and to receive a wider exposure to the different fields of pediatric surgery. The associated benefit for the local trainees is some reduction in their clinical responsibilities due to the additional workforce, providing them with the opportunity for protected academic and research time.

Optimising the trade-off between type I and II error rates in the Bayesian context.

For any decision-making study, there are two sorts of errors that can be made, declaring a positive result when the truth is negative, and declaring a negative result when the truth is positive. Traditionally, the primary analysis of a study is a two-sided hypothesis test, the type I error rate will be set to 5% and the study is designed to give suitably low type II error - typically 10 or 20% - to detect a given effect size. These values are standard, arbitrary and, other than the choice between 10 and 20%, do not reflect the context of the study, such as the relative costs of making type I and II errors and the prior belief the drug will be placebo-like. Several authors have challenged this paradigm, typically for the scenario where the planned analysis is frequentist. When resource is limited, there will always be a trade-off between the type I and II error rates, and this article explores optimising this trade-off for a study with a planned Bayesian statistical analysis. This work provides a scientific basis for a discussion between stakeholders as to what type I and II error rates may be appropriate and some algebraic results for normally distributed data.

Prophylactic antibiotics for penetrating abdominal trauma.

BACKGROUND: Penetrating abdominal trauma occurs when the peritoneal cavity is breached. Routine laparotomy for penetrating abdominal injuries began in the 1800s, with antibiotics first being used in World War II to combat septic complications associated with these injuries. This practice was marked with a reduction in sepsis-related mortality and morbidity. Whether prophylactic antibiotics are required in the prevention of infective complications following penetrating abdominal trauma is controversial, however, as no randomised placebo controlled trials have been published to date. There has also been debate about the timing of antibiotic prophylaxis. In 1972 Fullen noted a 7% to 11% post-surgical infection rate with pre-operative antibiotics, a 33% to 57% infection rate with intra-operative antibiotic administration and 30% to 70% infection rate with only post-operative antibiotic administration. Current guidelines state there is sufficient class I evidence to support the use of a single pre-operative broad spectrum antibiotic dose, with aerobic and anaerobic cover, and continuation (up to 24 hours) only in the event of a hollow viscus perforation found at exploratory laparotomy. OBJECTIVES: To assess the benefits and harms of prophylactic antibiotics administered for penetrating abdominal injuries for the reduction of the incidence of septic complications, such as septicaemia, intra-abdominal abscesses and wound infections. SEARCH METHODS: Searches were not restricted by date, language or publication status. We searched the following electronic databases: the Cochrane Injuries Group Specialised Register, CENTRAL (The Cochrane Library 2019, issue 7 of 12), MEDLINE (OvidSP), Embase (OvidSP), ISI Web of Science: Science Citation Index Expanded (SCI-EXPANDED), ISI Web of Science: Conference Proceedings Citation Index- Science (CPCI-S) and PubMed. Searches were last conducted on 23 July 2019. SELECTION CRITERIA: All randomised controlled trials of antibiotic prophylaxis in patients with penetrating abdominal trauma versus no antibiotics or placebo. DATA COLLECTION AND ANALYSIS: Two authors screened the literature search results independently. MAIN RESULTS: We identified no trials meeting the inclusion criteria. AUTHORS' CONCLUSIONS: There is currently no information from randomised controlled trials to support or refute the use of antibiotics for patients with penetrating abdominal trauma.

Correction to: A systematic review of necrotising fasciitis in children from its first description in 1930 to 2018.

After publication of the original article [1], we were notified that two of the author names were incorrectly displayed in the pdf version of the paper, while one other name was incorrectly tagged in the XML version.

A systematic review of necrotising fasciitis in children from its first description in 1930 to 2018.

