John A. Kairalla

Adaptive trial designs: a review of barriers and opportunities

Adaptive designs allow planned modifications based on data accumulating within a study. The promise of greater flexibility and efficiency stimulates increasing interest in adaptive designs from clinical, academic, and regulatory parties. When adaptive designs are used properly, efficiencies can include a smaller sample size, a more efficient treatment development process, and an increased chance of correctly answering the clinical question of interest. However, improper adaptations can lead to biased studies. A broad definition of adaptive designs allows for countless variations, which creates confusion as to the statistical validity and practical feasibility of many designs. Determining properties of a particular adaptive design requires careful consideration of the scientific context and statistical assumptions. We first review several adaptive designs that garner the most current interest. We focus on the design principles and research issues that lead to particular designs being appealing or unappealing in particular applications. We separately discuss exploratory and confirmatory stage designs in order to account for the differences in regulatory concerns. We include adaptive seamless designs, which combine stages in a unified approach. We also highlight a number of applied areas, such as comparative effectiveness research, that would benefit from the use of adaptive designs. Finally, we describe a number of current barriers and provide initial suggestions for overcoming them in order to promote wider use of appropriate adaptive designs. Given the breadth of the coverage all mathematical and most implementation details are omitted for the sake of brevity. However, the interested reader will find that we provide current references to focused reviews and original theoretical sources which lead to details of the current state of the art in theory and practice.

Adaptive clinical trials: progress and challenges.

Adaptive designs promise the flexibility to redesign clinical trials at interim stages. This flexibility would provide greater efficiency in drug development. However, despite this promise, many hesitate to implement such designs. Here we explore three possible reasons for the hesitation: (i) confusion with respect to the definition of an ‘adaptive design’ (ii) controversy surrounding the use of sample size re-estimation methods; and (iii) logistical barriers that must be overcome in order to use adaptive designs within existing trial frameworks.The large volume of recent work has created confusion with respect to the definition of an ‘adaptive design’. Unfortunately, this has resulted in reduced usage of many acceptable methods because of guilt by association with the more controversial methods. This review attempts to clarify the differences among many common types of proposed adaptive designs. Once the differences are noted, it becomes apparent that some adaptive designs are well accepted while others remain very controversial. In fact, much of the controversy and criticism surrounding adaptive designs has focused on their use for sample size re-estimation. Hence, this review also examines the different types of adaptive designs for sample size re-estimation in order to clarify the controversy surrounding the use of these methods. Specifically, separating the controversial from good practice requires clarifying differences between adaptive designs with sample size re-estimation based on a revised treatment effect and re-estimation based only on nuisance parameters (internal pilot designs). Finally, many logistical barriers must be overcome in order to use adaptive designs within existing trial frameworks.If the promise of adaptive designs is to be achieved, it will be important to bring together large groups of individuals from funding sources and regulatory agencies to address these limitations. Very few discussions of these issues have appeared in journals that are targeted to clinical audiences. In fact, current use of adaptive designs is not really hindered by the lack of statistical methods to accommodate the adaptations. Rather, there is a need for education as to which adaptive designs are acceptable and which are not acceptable. These discussions will require the involvement of many individuals outside the statistical community. In this review, we summarize the existing methods and current controversies with the intent of providing a clarification that will enable these individuals to participate in these much-needed discussions.

Public health nursing case management for women receiving temporary assistance for needy families: a randomized controlled trial using community-based participatory research.

OBJECTIVES We evaluated the effectiveness of a community-based participatory research-grounded intervention among women receiving Temporary Assistance for Needy Families (TANF) with chronic health conditions in increasing (1) health care visits, (2) Medicaid knowledge and skills, and (3) health and functional status. METHODS We used a randomized controlled trial design to assign 432 women to a public health nurse case management plus Medicaid intervention or a wait-control group. We assessed Medicaid outcomes pre- and posttraining; other outcomes were assessed at 3, 6, and 9 months. RESULTS Medicaid knowledge and skills improved (P < .001 for both). Intervention group participants were more likely to have a new mental health visit (odds ratio [OR] = 1.92; P = .007), and this likelihood increased in higher-risk subgroups (OR = 2.03 and 2.83; P = .04 and .006, respectively). Depression and functional status improved in the intervention group over time (P = .016 for both). No differences were found in routine or preventive care, or general health. CONCLUSIONS Health outcomes among women receiving TANF can be improved with public health interventions. Additional strategies are needed to further reduce health disparities in this population.

