Biometrical Journal最新文献

{"title":"Unscaled Indices for Assessing Agreement of Functional Data","authors":"Kaeum Choi,&nbsp;Jeong Hoon Jang","doi":"10.1002/bimj.70039","DOIUrl":"https://doi.org/10.1002/bimj.70039","url":null,"abstract":"<div>\u0000 \u0000 <p>A decision to adopt a new medical device requires a rigorous assessment of the reliability and reproducibility of its clinical measurements. In this paper, with the goal of establishing the validity and acceptability of modern high-tech medical devices that generate functional data, we focus on the problem of assessing agreement of multiple functional data that are measured on the same subjects by different methods/technologies/raters. Specifically, we introduce a series of unscaled indices, total deviation index (TDI) and coverage probability (CP), that themselves are functions of time and can delineate the trends of intramethod, intermethod, and total (intra+inter) agreement of functional data across time in terms of the original measurement scale. We also develop scalar-valued TDI and CP indices that summarize the degree of agreement over the entire domain based on the weighted average idea. We advocate an experimental design under which each of the two methods generates replicated functional data measurements for each subject, and express each index using a mean function and variance components of a bivariate multilevel functional linear mixed effects model. Such a formulation allows us to smoothly estimate the indices based on our bivariate multilevel functional principal component analysis approach that only requires eigenanalyses of univariate covariance functions for better efficiency and scalability. Comprehensive simulation studies are conducted to examine the finite-sample properties of the estimators. The proposed method is applied to assess the reliability and reproducibility of renogram curves generated by diuresis renography, a high-tech medical imaging device widely used to detect kidney obstruction.</p></div>","PeriodicalId":55360,"journal":{"name":"Biometrical Journal","volume":"67 1","pages":""},"PeriodicalIF":1.3,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143438780","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"High-Dimensional Variable Selection With Competing Events Using Cooperative Penalized Regression","authors":"Lukas Burk,&nbsp;Andreas Bender,&nbsp;Marvin N. Wright","doi":"10.1002/bimj.70036","DOIUrl":"https://doi.org/10.1002/bimj.70036","url":null,"abstract":"<p>Variable selection is an important step in the analysis of high-dimensional data, yet there are limited options for survival outcomes in the presence of competing risks. Commonly employed penalized Cox regression considers each event type separately through cause-specific models, neglecting possibly shared information between them. We adapt the feature-weighted elastic net (fwelnet), an elastic net generalization, to survival outcomes and competing risks. For two causes, our proposed algorithm fits two alternating cause-specific models, where each model receives the coefficient vector of the complementary model as prior information. We dub this “cooperative penalized regression,” as it enables the modeling of competing risk data with cause-specific models while accounting for shared effects between causes. Coefficients that are shrunken toward zero in the model for the first cause will receive larger penalization weights in the model for the second cause and vice versa. Through multiple iterations, this process ensures stronger penalization of uninformative predictors in both models. We demonstrate our method's variable selection capabilities on simulated genomics data and apply it to bladder cancer microarray data. We evaluate selection performance using the positive predictive value for the correct selection of informative features and the false positive rate for the selection of uninformative variables. The benchmark compares results with cause-specific penalized Cox regression, random survival forests, and likelihood-boosted Cox regression. Results indicate that our approach is more effective at selecting informative features and removing uninformative features. In settings without shared effects, variable selection performance is similar to cause-specific penalized Cox regression.</p>","PeriodicalId":55360,"journal":{"name":"Biometrical Journal","volume":"67 1","pages":""},"PeriodicalIF":1.3,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/bimj.70036","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143438781","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Parametric Estimation of the Mean Number of Events in the Presence of Competing Risks","authors":"Joshua P. Entrop,&nbsp;Lasse H. Jakobsen,&nbsp;Michael J. Crowther,&nbsp;Mark Clements,&nbsp;Sandra Eloranta,&nbsp;Caroline E. Dietrich","doi":"10.1002/bimj.70038","DOIUrl":"https://doi.org/10.1002/bimj.70038","url":null,"abstract":"<p>Recurrent events, for example, hospitalizations or drug prescriptions, are common in time-to-event research. One useful summary measure of the recurrent event process is the mean number of events. Methods for estimating the mean number of events exist and are readily implemented for situations in which the recurrent event is the only possible