Biometrical Journal最新文献

The receiver operating characteristic (ROC) curve stands as a cornerstone in assessing the efficacy of biomarkers for disease diagnosis. Beyond merely evaluating performance, it provides with an optimal cutoff for biomarker values, crucial for disease categorization. While diverse methodologies exist for cutoff estimation, less attention has been paid to integrating covariate impact into this process. Covariates can strongly impact diagnostic summaries, leading to variations across different covariate levels. Therefore, a tailored covariate-based framework is imperative for outlining covariate-specific optimal cutoffs. Moreover, recent investigations into cutoff estimators have overlooked the influence of ROC curve estimation methodologies. This study endeavors to bridge this gap by addressing the research void. Extensive simulation studies are conducted to scrutinize the performance of ROC curve estimation models in estimating different cutoffs in varying scenarios, encompassing diverse data-generating mechanisms and covariate effects. In addition, leveraging the Alzheimer's Disease Neuroimaging Initiative (ADNI) data set, the research assesses the performance of different biomarkers in diagnosing Alzheimer's disease and determines the suitable optimal cutoffs.

Restricted mean survival time (RMST) is gaining attention as a measure to quantify the treatment effect on survival outcomes in randomized clinical trials. Several methods to determine sample size based on the RMST-based tests have been proposed. However, to the best of our knowledge, there is no discussion about the power and sample size regarding the augmented version of RMST-based tests, which utilize baseline covariates for a gain in estimation efficiency and in power for testing no treatment effect. The conventional event-driven study design based on the logrank test allows us to calculate the power for a given hazard ratio without specifying the survival functions. In contrast, the existing sample size determination methods for the RMST-based tests relies on the adequacy of the assumptions of the entire survival curves of two groups. Furthermore, to handle the augmented test, the correlation between the baseline covariates and the martingale residuals must be handled. To address these issues, we propose an approximated sample size formula for the augmented version of the RMST-based test, which does not require specifying the entire survival curve in the treatment group, and also a sample size recalculation approach to update the correlations between the baseline covariates and the martingale residuals with the blinded data. The proposed procedure will enable the studies to have the target power for a given RMST difference even when correct survival functions cannot be specified at the design stage.

This special collection on Multiple Comparisons arose from the 12th International Conference on Multiple Comparison Procedures (MCP 2022) that took place from August 30 to September 2, 2022, at the University of Bremen, Germany. The conference was hosted locally by Professors Werner Brannath and Thorsten Dickhaus. MCP 2022 continued the tradition of this conference series. The contributions to the conference covered the latest methodological and applied developments in the areas of simultaneous and selective inference, including testing, confidence intervals, estimation, adaptive designs, statistical modelling, and machine learning approaches, under a variety of error rates to be controlled.

This article collection contains theoretical papers on multiple comparisons by Budig et al. (2024), Chen et al. (2024), Pöhlmann et al. (2024), and by Ochieng et al. (2024). Several sessions of MCP 2022 included contributions dealing with online control of the family-wise error rate or the false discovery rate, respectively. The papers by Fischer et al. (2024) and by Fisher (2024) in this special collection reflect this current research direction. Bounding the number or the proportion, respectively, of false discoveries is considered in the papers by Xu et al. (2024) and by Zheng et al. (2024). Statistical methods for planning and evaluating studies with adaptive or group-sequential designs are developed in the papers by Danzer et al. (2024) and by Zhao et al. (2025), and platform trials are studied by Greenstreet et al. (2025).

After the long time without face-to-face meetings because of the COVID-19 pandemic, the conference delegates (Figure 1) enjoyed the social program of MCP 2022, which included an evening reception in Bremen's historic Town Hall as well as a boat trip to Bremerhaven.

Surrogate endpoints are used when the primary outcome is difficult to measure accurately. Determining if a measure is suitable to use as a surrogate endpoint is a challenging task and a variety of meta-analysis models have been proposed for this purpose. The Daniels and Hughes bivariate model for trial-level surrogate endpoint evaluation is gaining traction but presents difficulties for frequentist estimation and hitherto only Bayesian solutions have been available. This is because the marginal model is not a conventional linear model and the number of unknown parameters increases at the same rate as the number of studies. This second property raises immediate concerns that the maximum likelihood estimator of the model's unknown variance component may be downwardly biased. We derive maximum likelihood estimating equations to motivate a bias adjusted estimator of this parameter. The bias correction terms in our proposed estimating equation are easily computed and have an intuitively appealing algebraic form. A simulation study is performed to illustrate how this estimator overcomes the difficulties associated with maximum likelihood estimation. We illustrate our methods using two contrasting examples from oncology.