Is There a Relationship between Throbbing Pain and Arterial Pulsations

Pain can have a throbbing quality, especially when it is severe and disabling. It is widely held that this throbbing quality is a primary sensation of ones own arterial pulsations, arising directly from the activation of localized pain-sensory neurons by closely apposed blood vessels. We examined this presumption more closely by simultaneously recording the subjective report of the throbbing rhythm and the arterial pulse in human subjects of either sex with throbbing dental pain—a prevalent condition whose pulsatile quality is widely regarded a primary sensation. Contrary to the generally accepted view, which would predict a direct correspondence between the two, we found that the throbbing rate (44 bpm ± 3 SEM) was much slower than the arterial pulsation rate (73 bpm ± 2 SEM, p < 0.001), and that the two rhythms exhibited no underlying synchrony. Moreover, the beat-to-beat variation in arterial and throbbing events observed distinct fractal properties, indicating that the physiological mechanisms underlying these rhythmic events are distinct. Confirmation of the generality of this observation in other pain conditions would support an alternative hypothesis that the throbbing quality is not a primary sensation but rather an emergent property, or perception, whose “pacemaker” lies within the CNS. Future studies leading to an improved understanding of the neurobiological basis of clinically relevant pain qualities, such as throbbing, will also enhance our ability to measure and therapeutically target severe and disabling pain.

The Beck Depression Inventory II Factor Structure Among Low-Income Women

Background:The Beck Depression Inventory II (BDI-II) is considered a gold standard for identifying depression in adults. Validity of the BDI-II has been documented in diverse populations using exploratory factor analysis (EFA), although no findings have been reported exclusively among lower income women. Among EFA findings, the factor structure of the BDI-II has been inconsistent, with cognitive, affective, and somatic domains emerging differentially within factors across studies. This, in conjunction with concerns around the confounding of depressive symptoms as measured by the BDI-II and other illness states, has led researchers to examine more complex factor structures using confirmatory factor analysis (CFA). Objective:The purpose of this study was to evaluate the factor structure of the BDI-II using both EFA and CFA among low-income women. Methods:After EFA with Promax rotation, CFA testing was conducted on several structural models with two randomly split subsamples of 108 and 200 women going through a Welfare Transition Program. Results:A two-factor structure was indicated by EFA, with the cognitive and affective domains represented in Factor 1 and somatic items comprising Factor 2. CFA revealed a general factor model, with General Depression and residual Cognitive and Somatic factors, best fit to the data on the basis of several indices (root mean square error of approximation = 0.05; standardized root mean square residual = 0.05; weighted root mean square residual = 0.69; comparative fit index = .98; and Tucker-Lewis index = .99) and model difference tests of significance (four comparisons: all &khgr;2 values >24.9, all p values < .001). Discussion:Measurement using BDI-II is best represented by a complex factor structure among low-income women and is consistent with findings in other populations. Additional consideration for how a general model factor structure provides potentially new directions for depression measurement may advance science in several areas.

Enhancing Braden pressure ulcer risk assessment in acutely ill adult veterans

This study sought to determine if a parsimonious pressure ulcer (PU) predictive model could be identified specific to acute care to enhance the current PU risk assessment tool (Braden Scale) utilized within veteran facilities. Factors investigated include: diagnosis of gangrene, anemia, diabetes, malnutrition, osteomyelitis, pneumonia/pneumonitis, septicemia, candidiasis, bacterial skin infection, device/implant/graft complications, urinary tract infection, paralysis, senility, respiratory failure, acute renal failure, cerebrovascular accident, or congestive heart failure during hospitalization; patients age, race, smoking status, history of previous PU, surgery, hours in surgery; length of hospitalization, and intensive care unit days. Retrospective chart review and logistic regression analyses were used to examine Braden scores and other risk factors in 213 acutely ill veterans in North Florida with (n = 100) and without (n = 113) incident PU from January–July 2008. Findings indicate four medical factors (malnutrition, pneumonia/pneumonitis, candidiasis, and surgery) have stronger predictive value (sensitivity 83%, specificity 72%, area under receiver operating characteristic [ROC] curve 0.82) for predicting PUs in acutely ill veterans than Braden Scale total scores alone (sensitivity 65%, specificity 70%, area under ROC curve 0.70). In addition, accounting for four medical factors plus two Braden subscores (activity and friction) demonstrates better overall model performance (sensitivity 80%, specificity 76%, area under ROC curve 0.88).

