Statistical Methods in Medical Research最新文献

{"title":"Treatment comparisons using a measurement during follow-up and a right-censored time-to-event outcome.","authors":"Michal Kicinski","doi":"10.1177/09622802261498390","DOIUrl":"https://doi.org/10.1177/09622802261498390","url":null,"abstract":"<p><p>In clinical trials, the comparison between treatment arms of a measurement is often complicated by an event such as death or progression that can make this measurement irrelevant or difficult to perform. In this article, an approach is proposed to compare treatment arms using the net treatment benefit or the win ratio. A more favorable outcome (win) for the experimental arm is defined as the event of (1) a longer time to event for a patient in the experimental arm compared to a patient from the control arm until a prespecified restriction time <math><mi>ϵ</mi></math> or (2) a more favorable outcome with respect to the measurement during follow-up for a patient from the experimental arm and the time to event greater than <math><mi>ϵ</mi></math> for both patients. An estimator is proposed. A simulation study showed approximately no bias. The methodology is illustrated using a leukemia trial.</p>","PeriodicalId":22038,"journal":{"name":"Statistical Methods in Medical Research","volume":" ","pages":"9622802261498390"},"PeriodicalIF":2.4,"publicationDate":"2026-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149196738","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"ROC-based methods for comparing two survival curves under non-proportional hazards with right, left, and doubly censored data.","authors":"Mohammod Mahmudur Rahman, Leonidas E Bantis","doi":"10.1177/09622802261497856","DOIUrl":"https://doi.org/10.1177/09622802261497856","url":null,"abstract":"<p><p>Studies comparing two survival curves to assess treatment differences are commonplace. The widely used log-rank test assumes proportional hazards (PH) and may yield misleading results when this assumption is violated. Alternative methods, such as the Fleming-Harrington weighted log-rank tests, rely on prior knowledge of survival patterns, which is often difficult to specify before a study. The recently developed MaxCombo test does not require such prior information; however, it leaves substantial room for power improvement, particularly when survival curves cross. To address these issues, we propose new nonparametric and semiparametric methods for comparing two survival curves based on the receiver operating characteristic (ROC) curve length and the overlap coefficient, along with a joint inference approach combining both measures. Our methods are applicable under non-PH settings and can accommodate right, left, and double censoring. We evaluate our methods through extensive simulation studies under different non-PH configurations. Our results show improved performance of the proposed methods compared to existing nonparametric methods, particularly under early and crossing effects. Real-world examples involving various non-PH scenarios are provided, illustrating the superiority of our methods in detecting survival differences. We further provide an R package named ''ROCsurvcomp\" that implements all our proposed approaches and is available on CRAN.</p>","PeriodicalId":22038,"journal":{"name":"Statistical Methods in Medical Research","volume":" ","pages":"9622802261497856"},"PeriodicalIF":2.4,"publicationDate":"2026-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149196697","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cluster-level analysis in three-level cluster randomised trials with multi-level covariate-dependent missingness.","authors":"Satish Pradhan, Priyanka Majumder","doi":"10.1177/09622802261498389","DOIUrl":"https://doi.org/10.1177/09622802261498389","url":null,"abstract":"<p><p>Community-based public health interventions often use three-level cluster randomised trials (CRTs), for example, individuals are nested within households which are again nested within communities. In these trials, outcome missingness commonly depends on baseline covariates measured at multiple levels. Although two-level CRTs are well studied, the effects of subcluster-level attrition and hierarchical covariate correlations on bias and variance are not yet fully explored. We develop an analytical framework for three-level CRTs under multi-level covariate-dependent missingness (CDM), explicitly incorporating within- and between-subcluster covariate correlations. We examine the performance of unadjusted and covariate-adjusted cluster-level treatment effect estimators using Monte Carlo simulations and a plasmode simulation based on the 2021 Madagascar Demographic and Health Survey. Our study reveals that unadjusted cluster-level analyses produce biased estimates under multi-level CDM. Linear mixed models are unbiased when correctly specified under missing-at-random assumptions but may be computationally unstable in small samples. The covariate-adjusted cluster-level estimator remains unbiased when covariate effects and missingness mechanisms are homogeneous across treatment arms. Subcluster-level attrition can lead to greater variance inflation than individual-level attrition. For CRTs with fewer than 30 clusters per arm and homogeneous treatment effects, covariate-adjusted cluster-level analysis may serve as a practical alternative to mixed models. A decision flowchart is provided to guide method selection.