BACKGROUND: Necrotising fasciitis is a rapidly progressing soft-tissue infection with a low incidence that carries a relevant risk of morbidity and mortality. Although necrotising fasciitis is often fatal in adults, its case fatality rate seems to be lower in children. A highly variable clinical presentation makes the diagnosis challenging, which often results in misdiagnosis and time-delay to therapy. METHODS: We conducted a protocol-based systematic review to identify specific features of necrotising fasciitis in children aged one month to 17 years. We searched 'PubMed', 'Web of Science' and 'SCOPUS' for relevant literature. Primary outcomes were incidence and case fatality rates in population-based studies, and skin symptoms on presentation. We also assessed signs of systemic illness, causative organisms, predisposing factors, and reconstructive procedures as secondary outcomes. RESULTS: We included five studies reporting incidence and case fatality rates, two case-control studies, and 298 cases from 195 reports. Incidence rates varied between 0.022 and 0.843 per 100,000 children per year with a case-fatality rate ranging from 0% to 14.3%. The most frequent skin symptoms were erythema (58.7%; 175/298) and swelling (48%; 143/298), whereas all other symptoms occurred in less than 50% of cases. The majority of cases had fever (76.7%; 188/245), but other signs of systemic illness were present in less than half of the cohort. Group-A streptococci accounted for 44.8% (132/298) followed by Gram-negative rods in 29.8% (88/295), while polymicrobial infections occurred in 17.3% (51/295). Extremities were affected in 45.6% (136/298), of which 73.5% (100/136) occurred in the lower extremities. Skin grafts were necessary in 51.6% (84/162) of the pooled cases, while flaps were seldom used (10.5%; 17/162). The vast majority of included reports originate from developed countries. CONCLUSIONS: Clinical suspicion remains the key to diagnose necrotising fasciitis. A combination of swelling, pain, erythema, and a systemic inflammatory response syndrome might indicate necrotising fasciitis. Incidence and case-fatality rates in children are much smaller than in adults, although there seems to be a relevant risk of morbidity indicated by the high percentage of skin grafts. Systematic multi-institutional research efforts are necessary to improve early diagnosis on necrotising fasciits.

The effect of evidence and theory-based health advice accompanying smartphone air quality alerts on adherence to preventative recommendations during poor air quality days: A randomised controlled trial.

Although poor air quality can have a negative impact on human health, studies have shown suboptimal levels of adherence to health advice associated with air quality alerts. The present study compared the behavioural impact of the UK Air Quality Index (DAQI) with an alternative message format, using a 2 (general population vs. at-risk individuals) X 2 (usual DAQI messages vs. behaviourally enhanced messages) factorial design. Messages were sent via a smartphone application. Eighty-two participants were randomly allocated to the experimental groups. It was found that the enhanced messages (targeting messages specificity and psychosocial predictors of behaviour change) increased intentions to make permanent behavioural changes to reduce exposure, compared to the control group (V = 0.23). This effect was mediated by a reduced perception of not having enough time to follow the health advice received (b = -0.769, BCa CI [-2.588, 0.533]). It was also found that higher worry about air pollution, perceived severity, perceived efficacy of the recommended behaviour and self-efficacy were predictive of self-reported behaviour change at four weeks. In response to a real moderate air quality alert, among those with a pre-existing lung condition, more respondents in the intervention group reported to have used their preventer inhaler compared to the control group (V = 0.49). On the other hand, the two message formats performed similarly when intentions were collected in relation to a hypothetical high air pollution scenario, with all groups showing relatively high intentions to change behaviours. This study expands the currently limited understanding of how to improve the behavioural impact of existing air quality alerts.

How to design a dose-finding study using the continual reassessment method.

INTRODUCTION: The continual reassessment method (CRM) is a model-based design for phase I trials, which aims to find the maximum tolerated dose (MTD) of a new therapy. The CRM has been shown to be more accurate in targeting the MTD than traditional rule-based approaches such as the 3 + 3 design, which is used in most phase I trials. Furthermore, the CRM has been shown to assign more trial participants at or close to the MTD than the 3 + 3 design. However, the CRM's uptake in clinical research has been incredibly slow, putting trial participants, drug development and patients at risk. Barriers to increasing the use of the CRM have been identified, most notably a lack of knowledge amongst clinicians and statisticians on how to apply new designs in practice. No recent tutorial, guidelines, or recommendations for clinicians on conducting dose-finding studies using the CRM are available. Furthermore, practical resources to support clinicians considering the CRM for their trials are scarce. METHODS: To help overcome these barriers, we present a structured framework for designing a dose-finding study using the CRM. We give recommendations for key design parameters and advise on conducting pre-trial simulation work to tailor the design to a specific trial. We provide practical tools to support clinicians and statisticians, including software recommendations, and template text and tables that can be edited and inserted into a trial protocol. We also give guidance on how to conduct and report dose-finding studies using the CRM. RESULTS: An initial set of design recommendations are provided to kick-start the design process. To complement these and the additional resources, we describe two published dose-finding trials that used the CRM. We discuss their designs, how they were conducted and analysed, and compare them to what would have happened under a 3 + 3 design. CONCLUSIONS: The framework and resources we provide are aimed at clinicians and statisticians new to the CRM design. Provision of key resources in this contemporary guidance paper will hopefully improve the uptake of the CRM in phase I dose-finding trials.

