The potential for increased power from combining P-values testing the same hypothesis

Variable Duration Trial as an Alternative Design for Continuous Endpoints

Clinical trials with continuous primary endpoints typically measure outcomes at baseline, at a fixed timepoint (denoted Tmin), and at intermediate timepoints. The analysis is commonly performed using the mixed model repeated measures method. It is sometimes expected that the effect size will be larger with follow-up longer than Tmin. But extending the follow-up for all patients delays trial completion. We propose an alternative trial design and analysis method that potentially increases statistical power without extending the trial duration or increasing the sample size. We propose following the last enrolled patient until Tmin, with earlier enrollees having variable follow-up durations up to a maximum of Tmax. The sample size at Tmax will be smaller than at Tmin, and due to staggered enrollment, data missing at Tmax will be missing completely at random. For analysis, we propose an alpha-adjusted procedure based on the smaller of the p values at Tmin and Tmax, termedminP $$ minP $$ . This approach can provide the highest power when the powers at Tmin and Tmax are similar. If the power at Tmin and Tmax differ significantly, the power ofminP $$ minP $$ is modestly reduced compared with the larger of the two powers. Rare disease trials, due to the limited size of the patient population, may benefit the most with this design.

Surgically treated pelvic liposarcoma and leiomyosarcoma: The effect of tumor size on cancer-specific survival

INTRODUCTION

In soft tissue pelvic liposarcoma and leiomyosarcoma, it is unknown whether a specific tumor size cut-off may help to better predict prognosis, defined as cancer-specific survival (CSS). We tested whether different tumor size cut-offs, could improve CSS prediction.

MATERIALS AND METHODS

Surgically treated non-metastatic soft tissue pelvic sarcoma patients were identified (Surveillance, Epidemiology, and End Results 2004-2019). Kaplan-Meier plots, univariable and multivariable Cox-regression models and receiver operating characteristic-derived area under the curve (AUC) estimates were used.

RESULTS

Overall, 672 (65 %) liposarcoma (median tumor size 11 cm, interquartile range [IQR] 7-16) and 367 (35 %) leiomyosarcoma (median tumor size 8 cm, IQR 5-12) patients were identified. The p-value derived ideal tumor size cut-off was 17.1 cm, in liposarcoma and 7.0 cm, in leiomyosarcoma. In liposarcoma, according to p-value derived cut-off, five-year CSS rates were 92 vs 83 % (≤17.1 vs > 17.1 cm). This cut-off represented an independent predictor of CSS and improved prognostic ability from 83.8 to 86.8 % (Δ = 3 %). Similarly, among previously established cut-offs (5 vs 10 vs 15 cm), also 15 cm represented an independent predictor of CSS and improved prognostic ability from 83.8 to 87.0 % (Δ = 3.2 %). In leiomyosarcoma, according to p-value derived cut-off, five-year CSS rates were 86 vs 55 % (≤7.0 vs > 7.0 cm). This cut-off represented an independent predictor of CSS and improved prognostic ability from 68.6 to 76.5 % (Δ = 7.9 %).

CONCLUSIONS

In liposarcoma, the p-value derived tumor size cut-off was 17.1 cm vs 7.0 cm, in leiomyosarcoma. In both histologic subtypes, these cut-offs exhibited the optimal statistical characteristics (univariable, multivariable and AUC analyses). In liposarcoma, the 15 cm cut-off represented a valuable alternative.

Study design challenges and strategies in clinical trials for rare diseases: Lessons learned from pantothenate kinase-associated neurodegeneration

Substantial challenges in study design and methodology exist during clinical trial development to examine treatment response in patients with a rare disease, especially those with predominant central nervous system involvement and heterogeneity in clinical manifestations and natural history. Here we discuss crucial decisions which may significantly impact success of the study, including patient selection and recruitment, identification and selection of endpoints, determination of the study duration, consideration of control groups including natural history controls, and selection of appropriate statistical analyses. We review strategies for the successful development of a clinical trial to evaluate treatment of a rare disease with a focus on inborn errors of metabolism (IEMs) that present with movement disorders. The strategies presented using pantothenate kinase-associated neurodegeneration (PKAN) as the rare disease example can be applied to other rare diseases, particularly IEMs with movement disorders (e.g., other neurodegeneration with brain iron accumulation disorders, lysosomal storage disorders). The significant challenges associated with designing a clinical trial in rare disease can sometimes be successfully met through strategic engagement with experts in the rare disease, seeking regulatory and biostatistical guidance, and early involvement of patients and families. In addition to these strategies, we discuss the urgent need for a paradigm shift within the regulatory processes to help accelerate medical product development and bring new innovations and advances to patients with rare neurodegenerative diseases who need them earlier in disease progression and prior to clinical manifestations.

Combining p-values from various statistical methods for microbiome data

MOTIVATION

In the field of microbiome analysis, there exist various statistical methods that have been developed for identifying differentially expressed features, that account for the overdispersion and the high sparsity of microbiome data. However, due to the differences in statistical models or test formulations, it is quite often to have inconsistent significance results across statistical methods, that makes it difficult to determine the importance of microbiome taxa. Thus, it is practically important to have the integration of the result from all statistical methods to determine the importance of microbiome taxa. A standard meta-analysis is a powerful tool for integrative analysis and it provides a summary measure by combining p-values from various statistical methods. While there are many meta-analyses available, it is not easy to choose the best meta-analysis that is the most suitable for microbiome data.