</p>","PeriodicalId":22038,"journal":{"name":"Statistical Methods in Medical Research","volume":" ","pages":"9622802261498389"},"PeriodicalIF":2.4,"publicationDate":"2026-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149196703","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Mixture cure rate model with artificial neural network for interval-censored data.","authors":"Junyao Ren, Shishun Zhao, Dianliang Deng, Shuwei Li","doi":"10.1177/09622802261495091","DOIUrl":"https://doi.org/10.1177/09622802261495091","url":null,"abstract":"<p><p>Mixture cure rate models represent a valuable tool to delineate the presence of a cured subgroup in the entire population under study. Among the vast literature, a popular research line is to regress the probability of an individual being cured on covariates through a parametric model, such as the logistic model. However, when the assumed parametric model is mis-specified, one could only attain a biased parameter estimate. In this work, motivated by the robustness and powerful approximation ability of neural networks, we offer a flexible mixture cure rate modeling approach for analyzing interval-censored data, which arise frequently in many scientific fields involving periodic follow-up or cross-sectional screening. In particular, we utilize the artificial neural network to model the cured probability and the proportional hazards model to characterize the latent event time distribution related to uncured individuals. After approximating the cumulative baseline hazard function with monotone splines, we develop a stable expectation-maximization algorithm coupled with a multiple imputation strategy and resilient backpropagation to locate the sieve maximum likelihood estimator. We establish the consistency and convergence rate of the proposed sieve estimator, as well as the asymptotic normality and semiparametric efficiency of the regression parameter estimator. Simulation experiments demonstrate that our proposed method works well and substantially outperforms the comparative methods. We then apply the proposed method to a real-world data set, revealing new findings and a better predictive performance.</p>","PeriodicalId":22038,"journal":{"name":"Statistical Methods in Medical Research","volume":" ","pages":"9622802261495091"},"PeriodicalIF":2.4,"publicationDate":"2026-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149138234","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Bayesian prevalence incidence cure model for estimating survival using electronic health records with incomplete baseline diagnoses.","authors":"Matilda Pitt, Robert Jb Goudie","doi":"10.1177/09622802261495109","DOIUrl":"https://doi.org/10.1177/09622802261495109","url":null,"abstract":"<p><p>Retrospective cohorts can be extracted from electronic health records (EHRs) to study prevalence, time until disease or event occurrence, and cure proportion in real-world scenarios. However, EHRs are collected for patient care rather than research, and thus typically have complexities, such as patients with missing baseline disease status. Prevalence incidence (PI) models, which use a two-component mixture model to account for this missing data, have been proposed. However, PI models are biased in settings in which some individuals will never experience the endpoint (they are 'cured'). To address this, we propose a prevalence-incidence-cure (PIC) model, a three-component mixture model that combines the PI model framework with a cure model. Our PIC model enables estimation of the prevalence rate, time-to-incidence, and the cure proportion, and allows for covariate effects on each component. We adopt a Bayesian inference approach, and focus on the interpretability of the prior. We show in a simulation study that the PIC model has smaller bias than PI and cure models for the survival probability; and we compare inference under vague, informative and misspecified priors. We illustrate our PIC model using a dataset of 1964 patients who underwent treatment for diabetic macular oedema, and demonstrate improved fit under our model.