Comparison of depressive symptom severity scores in low-income women.

Background:The Beck Depression Inventory, Second Edition (BDI-II), and the Patient Health Questionnaire-9 (PHQ-9) are considered reliable and valid for measuring depressive symptom severity and screening for a depressive disorder. Few studies have examined the convergent or divergent validity of these two measures, and none has been conducted among low-income women-although rates of depression in this group are extremely high. Moreover, variation in within-subject scores suggests that these measures may be less comparable in select subgroups. Objective:We sought to compare these two measures in terms of construct validity and to examine whether within-subject differences in depressive symptom severity scores could be accounted for by select characteristics in low-income women. Methods:In a sample of 308 low-income women, construct validity was assessed using a multitrait-monomethod matrix approach, between-instrument differences in continuous symptom severity scores were regressed on select characteristics using backward stepwise selection, and differences in depressive symptom classification were assessed using the Mantel-Haenszel test. Results:Convergent validity was high (rs = .80, p < .001). Among predictors that included age, race, education, number of chronic health conditions, history of depression, perceived stress, anxiety, and/or the number of generalized symptoms, none explained within-subject differences in depressive symptom scores between the BDI-II and the PHQ-9 (p > .05, R2 < .04). Similarly, there was consistency in depressive symptom classification (&khgr;2 = 172 and 172.6, p < .0001). Discussion:These findings demonstrate that the BDI-II and the PHQ-9 perform similarly among low-income women in terms of depressive symptom severity measurement and classifying levels of depressive symptoms, and do not vary across subgroups on the basis of select demographics.

Injuries and Unattended Home Exits in Persons with Dementia: A 12-Month Prospective Study

Persons with dementia are at particular risk for injuries and unattended home exits. The purposes of this study were to prospectively describe the characteristics and determine the hazard rates of unattended home exits and injuries. A total of 9 times over 12 months, data were collected from 53 caregivers of persons with dementia about persons with dementia unattended home exits or injuries. A total of 24% of persons with dementia had at least 1 unattended exit; 4 participants exited multiple times. Men and younger persons with dementia were significantly more likely to exit than women or older individuals. A total of 30% of persons with dementia sustained injuries in 29 separate incidents; all but 3 injuries were caused by falls, and 38% of injuries resulted in nursing home placement. The hazard rate of untoward events was high, at approximately 1 unattended exit and 1 fall per person-year. For all persons with dementia living in the community, health care plans should include specific interventions to prevent these untoward events.

Combining an Internal Pilot with an Interim Analysis for Single Degree of Freedom Tests.

An internal pilot with interim analysis (IPIA) design combines interim power analysis (an internal pilot) with interim data analysis (two-stage group sequential). We provide IPIA methods for single df hypotheses within the Gaussian general linear model, including one and two group t tests. The design allows early stopping for efficacy and futility while also re-estimating sample size based on an interim variance estimate. Study planning in small samples requires the exact and computable forms reported here. The formulation gives fast and accurate calculations of power, Type I error rate, and expected sample size.

Rituximab in Idiopathic Nephrotic Syndrome: Does it Make Sense?

Idiopathic nephrotic syndrome (INS) includes three different entities: minimal change disease (MCD), focal segmental glomerulosclerosis (FSGS), and mesangial proliferative glomerulonephritis. Historically, this condition has been attributed to a T-cell disorder resulting in the secretion of a circulating factor that increases glomerular permeability to plasma proteins. The therapeutic approach to control the proteinuria of INS remains the use of drugs that have been considered to suppress the production of the “circulating factor” secreted by T cells. Recently, rituximab (RTX), a chimeric monoclonal antibody directed against the CD20 cell surface receptor expressed on B cells, has emerged as potential therapeutic agent. The number of publications reporting clinical experience with RTX in the treatment of nephrotic syndrome has greatly increased in the last few years. However, there is currently no good evidence from clinical or experimental studies that support a role of RTX in the treatment of MCD and FSGS proteinuria. In summary, there is the need for a better understanding of the pathogenesis of the proteinuria in INS and the potential role of RTX in this condition.