Mass spectrometry imaging techniques measure molecular abundance in a tissue sample at a cellular resolution, all while preserving the spatial structure of the tissue. This kind of technology offers a detailed understanding of the role of several molecular factors in biological systems. For this reason, the development of fast and efficient computational methods that can extract relevant signals from massive experiments has become necessary. A key goal in mass spectrometry data analysis is the identification of molecules with similar functions in the analyzed biological system. This result can be achieved by studying the spatial distribution of the molecules' abundance patterns. To do so, one can perform coclustering, that is, dividing the molecules into groups according to their expression patterns over the tissue and segmenting the tissue according to the molecules' abundance levels. We present TRIFASE, a semi-nonnegative matrix trifactorization technique that performs coclustering while accounting for the spatial correlation of the data. We propose an estimation algorithm that solves the proposed matrix trifactorization problem. Moreover, to improve scalability, we also propose two heuristic approximations of the most expensive steps, which help the algorithm converge while significantly streamlining the computational cost. We validated our method on a series of simulation experiments, comparing the different estimating strategies discussed in the article. Last, we analyzed a mouse brain tissue sample processed with MALDI-MSI technology, showing how TRIFASE extracts specific expression patterns of molecule abundance in localized tissue areas and discovers blocks of proteins whose activation is directly linked to specific biological mechanisms.

In recent years, power analysis has become widely used in applied sciences, with the increasing importance of the replicability issue. When distribution-free methods, such as partial least squares (PLS)-based approaches, are considered, formulating power analysis is challenging. In this study, we introduce the methodological framework of a new procedure for performing power analysis when PLS-based methods are used. Data are simulated by the Monte Carlo method, assuming the null hypothesis of no effect is false and exploiting the latent structure estimated by PLS in the pilot data. In this way, the complex correlation data structure is explicitly considered in power analysis and sample size estimation. The paper offers insights into selecting test statistics for the power analysis procedure, comparing accuracy-based tests and those based on continuous parameters estimated by PLS. Simulated and real data sets are investigated to show how the method works in practice.

N-of-1 trials are currently receiving broader attention in healthcare research when assessing the effectiveness of interventions. In contrast to the most commonly applied two-arm randomized controlled trial (RCT), in an N-of-1 design, the individual acts as their own control condition in the sense of a multiple crossover trial. N-of-1 trials can lead to a higher quality of patient by examining the effectiveness of an intervention at an individual level. Moreover, when a series of N-of-1 trials are properly aggregated, it becomes possible to detect an intervention effect at a population level. This work investigates whether a meta-analysis of summary data of a series of N-of-1 trials allows us to detect a statistically significant intervention effect with fewer participants than in a traditional, prospectively powered two-arm RCT and crossover design when evaluating a digital health intervention in cardiovascular care. After introducing these different analysis approaches, we compared the empirical properties in a simulation study both under the null hypothesis and with respect to power with different between-subject heterogeneity settings and in the presence of a carry-over effect. We further investigate the performance of a sequential aggregation procedure. In terms of simulated power, the threshold of 80% was achieved earlier for the aggregating procedure, requiring fewer participants.

Supervised learning in presence of multiple sets of noisy labels is a challenging task that is receiving increasing interest in the ever-evolving landscape of healthcare analytics. Such an issue arises when multiple annotators are tasked to manually label the same training samples, potentially giving rise to discrepancies in class assignments among the supplied labels with respect to the ground truth. Commonly, the labeling process is entrusted to a small group of domain experts, and different level of experience and subjectivity may result in noisy training labels. To solve the classification task leveraging on the availability of multiple data annotators, we introduce a novel ensemble methodology constructed combining model-based classifiers separately trained on single sets of noisy labels. Eigenvalue Decomposition Discriminant Analysis is employed for the definition of the base learners, and six distinct averaging strategies are proposed to combine them. Two solutions necessitate a priori information, such as the partial knowledge of the ground truth labels or the annotators' level of expertise. Differently, the remaining four approaches are entirely data-driven. A simulation study and an application on real data showcase the improved predictive performance of our proposal, while also demonstrating the ability of automatically inferring annotators' expertise level as a by-product of the learning process.