</p>","PeriodicalId":22038,"journal":{"name":"Statistical Methods in Medical Research","volume":" ","pages":"9622802261495109"},"PeriodicalIF":2.4,"publicationDate":"2026-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149138188","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Robust Bayesian hierarchical models for basket trials enabling joint evaluation of toxicity and efficacy.","authors":"Zhi Cao, Pavel Mozgunov, Haiyan Zheng","doi":"10.1177/09622802261465336","DOIUrl":"10.1177/09622802261465336","url":null,"abstract":"<p><p>Basket trials have gained increasing attention for their efficiency, as multiple patient subgroups are evaluated simultaneously. Conducted basket trials focus primarily on establishing the early efficacy of a treatment, yet continued monitoring of toxicity is essential. In this article, we propose two Bayesian hierarchical models that enable bivariate analyses of toxicity and efficacy, while accounting for heterogeneity present in the treatment effects across patient subgroups. Specifically, one assumes the subgroup-specific toxicity and efficacy treatment effects, as a parameter vector, can be exchangeable or non-exchangeable; the other allows either the toxicity or efficacy parameters specific to the subgroups, to be exchangeable or non-exchangeable. The bivariate exchangeability and non-exchangeability distributions introduce a correlation parameter between treatment effects, while we stipulate a zero correlation when only toxicity or efficacy parameters are exchangeable. Simulation results show that our models perform robustly under different scenarios compared to the standard Bayesian hierarchical model and the stand-alone analyses, especially in producing higher power when the subgroup-specific effects are exchangeable in toxicity or efficacy only. When considerable correlation between the toxicity and efficacy effects exists, our methodology gives small error rates and greater power than alternatives that analyse toxicity and efficacy by parts.</p>","PeriodicalId":22038,"journal":{"name":"Statistical Methods in Medical Research","volume":" ","pages":"2061-2075"},"PeriodicalIF":2.4,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13646420/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148881614","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A propensity score-integrated win ratio method for placebo borrowing.","authors":"Yurong Chen, Michael Sonksen, Tuo Wang, Yingdong Feng, Joon Jin Song","doi":"10.1177/09622802261478737","DOIUrl":"10.1177/09622802261478737","url":null,"abstract":"<p><p>Leveraging external control data has been used to enhance the efficiency of clinical trials, especially in rare diseases where recruitment is often challenging. However, directly pooling data from different studies without appropriate adjustments can lead to biased results when populations differ across these studies. In addition to limited sample sizes, trials for rare diseases commonly assess treatment efficacy through multiple clinical endpoints using composite endpoints. The win ratio has gained attention for composite endpoint analysis, as it enables prioritized comparisons that account for the relative clinical importance of each endpoint. Motivated by these two challenges, we proposed novel propensity score (PS)-integrated win ratio methods to incorporate external control data. Specifically, two PS-based weighting approaches, PS-ratio and PS-difference, are proposed to adjust for between-study baseline covariate differences, thereby mitigating the risk of potential bias. Simulation studies and real-world case analysis demonstrate that the proposed methods consistently improve statistical power while maintaining proper Type I error control. This framework offers a robust and practical solution for composite endpoint analysis using external controls, with particular relevance to rare disease trials and regulatory decision-making.</p>","PeriodicalId":22038,"journal":{"name":"Statistical Methods in Medical Research","volume":" ","pages":"2116-2128"},"PeriodicalIF":2.4,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148832440","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Bayesian variable selection for joint models of heterogeneous longitudinal variables and a binary outcome.","authors":"Lingpeng Shan, Michelle J Naughton, Electra D Paskett, Michael L Pennell","doi":"10.1177/09622802261478572","DOIUrl":"10.1177/09622802261478572","url":null,"abstract":"<p><p>Biomedical studies often collect mixed-type longitudinal data (e.g., clinical, lifestyle) to identify predictors of a binary health outcome. A common analytical challenge is to link these irregularly collected variables to the outcome, particularly when the number of potential predictors is large. While joint models (JM) can handle this complex data structure, a critical gap exists, as they lack a formal framework for variable selection, limiting their utility for identifying relevant predictors. This article fills that methodological gap by introducing two novel, structured Bayesian variable selection strategies. Our first approach (JM1) selects predictors for the binary outcome, while our more advanced approach (JM2) performs simultaneous two-level selection for both the outcome and the longitudinal trajectories. Our framework leverages shrinkage priors to handle high-dimensional predictors and interactions, preventing overfitting. To guide final variable selection, we extend false discovery rate-based rules to our complex, multi-part joint model, which also accommodates grouped categorical predictors. We apply our method to Women's Health Initiative and Life and Longevity After Cancer study data, identifying factors for post-treatment insomnia in breast cancer survivors. Our model identified a key predictor missed by conventional methods. This integrated approach provides a robust, interpretable, and computationally efficient framework, offering substantial gains in statistical power.