RESULTS

In this study, we investigated which meta-analysis method most adequately represents the importance of microbiome taxa. We considered Fisher's method, minimum value of p method, Simes method, Stouffer's method, Kost method, and Cauchy combination test. Through simulation studies, we showed that Cauchy combination test provides the best combined value of p in the sense that it performed the best among the examined methods while controlling the type 1 error rates. Furthermore, it produced high rank similarity with the true ranks. Through the real data application of colorectal cancer microbiome data, we demonstrated that the most highly ranked microbiome taxa by Cauchy combination test have been reported to be associated with colorectal cancer.

Powerful p-value combination methods to detect incomplete association

Meta-analyses increase statistical power by combining statistics from multiple studies. Meta-analysis methods have mostly been evaluated under the condition that all the data in each study have an association with the given phenotype. However, specific experimental conditions in each study or genetic heterogeneity can result in "unassociated statistics" that are derived from the null distribution. Here, we show that power of conventional meta-analysis methods rapidly decreases as an increasing number of unassociated statistics are included, whereas the classical Fisher's method and its weighted variant (wFisher) exhibit relatively high power that is robust to addition of unassociated statistics. We also propose another robust method based on joint distribution of ordered p-values (ordmeta). Simulation analyses for t-test, RNA-seq, and microarray data demonstrated that wFisher and ordmeta, when only a small number of studies have an association, outperformed existing meta-analysis methods. We performed meta-analyses of nine microarray datasets (prostate cancer) and four association summary datasets (body mass index), where our methods exhibited high biological relevance and were able to detect genes that the-state-of-the-art methods missed. The metapro R package that implements the proposed methods is available from both CRAN and GitHub ( http://github.com/unistbig/metapro ).

Magna Graecia transcatheter aortic valve implantation registry: data on contrast medium osmolality and postprocedural acute kidney injury

A comprehensive description of baseline characteristics, procedural features and outcomes related to the development of acute kidney injury (AKI) after transcatheter aortic valve implantation (TAVI) is reported in our research paper (Impact of contrast medium osmolality on the risk of acute kidney injury after transcatheter aortic valve implantation: insights from the Magna Graecia TAVI registry. Int J Cardiol. DOI: 10.1016/j.ijcard.2020.12.049). Three Italian heart centers were involved in this multicentric observational study. Between March 2011 and February 2019, a total of 888 patients underwent TAVI; according to the inclusion and exclusion criteria, 697 patients were included in the post-hoc analysis. This Data in Brief paper aims to report demographic, clinical, laboratory, echocardiographic, intraprocedural, periprocedural, postprocedural and follow-up data; all of them were prospectively collected from each patient's health record, whereas the analysis was performed retrospectively. Targets of this data analysis were: 1) to evaluate the impact of contrast medium (CM) osmolality on TAVI-related AKI; 2) to identify the most of risk factors involved in the development of such complication, and consequently in the occurrence of 1-year mortality; 3) to estimate the impact of CM osmolality on AKI in specific patient subgroups.

Robust inference for responder analysis: Innovative clinical trial design using a minimum p-value approach

Responder analysis is in common use in clinical trials, and has been described and endorsed in regulatory guidance documents, especially in trials where "soft" clinical endpoints such as rating scales are used. The procedure is useful, because responder rates can be understood more intuitively than a difference in means of rating scales. However, two major issues arise: 1) such dichotomized outcomes are inefficient in terms of using the information available and can seriously reduce the power of the study; and 2) the results of clinical trials depend considerably on the response cutoff chosen, yet in many disease areas there is no consensus as to what is the most appropriate cutoff. This article addresses these two issues, offering a novel approach for responder analysis that could both improve the power of responder analysis and explore different responder cutoffs if an agreed-upon common cutoff is not present. Specifically, we propose a statistically rigorous clinical trial design that pre-specifies multiple tests of responder rates between treatment groups based on a range of pre-specified responder cutoffs, and uses the minimum of the p-values for formal inference. The critical value for hypothesis testing comes from permutation distributions. Simulation studies are carried out to examine the finite sample performance of the proposed method. We demonstrate that the new method substantially improves the power of responder analysis, and in certain cases, yields power that is approaching the analysis using the original continuous (or ordinal) measure.

Bioconductor's EnrichmentBrowser: seamless navigation through combined results of set- & network-based enrichment analysis

BACKGROUND

Enrichment analysis of gene expression data is essential to find functional groups of genes whose interplay can explain experimental observations. Numerous methods have been published that either ignore (set-based) or incorporate (network-based) known interactions between genes. However, the often subtle benefits and disadvantages of the individual methods are confusing for most biological end users and there is currently no convenient way to combine methods for an enhanced result interpretation.

RESULTS

We present the EnrichmentBrowser package as an easily applicable software that enables (1) the application of the most frequently used set-based and network-based enrichment methods, (2) their straightforward combination, and (3) a detailed and interactive visualization and exploration of the results. The package is available from the Bioconductor repository and implements additional support for standardized expression data preprocessing, differential expression analysis, and definition of suitable input gene sets and networks.

CONCLUSION

The EnrichmentBrowser package implements essential functionality for the enrichment analysis of gene expression data. It combines the advantages of set-based and network-based enrichment analysis in order to derive high-confidence gene sets and biological pathways that are differentially regulated in the expression data under investigation. Besides, the package facilitates the visualization and exploration of such sets and pathways.