outcome. However, estimation gets more challenging in the competing risk setting, in which methods are so far limited to nonparametric approaches. To this end, we propose a postestimation command for estimating the mean number of events in the presence of competing risks by jointly modeling the intensity function of the recurrent event and the survival function for the competing events. The proposed method is implemented in the R-package <span>JointFPM</span> which is available on CRAN. Simulations demonstrate low bias and good coverage in scenarios where the intensity of the recurrent event does not depend on the number of previous events. We illustrate our method using data on readmissions after colorectal cancer surgery included in the <span>frailtypack</span> package for R. Estimates of the mean number of events can be used to augment time-to-event analyses when both recurrent and competing events exist. The proposed parametric approach offers estimation of a smooth function across time as well as easy estimation of different contrasts which is not available using a nonparametric approach.</p>","PeriodicalId":55360,"journal":{"name":"Biometrical Journal","volume":"67 1","pages":""},"PeriodicalIF":1.3,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/bimj.70038","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143438779","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Network Meta-Analysis of Time-to-Event Endpoints With Individual Participant Data Using Restricted Mean Survival Time Regression","authors":"Kaiyuan Hua,&nbsp;Xiaofei Wang,&nbsp;Hwanhee Hong","doi":"10.1002/bimj.70037","DOIUrl":"https://doi.org/10.1002/bimj.70037","url":null,"abstract":"<div>\u0000 \u0000 <p>Network meta-analysis (NMA) extends pairwise meta-analysis to compare multiple treatments simultaneously by combining “direct” and “indirect” comparisons of treatments. The availability of individual participant data (IPD) makes it possible to evaluate treatment effect moderation and to draw inferences about treatment effects by taking the full utilization of individual covariates from multiple clinical trials. In IPD-NMA, restricted mean survival time (RMST) models have gained popularity when analyzing time-to-event outcomes because RMST models offer more straightforward interpretations of treatment effects with fewer assumptions than hazard ratios commonly estimated from Cox models. Existing approaches estimate RMST within each study and then combine by using aggregate-level NMA methods. However, these methods cannot incorporate individual covariates to evaluate the effect moderation. In this paper, we propose advanced RMST NMA models when IPD are available. Our models allow us to study treatment effect moderation and provide a comprehensive understanding about comparative effectiveness of treatments and subgroup effects. The methods are evaluated by an extensive simulation study and illustrated using a real NMA example about treatments for patients with atrial fibrillation.</p></div>","PeriodicalId":55360,"journal":{"name":"Biometrical Journal","volume":"67 1","pages":""},"PeriodicalIF":1.3,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143438782","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Bias-Corrected Bayesian Nonparametric Model for Combining Studies With Varying Quality in Meta-Analysis","authors":"Pablo Emilio Verde,&nbsp;Gary L. Rosner","doi":"10.1002/bimj.70034","DOIUrl":"https://doi.org/10.1002/bimj.70034","url":null,"abstract":"<p>Bayesian nonparametric (BNP) approaches for meta-analysis have been developed to relax distributional assumptions and handle the heterogeneity of random effects distributions. These models account for possible clustering and multimodality of the random effects distribution. However, when we combine studies of varying quality, the resulting posterior is not only a combination of the results of interest but also factors threatening the integrity of the studies' results. We refer to these factors as the studies' <i>internal validity biases</i> (e.g., reporting bias, data quality, and patient selection bias). In this paper, we introduce a new meta-analysis model called the bias-corrected Bayesian nonparametric (BC-BNP) model, which aims to automatically correct for internal validity bias in meta-analysis by only using the reported effects and their standard errors. The BC-BNP model is based on a mixture of a parametric random effects distribution, which represents the model of interest, and a BNP model for the bias component. This model relaxes the parametric assumptions of the bias distribution of the model introduced by Verde. Using simulated data sets, we evaluate the BC-BNP model and illustrate its applications with two real case studies. Our results show several potential advantages of the BC-BNP model: (1) It can detect bias when present while producing results similar to a simple normal–normal random effects model when bias is absent. (2) Relaxing the parametric assumptions of the bias component does not affect the model of interest and yields consistent results with the model of Verde. (3) In some applications, a BNP model of bias offers a better understanding of the studies' biases by clustering studies with similar biases. We implemented the BC-BNP model in the R package jarbes, facilitating its practical application.