</p>","PeriodicalId":22038,"journal":{"name":"Statistical Methods in Medical Research","volume":" ","pages":"2147-2163"},"PeriodicalIF":2.4,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148765067","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Sample size determination for a prospective bridging study to harmonize retrospective data from multiple studies-Application to a biofluid biomarker study of Alzheimer's disease.","authors":"Chengjie Xiong, Yuzheng Nie, Jingqin Luo, Ruijin Lu, David Wolk, Leslie M Shaw, Carey E Gleason, Sterling C Johnson, Folasade Agboola, John C Morris, Suzanne E Schindler","doi":"10.1177/09622802261468023","DOIUrl":"10.1177/09622802261468023","url":null,"abstract":"<p><p>Biomarkers measured from biofluid samples and imaging scans are important to aid diagnosis of diseases and track their progression over time, especially in neurodegenerative diseases such as Alzheimer's disease (AD). Combining retrospectively obtained biomarker data across multiple studies can increase statistical power, but existing biomarker data may be generated using different assay platforms, scanner types, or processing protocols by different studies, which may significantly affect the measurements of biomarkers and hence render it necessary to harmonize the data across the studies. An optimal way of biomarker data harmonization is to re-analyze all the biofluid samples or imaging scans together on a single platform in a central reference lab, but this is often not practical because of the substantial cost involved as well as the limited amount of biofluid samples available. A more practical solution is to prospectively design a bridging study by re-measuring a subset of biofluid samples or imaging scans from the studies in a reference lab to evaluate how biomarker values may be harmonized across studies. An important design question for such a bridging study is the size of the retrospectively collected biofluid samples or imaging scans that will be re-measured. We aim to address this question by conceptualizing a latent but true biomarker that underlies the observed versions of the biomarker measured across retrospective studies and proposing methods to determine the sample size of a bridging study for estimating the biological correlation of the true biomarker with a standard and validated clinical outcome. We also report bridging data of several analytes from cerebrospinal fluid (CSF) in a multi-center biomarker study of AD and demonstrate that a small proportion of the CSF samples may be sufficient to design a future bridging study for estimating the correlations of CSF biomarkers with a cognitive and functional outcome.</p>","PeriodicalId":22038,"journal":{"name":"Statistical Methods in Medical Research","volume":" ","pages":"2047-2060"},"PeriodicalIF":2.4,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148913618","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A flexible Monte Carlo quantitative bias analysis for unmeasured confounding.","authors":"Emily Kawabata, Chin Yang Shapland, Tom Palmer, David Carslake, Kate Tilling, Rachael Hughes","doi":"10.1177/09622802261488056","DOIUrl":"https://doi.org/10.1177/09622802261488056","url":null,"abstract":"<p><p>Quantitative bias analysis (QBA) for unmeasured confounding is essential for observational studies. A probabilistic QBA incorporates external information about the unmeasured confounders via prior distributions for certain parameters (known as <i>bias parameters</i>) that specify the relationship between the unmeasured confounders, <math><mi>U</mi></math>, and the study data. It can be implemented as a Bayesian or Monte Carlo QBA. Software implementations of probabilistic QBAs to unmeasured confounding are scarce and mainly limited to unadjusted analyses of binary variables. We propose a Monte Carlo QBA applicable to a generalised linear model or survival proportional hazards model that allows for: (i) binary, continuous, or categorical exposure and measured confounders <math><mi>C</mi></math>, (ii) dependence between <math><mi>C</mi></math> and <math><mi>U</mi></math>, and (iii) one or multiple binary or continuous <math><mi>U</mi></math>. To minimise the number of bias parameters, our proposed bias model does not model <math><mi>U</mi></math> directly but instead models the part of <math><mi>U</mi></math> not explained by <math><mi>C</mi></math>. Using a data example and simulation studies, we show that our Monte Carlo QBA, with informative priors, can virtually eliminate the bias due to unmeasured confounding in a wide range of scenarios and performs as well as a Bayesian QBA. Our Monte Carlo QBA will be available as Stata command and R package, <i>qbaconfound</i>.</p>","PeriodicalId":22038,"journal":{"name":"Statistical Methods in Medical Research","volume":" ","pages":"9622802261488056"},"PeriodicalIF":2.4,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149115054","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}