Impact of London's low emission zone on air quality and children's respiratory health: a sequential annual cross-sectional study.

BACKGROUND: Low emission zones (LEZ) are an increasingly common, but unevaluated, intervention aimed at improving urban air quality and public health. We investigated the impact of London's LEZ on air quality and children's respiratory health. METHODS: We did a sequential annual cross-sectional study of 2164 children aged 8-9 years attending primary schools between 2009-10 and 2013-14 in central London, UK, following the introduction of London's LEZ in February, 2008. We examined the association between modelled pollutant exposures of nitrogen oxides (including nitrogen dioxide [NO2]) and particulate matter with a diameter of less than 2·5 µm (PM2·5) and less than 10 µm (PM10) and lung function: postbronchodilator forced expiratory volume in 1 s (FEV1, primary outcome), forced vital capacity (FVC), and respiratory or allergic symptoms. We assigned annual exposures by each child's home and school address, as well as spatially resolved estimates for the 3 h (0600-0900 h), 24 h, and 7 days before each child's assessment, to isolate long-term from short-term effects. FINDINGS: The percentage of children living at addresses exceeding the EU limit value for annual NO2 (40 µg/m3) fell from 99% (444/450) in 2009 to 34% (150/441) in 2013. Over this period, we identified a reduction in NO2 at both roadside (median -1·35 µg/m3 per year; 95% CI -2·09 to -0·61; p=0·0004) and background locations (-0·97; -1·56 to -0·38; p=0·0013), but not for PM10. The effect on PM2·5 was equivocal. We found no association between postbronchodilator FEV1 and annual residential pollutant attributions. By contrast, FVC was inversely correlated with annual NO2 (-0·0023 L/µg per m3; -0·0044 to -0·0002; p=0·033) and PM10 (-0·0090 L/µg per m3; -0·0175 to -0·0005; p=0·038). INTERPRETATION: Within London's LEZ, a smaller lung volume in children was associated with higher annual air pollutant exposures. We found no evidence of a reduction in the proportion of children with small lungs over this period, despite small improvements in air quality in highly polluted urban areas during the implementation of London's LEZ. Interventions that deliver larger reductions in emissions might yield improvements in children's health. FUNDING: National Institute for Health Research Biomedical Research Centre at Guy's and St Thomas' National Health Service (NHS) Foundation Trust and King's College London, NHS Hackney, Lee Him donation, and Felicity Wilde Charitable Trust.

Minimizing Patient Burden Through the Use of Historical Subject-Level Data in Innovative Confirmatory Clinical Trials: Review of Methods and Opportunities.

The goal of clinical trial research is to deliver safe and efficacious new treatments to patients in need in a timely and cost-effective manner. There is precedent in using historical control data to reduce the number of concurrent control subjects required in developing medicines for rare diseases and other areas of unmet need. The purpose of this paper is to provide a review for a regulatory and industry audience of the current state of relevant statistical methods, and of the uptake of these approaches and the opportunities for broader use of historical data in confirmatory clinical trials. General principles to consider when incorporating historical control data in a new trial are presented. Bayesian and frequentist approaches are outlined including how the operating characteristics for such a trial can be obtained. Finally, examples of approved new treatments that incorporated historical controls in their confirmatory trials are presented.

Statistical issues in first-in-human studies on BIA 10-2474: Neglected comparison of protocol against practice.

By setting the regulatory-approved protocol for a suite of first-in-human studies on BIA 10-2474 against the subsequent French investigations, we highlight 6 key design and statistical issues, which reinforce recommendations by a Royal Statistical Society Working Party, which were made in the aftermath of cytokine release storm in 6 healthy volunteers in the United Kingdom in 2006. The 6 issues are dose determination, availability of pharmacokinetic results, dosing interval, stopping rules, appraisal by safety committee, and clear algorithm required if combining approvals for single and multiple ascending dose studies.