</p>","PeriodicalId":55360,"journal":{"name":"Biometrical Journal","volume":"67 1","pages":""},"PeriodicalIF":1.3,"publicationDate":"2025-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/bimj.70034","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143362461","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Mediation Analysis With Exposure–Mediator Interaction and Covariate Measurement Error Under the Additive Hazards Model","authors":"Ying Yan,&nbsp;Lingzhu Shen","doi":"10.1002/bimj.70035","DOIUrl":"https://doi.org/10.1002/bimj.70035","url":null,"abstract":"<div>\u0000 \u0000 <p>Causal mediation analysis is a useful tool to examine how an exposure variable causally affects an outcome variable through an intermediate variable. In recent years, there is increasing research interest in mediation analysis with survival data. The existing literature usually requires accurate measurements of the mediator and the confounders, which is infeasible in many biomedical and social science studies. Ignoring measurement errors may lead to misleading inference results. Furthermore, the current identification results of causal effects under the additive hazards model are limited to the scenario with no exposure–mediator interaction, which can be unappealing in mediation analysis. In this paper, we derive the identification results of direct and indirect effects under the additive hazards model in the presence of exposure–mediator interaction. Furthermore, we propose a corrected approach to adjust for the impact of measurement error in the mediator and the confounders and obtain consistent estimations of the direct and indirect effects. The performance of the proposed method is studied in simulation studies and a real data study.</p></div>","PeriodicalId":55360,"journal":{"name":"Biometrical Journal","volume":"67 1","pages":""},"PeriodicalIF":1.3,"publicationDate":"2025-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143362514","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multiple Contrast Tests in the Presence of Partial Heteroskedasticity","authors":"Mario Hasler,&nbsp;Tim Birr,&nbsp;Ludwig A. Hothorn","doi":"10.1002/bimj.70019","DOIUrl":"10.1002/bimj.70019","url":null,"abstract":"<p>This paper proposes a general approach for handling multiple contrast tests for normally distributed data in the presence of partial heteroskedasticity. In contrast to the usual case of complete heteroskedasticity, the treatments belong to subgroups according to their variances. Treatments within these subgroups are homoskedastic, whereas treatments of different subgroups are heteroskedastic. New candidate as well as already existing approaches are described and compared by <span></span><math>\u0000 <semantics>\u0000 <mi>α</mi>\u0000 <annotation>$alpha$</annotation>\u0000 </semantics></math>-simulations. Power simulations show that a gain in power is achieved when the partial heteroskedasticity is taken into account compared to procedures which wrongly assume complete heteroskedasticity. The new approaches will be applied to a phytopathological experiment.</p>","PeriodicalId":55360,"journal":{"name":"Biometrical Journal","volume":"67 1","pages":""},"PeriodicalIF":1.3,"publicationDate":"2025-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11729621/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142980377","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Quantification of Difference in Nonselectivity Between In Vitro Diagnostic Medical Devices","authors":"Pernille Kjeilen Fauskanger,&nbsp;Sverre Sandberg,&nbsp;Jesper Johansen,&nbsp;Thomas Keller,&nbsp;Jeffrey Budd,&nbsp;W. Greg Miller,&nbsp;Anne Stavelin,&nbsp;Vincent Delatour,&nbsp;Mauro Panteghini,&nbsp;Bård Støve","doi":"10.1002/bimj.70032","DOIUrl":"10.1002/bimj.70032","url":null,"abstract":"<p>Correct measurement results from in vitro diagnostic (IVD) medical devices (MD) are crucial for optimal patient care. The performance of IVD-MDs is often assessed through method comparison studies. Such studies can be compromised by the influence of various factors. The effect of these factors must be examined in every method comparison study, for example, nonselectivity differences between compared IVD-MDs are examined. Historically, selectivity or nonselectivity has been defined as a qualitative term. However, a quantification of nonselectivity differences between IVD-MDs is needed. This paper fills this need by introducing a novel measure for quantifying differences in nonselectivity (DINS) between a pair of IVD-MDs. Assuming one of the IVD-MDs involved in the comparison exhibits high selectivity for the analyte, it becomes feasible to quantify nonselectivity in the other IVD-MD by employing this DINS measure. Our approach leverages elements from univariate ordinary least squares regression and incorporates repeatability IVD-MD variances, resulting in a normalized measure. We also introduce a plug-in estimator for this measure, which is notably linked to the average relative increase in prediction interval widths attributable to DINS. This connection is exploited to establish a criterion for identifying excessive DINS utilizing a proof-of-hazard approach. Utilizing Monte Carlo simulations, we investigate how the estimator relates to population characteristics like DINS and heteroskedasticity. We find that DINS impacts the mean, variance, and 99th percentile of the estimator, while heteroskedasticity affects only the latter two, and to a considerably smaller extent compared to DINS. Importantly, the size of the study design modulates these effects. We also confirm, when using clinical data, that DINS between pairs of IVD-MDs influence the estimator correspondingly to those of simulated data. Thus, the proposed estimator serves as an effective metric for quantifying DINS between IVD-MDs and helping to determine the quality of a method comparison study.