Statistics in Medicine最新文献

Viral load (VL) in the respiratory tract is the leading proxy for assessing infectiousness potential. Understanding the dynamics of disease-related VL within the host is of great importance, as it helps to determine different policies and health recommendations. However, normally the VL is measured on individuals only once, in order to confirm infection, and furthermore, the infection date is unknown. It is therefore necessary to develop statistical approaches to estimate the typical VL trajectory. We show here that, under plausible parametric assumptions, two measures of VL on infected individuals can be used to accurately estimate the VL mean function. Specifically, we consider a discrete-time likelihood-based approach to modeling and estimating partial observed longitudinal samples. We study a multivariate normal model for a function of the VL that accounts for possible correlation between measurements within individuals. We derive an expectation-maximization (EM) algorithm which treats the unknown time origins and the missing measurements as latent variables. Our main motivation is the reconstruction of the daily mean VL, given measurements on patients whose VLs were measured multiple times on different days. Such data should and can be obtained at the beginning of a pandemic with the specific goal of estimating the VL dynamics. For demonstration purposes, the method is applied to SARS-Cov-2 cycle-threshold-value data collected in Israel.

With the increasing maturity of genetic profiling, an essential and routine task in cancer research is to model disease outcomes/phenotypes using genetic variables. Many methods have been successfully developed. However, oftentimes, empirical performance is unsatisfactory because of a "lack of information." In cancer research and clinical practice, a source of information that is broadly available and highly cost-effective comes from pathological images, which are routinely collected for definitive diagnosis and staging. In this article, we consider a Bayesian approach for selecting relevant genetic variables and modeling their relationships with a cancer outcome/phenotype. We propose borrowing information from (manually curated, low-dimensional) pathological imaging features via reinforcing the same selection results for the cancer outcome and imaging features. We further develop a weighting strategy to accommodate the scenario where information borrowing may not be equally effective for all subjects. Computation is carefully examined. Simulations demonstrate competitive performance of the proposed approach. We analyze TCGA (The Cancer Genome Atlas) LUAD (lung adenocarcinoma) data, with overall survival and gene expressions being the outcome and genetic variables, respectively. Findings different from the alternatives and with sound properties are made.

Multi-gene panel testing allows efficient detection of pathogenic variants in cancer susceptibility genes including moderate-risk genes such as ATM and PALB2. A growing number of studies examine the risk of breast cancer (BC) conferred by pathogenic variants of these genes. A meta-analysis combining the reported risk estimates can provide an overall estimate of age-specific risk of developing BC, that is, penetrance for a gene. However, estimates reported by case-control studies often suffer from ascertainment bias. Currently, there is no method available to adjust for such bias in this setting. We consider a Bayesian random effect meta-analysis method that can synthesize different types of risk measures and extend it to incorporate studies with ascertainment bias. This is achieved by introducing a bias term in the model and assigning appropriate priors. We validate the method through a simulation study and apply it to estimate BC penetrance for carriers of pathogenic variants in the ATM and PALB2 genes. Our simulations show that the proposed method results in more accurate and precise penetrance estimates compared to when no adjustment is made for ascertainment bias or when such biased studies are discarded from the analysis. The overall estimated BC risk for individuals with pathogenic variants are (1) 5.77% (3.22%-9.67%) by age 50 and 26.13% (20.31%-32.94%) by age 80 for ATM; (2) 12.99% (6.48%-22.23%) by age 50, and 44.69% (34.40%-55.80%) by age 80 for PALB2. The proposed method allows meta-analyses to include studies with ascertainment bias, resulting in inclusion of more studies and thereby more accurate estimates.

This manuscript derives the allocation predictability measured by the correct guess probability and the probability of being deterministic for individual treatment assignments, as well as the averages of a randomization sequence, based on the treatment imbalance transition matrix and the conditional allocation probability. The methods described are applicable to restricted randomization designs that satisfy the following criteria: (1) two-arm equal allocation, (2) restriction of maximum tolerated imbalance, and (3) conditional allocation probability fully determined by the observed current treatment imbalance. Analytical results indicate that, for two-arm equal allocation trials, allocation predictability alternates by the odd/even sequence order of the treatment assignment. Additionally, the sequence average allocation predictability converges to its asymptotic value significantly more slowly than the allocation predictability for individual assignment does. Consequently, comparisons of allocation predictability between different randomization designs based on sequence averages are sensitive to sequence length. Using sequence average allocation predictability may underestimate the risk of selection bias for individual assignment. This discrepancy is particularly pronounced for short sequence lengths, where individual assignment predictability can be substantially higher than the sequence average.

Evaluating classifications is crucial in statistics and machine learning, as it influences decision-making across various fields, such as patient prognosis and therapy in critical conditions. The Matthews correlation coefficient (MCC), also known as the phi coefficient, is recognized as a performance metric with high reliability, offering a balanced measurement even in the presence of class imbalances. Despite its importance, there remains a notable lack of comprehensive research on the statistical inference of MCC. This deficiency often leads to studies merely validating and comparing MCC point estimates-a practice that, while common, overlooks the statistical significance and reliability of results. Addressing this research gap, our paper introduces and evaluates several methods to construct asymptotic confidence intervals for the single MCC and the differences between MCCs in paired designs. Through simulations across various scenarios, we evaluate the finite-sample behavior of these methods and compare their performances. Furthermore, through real data analysis, we illustrate the potential utility of our findings in comparing binary classifiers, highlighting the possible contributions of our research in this field.