Response-adaptive clinical trials: case studies in the medical literature.

The past 15 years has seen many pharmaceutical sponsors consider and implement adaptive designs (AD) across all phases of drug development. Given their arrival at the turn of the millennium, we might think that they are a recent invention. That is not the case. The earliest idea of an AD predates Bradford Hill's MRC tuberculosis study, appearing in Biometrika in 1933. In this paper, we trace the development of response-ADs, designs in which the allocation to intervention arms depends on the responses of subjects already treated. We describe some statistical details underlying the designs, but our main focus is to describe and comment on ADs from the medical research literature. Copyright © 2016 John Wiley & Sons, Ltd.

Regenerative capacity of the enteric nervous system: is immaturity defining the point of no return?

BACKGROUND: Intestinal obstruction in newborns is associated with intestinal motility disorders after surgery. Alterations in the enteric nervous system (ENS) might cause abnormal peristalsis, which may then result in intestinal motility disorders. We aimed to quantify alterations in the myenteric plexus after a ligation and to test if these alterations were reversible. METHODS: Small intestines of chicken embryos were ligated in ovo at embryonic day (ED) 11 for either 4 d (ED 11-15) or 8 d (ED 11-19). Both treated groups and control group were sacrificed and intestinal segments examined by means of both light and electron microscopy. RESULTS: The number of proximal myenteric ganglia increased (ED 19, 30.7 ± 3.16 versus 23.1 ± 2.03; P < 0.001) in the 8-d ligature group but had values similar to the control group in the 4-d ligature group. The size distribution was skewed toward small ganglia in the 8-d ligature group (ED 19, 83.71 ± 11.60% versus 3.88 ± 4.74% in the control group; P < 0.001) but comparable with the control group in the 4-d ligature group. Subcellular alterations in the 4-d ligature group were reversible. CONCLUSIONS: The pathologic alterations in the ENS were fully reversible in the 4-d ligature group. This reversibility might be linked to the degree of immaturity of the ENS.

Simulation-based sample-sizing and power calculations in logistic regression with partial prior information.

There have been many approximations developed for sample sizing of a logistic regression model with a single normally-distributed stimulus. Despite this, it has been recognised that there is no consensus as to the best method. In pharmaceutical drug development, simulation provides a powerful tool to characterise the operating characteristics of complex adaptive designs and is an ideal method for determining the sample size for such a problem. In this paper, we address some issues associated with applying simulation to determine the sample size for a given power in the context of logistic regression. These include efficient methods for evaluating the convolution of a logistic function and a normal density and an efficient heuristic approach to searching for the appropriate sample size. We illustrate our approach with three case studies. Copyright © 2016 John Wiley & Sons, Ltd.

The predictive distribution of the residual variability in the linear-fixed effects model for clinical cross-over trials.

In the linear model for cross-over trials, with fixed subject effects and normal i.i.d. random errors, the residual variability corresponds to the intraindividual variability. While population variances are in general unknown, an estimate can be derived that follows a gamma distribution, where the scale parameter is based on the true unknown variability. This gamma distribution is often used for the sample size calculation for trial planning with the precision approach, where the aim is to achieve in the next trial a predefined precision with a given probability. But then the imprecision in the estimated residual variability or, from a Bayesian perspective, the uncertainty of the unknown variability is not taken into account. Here, we present the predictive distribution for the residual variability, and we investigate a link to the F distribution. The consequence is that in the precision approach more subjects will be necessary than with the conventional calculation. For values of the intraindividual variability that are typical of human pharmacokinetics, that is a gCV of 17-36%, we would need approximately a sixth more subjects.

Idle thoughts of a 'well-calibrated' Bayesian in clinical drug development.

The use of Bayesian approaches in the regulated world of pharmaceutical drug development has not been without its difficulties or its critics. The recent Food and Drug Administration regulatory guidance on the use of Bayesian approaches in device submissions has mandated an investigation into the operating characteristics of Bayesian approaches and has suggested how to make adjustments in order that the proposed approaches are in a sense calibrated. In this paper, I present examples of frequentist calibration of Bayesian procedures and argue that we need not necessarily aim for perfect calibration but should be allowed to use procedures, which are well-calibrated, a position supported by the guidance.