</p>","PeriodicalId":55360,"journal":{"name":"Biometrical Journal","volume":"67 1","pages":""},"PeriodicalIF":1.3,"publicationDate":"2025-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11695778/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142923893","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Sensitivity Analysis for Effects of Multiple Exposures in the Presence of Unmeasured Confounding","authors":"Boram Jeong,&nbsp;Seungjae Lee,&nbsp;Shinhee Ye,&nbsp;Donghwan Lee,&nbsp;Woojoo Lee","doi":"10.1002/bimj.70033","DOIUrl":"10.1002/bimj.70033","url":null,"abstract":"<div>\u0000 \u0000 <p>Epidemiological research aims to investigate how multiple exposures affect health outcomes of interest, but observational studies often suffer from biases caused by unmeasured confounders. In this study, we develop a novel sensitivity model to investigate the effect of correlated multiple exposures on the continuous health outcomes of interest. The proposed sensitivity analysis is model-agnostic and can be applied to any machine learning algorithm. The interval of single- or joint-exposure effects is efficiently obtained by solving a linear programming problem with a quadratic constraint. Some strategies for reducing the input burden in the sensitivity analysis are discussed. We demonstrate the usefulness of sensitivity analysis via numerical studies and real data application.</p></div>","PeriodicalId":55360,"journal":{"name":"Biometrical Journal","volume":"67 1","pages":""},"PeriodicalIF":1.3,"publicationDate":"2024-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142911258","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Developing and Comparing Four Families of Bayesian Network Autocorrelation Models for Binary Outcomes: Estimating Peer Effects Involving Adoption of Medical Technologies","authors":"Guanqing Chen,&nbsp;A. James O'Malley","doi":"10.1002/bimj.70030","DOIUrl":"10.1002/bimj.70030","url":null,"abstract":"<div>\u0000 \u0000 <p>Despite the extensive use of network autocorrelation models in social network analysis, network autocorrelation models for binary dependent variables have received surprisingly scant attention. In this paper, we develop four network autocorrelation models for a binary random variable defined by whether the peer effect (also termed social influence or contagion) acts on latent continuous outcomes leading to an <i>indirect effect</i> under a normal or a logistic distribution or on the probability of the observed outcome itself under a probit or a logit link function defining a <i>direct effect</i> to account for interdependence between outcomes. For all models, we use a Bayesian approach for model estimation under a uniform prior on a transformed peer effect parameter (<span></span><math>\u0000 <semantics>\u0000 <mi>ρ</mi>\u0000 <annotation>$rho$</annotation>\u0000 </semantics></math>) designed to enhance model computation and compare results to those under the uniform prior for <span></span><math>\u0000 <semantics>\u0000 <mi>ρ</mi>\u0000 <annotation>$rho$</annotation>\u0000 </semantics></math>. We use simulation to assess the performance of Bayesian point and interval estimators for each of the four models when the model that generated the data is used for estimation (precision assessment) and when each of the other three models instead generated the data (robustness assessment). We construct a United States New England region patient-sharing hospital network and apply the four network autocorrelation models to study the adoption of robotic surgery, a new medical technology, among hospitals using a cohort of United States Medicare beneficiaries in 2016 and 2017. Finally, we develop a deviance information criterion for each of the four models to compare their fit to the observed data and use posterior predictive <i>p</i>-values to assess the models' ability to recover specified features of the data. The results find that although the indirect peer effect of the propensity of peer hospital adoption on that of the focal hospital is positive under both latent response autocorrelation models, the direct peer effect of the peer hospital's probability of adopting robotic surgery on the probability of the focal hospital adopting robotic surgery decreases under both mean autocorrelation data models. However, neither of these associations is statistically significant.</p></div>","PeriodicalId":55360,"journal":{"name":"Biometrical Journal","volume":"67 1","pages":""},"PeriodicalIF":1.3,"publicationDate":"2024-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142911256","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}