Generalized estimating equations (GEE) are of great importance in analyzing clustered data without full specification of multivariate distributions. A recent approach by Luo and Pan jointly models the mean, variance, and correlation coefficients of clustered data through three sets of regressions. We note that it represents a specific case of the more general estimating equations proposed by Yan and Fine which further allow the variance to depend on the mean through a variance function. In certain scenarios, the proposed variance estimators for the variance and correlation parameters in Luo and Pan may face challenges due to the subtle dependence induced by the nested structure of the estimating equations. We characterize specific model settings where their variance estimation approach may encounter limitations and illustrate how the variance estimators in Yan and Fine can correctly account for such dependencies. In addition, we introduce a novel model selection criterion that enables the simultaneous selection of the mean-scale-correlation model. The sandwich variance estimator and the proposed model selection criterion are tested by several simulation studies and real data analysis, which validate its effectiveness in variance estimation and model selection. Our work also extends the R package geepack with the flexibility to apply different working covariance matrices for the variance and correlation structures.

High-dimensional regression problems, for example with genomic or drug exposure data, typically involve automated selection of a sparse set of regressors. Penalized regression methods like the LASSO can deliver a family of candidate sparse models. To select one, there are criteria balancing log-likelihood and model size, the most common being AIC and BIC. These two methods do not take into account the implicit multiple testing performed when selecting variables in a high-dimensional regression, which makes them too liberal. We propose the extended AIC (EAIC), a new information criterion for sparse model selection in high-dimensional regressions. It allows for asymptotic FWER control when the candidate regressors are independent. It is based on a simple formula involving model log-likelihood, model size, the total number of candidate regressors, and the FWER target. In a simulation study over a wide range of linear and logistic regression settings, we assessed the variable selection performance of the EAIC and of other information criteria (including some that also use the number of candidate regressors: mBIC, mAIC, and EBIC) in conjunction with the LASSO. Our method controls the FWER in nearly all settings, in contrast to the AIC and BIC, which produce many false positives. We also illustrate it for the automated signal detection of adverse drug reactions on the French pharmacovigilance spontaneous reporting database.

Hazard models are the most commonly used tool to analyze time-to-event data. If more than one time scale is relevant for the event under study, models are required that can incorporate the dependence of a hazard along two (or more) time scales. Such models should be flexible to capture the joint influence of several time scales, and nonparametric smoothing techniques are obvious candidates. $P$ -splines offer a flexible way to specify such hazard surfaces, and estimation is achieved by maximizing a penalized Poisson likelihood. Standard observation schemes, such as right-censoring and left-truncation, can be accommodated in a straightforward manner. Proportional hazards regression with a baseline hazard varying over two time scales is presented. Efficient computation is possible by generalized linear array model (GLAM) algorithms or by exploiting a sparse mixed model formulation. A companion R-package is provided.

In medical research, individual-level patient data provide invaluable information, but the patients' right to confidentiality remains of utmost priority. This poses a huge challenge when estimating statistical models such as a linear mixed model, which is an extension of linear regression models that can account for potential heterogeneity whenever data come from different data providers. Federated learning tackles this hurdle by estimating parameters without retrieving individual-level data. Instead, iterative communication of parameter estimate updates between the data providers and analysts is required. In this article, we propose an alternative framework to federated learning for fitting linear mixed models. Specifically, our approach only requires the mean, covariance, and sample size of multiple covariates from different data providers once. Using the principle of statistical sufficiency within the likelihood framework as theoretical support, this proposed strategy achieves estimates identical to those derived from actual individual-level data. We demonstrate this approach through real data on 15 068 patient records from 70 clinics at the Children's Hospital of Pennsylvania. Assuming that each clinic only shares summary statistics once, we model the COVID-19 polymerase chain reaction test cycle threshold as a function of patient information. Simplicity, communication efficiency, generalisability, and wider scope of implementation in any statistical software distinguish our approach from existing strategies in the literature.

Partially linear models provide a valuable tool for modeling failure time data with nonlinear covariate effects. Their applicability and importance in survival analysis have been widely acknowledged. To date, numerous inference methods for such models have been developed under traditional right censoring. However, the existing studies seldom target interval-censored data, which provide more coarse information and frequently occur in many scientific studies involving periodical follow-up. In this work, we propose a flexible class of partially linear transformation models to examine parametric and nonparametric covariate effects for interval-censored outcomes. We consider the sieve maximum likelihood estimation approach that approximates the cumulative baseline hazard function and nonparametric covariate effect with the monotone splines and $B$ -splines, respectively. We develop an easy-to-implement expectation-maximization algorithm coupled with three-stage data augmentation to facilitate maximization. We establish the consistency of the proposed estimators and the asymptotic distribution of parametric components based on the empirical process techniques. Numerical results from extensive simulation studies indicate that our proposed method performs satisfactorily in finite samples. An application to a study on hypobaric decompression sickness suggests that the variable TR360 exhibits a significant dynamic and nonlinear effect on the risk of developing hypobaric decompression sickness.