Statistics in Medicine最新文献

Polygenic risk scores (PRS) aim to predict a trait from genetic information, relying on common genetic variants with low to medium effect sizes. As genotype data are high-dimensional in nature, it is crucial to develop methods that can be applied to large-scale data (large $n$ and large $p$ ). Many PRS tools aggregate univariate summary statistics from genome-wide association studies into a single score. Recent advancements allow simultaneous modeling of variant effects from individual-level genotype data. In this context, we introduced snpboost, an algorithm that applies statistical boosting on individual-level genotype data to estimate PRS via multivariable regression models. By processing variants iteratively in batches, snpboost can deal with large-scale cohort data. Having solved the technical obstacles due to data dimensionality, the methodological scope can now be broadened-focusing on key objectives for the clinical application of PRS. Similar to most methods in this context, snpboost has, so far, been restricted to quantitative and binary traits. Now, we incorporate more advanced alternatives-targeted to the particular aim and outcome. Adapting the loss function extends the snpboost framework to further data situations such as time-to-event and count data. Furthermore, alternative loss functions for continuous outcomes allow us to focus not only on the mean of the conditional distribution but also on other aspects that may be more helpful in the risk stratification of individual patients and can quantify prediction uncertainty, for example, median or quantile regression. This work enhances PRS fitting across multiple model classes previously unfeasible for this data type.

There are limited options to estimate the treatment effects of variables which are continuous and measured at multiple time points, particularly if the true dose-response curve should be estimated as closely as possible. However, these situations may be of relevance: in pharmacology, one may be interested in how outcomes of people living with-and treated for-HIV, such as viral failure, would vary for time-varying interventions such as different drug concentration trajectories. A challenge for doing causal inference with continuous interventions is that the positivity assumption is typically violated. To address positivity violations, we develop projection functions, which reweigh and redefine the estimand of interest based on functions of the conditional support for the respective interventions. With these functions, we obtain the desired dose-response curve in areas of enough support, and otherwise a meaningful estimand that does not require the positivity assumption. We develop $g$ -computation type plug-in estimators for this case. Those are contrasted with g-computation estimators which are applied to continuous interventions without specifically addressing positivity violations, which we propose to be presented with diagnostics. The ideas are illustrated with longitudinal data from HIV positive children treated with an efavirenz-based regimen as part of the CHAPAS-3 trial, which enrolled children years in Zambia/Uganda. Simulations show in which situations a standard g-computation approach is appropriate, and in which it leads to bias and how the proposed weighted estimation approach then recovers the alternative estimand of interest.

Within each of 170 physicians, patients were randomized to access e-assist, an online program that aimed to increase colorectal cancer screening (CRCS), or control. Compliance was partial: $78.34\%$ of the experimental patients accessed e-assist while no controls were provided the access. Of interest are the average causal effect of assignment to treatment and the complier average causal effect as well as the variation of these causal effects across physicians. Each physician generates probabilities of screening for experimental compliers (experimental patients who accessed e-assist), control compliers (controls who would have accessed e-assist had they been assigned to e-assist), and never takers (patients who would have avoided e-assist no matter what). Estimating physician-specific probabilities jointly over physicians poses novel challenges. We address these challenges by maximum likelihood, factoring a "complete-data likelihood" uniquely into the conditional distribution of screening and partially observed compliance given random effects and the distribution of random effects. We marginalize this likelihood using adaptive Gauss-Hermite quadrature. The approach is doubly iterative in that the conditional distribution defies analytic evaluation. Because the small sample size per physician constrains estimability of multiple random effects, we reduce their dimensionality using a shared random effects model having a factor analytic structure. We assess estimators and recommend sample sizes to produce reasonably accurate and precise estimates by simulation, and analyze data from a trial of a CRCS intervention.

The first Adaptive COVID-19 Treatment Trial (ACTT-1) showed that remdesivir improved COVID-19 recovery time compared with placebo in hospitalized adults. The secondary outcome of mortality was almost significant overall (p = 0.07) and highly significant for people receiving supplemental oxygen at enrollment (p = 0.002), suggesting a mortality benefit concentrated in this group. We explore analysis methods that are helpful when a single subgroup benefits from treatment and apply them to ACTT-1, using baseline oxygen use to define subgroups. We consider two questions: (1) is the remdesivir effect for people receiving supplemental oxygen real, and (2) does this effect differ from the overall effect? For Question 1, we apply a Bonferroni adjustment to subgroup-specific hypothesis tests and the Westfall and Young permutation test, which is valid when small cell counts preclude normally distributed test statistics (a frequently unexamined condition in subgroup analyses). For Question 2, we introduce Q_max, the largest standardized difference between subgroup-specific effects and the overall effect. Q_max simultaneously tests whether any subgroup effect differs from the overall effect and identifies the subgroup benefitting most. We demonstrate that Q_max strongly controls the familywise error rate (FWER) when test statistics are normally distributed with no mean-variance relationship. We compare Q_max to a related permutation test, SEAMOS, which was previously proposed but not extensively applied or tested. We show that SEAMOS can have inflated Type 1 error under the global null when control arm event rates differ between subgroups. Our results support a mortality benefit from remdesivir in people receiving supplemental oxygen.

We consider the problem of combining multiple biomarkers to improve the diagnostic accuracy of detecting a disease when only group-tested data on the disease status are available. There are several challenges in addressing this problem, including unavailable individual disease statuses, differential misclassification depending on group size and number of diseased individuals in the group, and extensive computation due to a large number of possible combinations of multiple biomarkers. To tackle these issues, we propose a pairwise model fitting approach to estimating the distribution of the optimal linear combination of biomarkers and its diagnostic accuracy under the assumption of a multivariate normal distribution. The approach is evaluated in simulation studies and applied to data on chlamydia detection and COVID-19 diagnosis.

It is becoming increasingly common for researchers to consider leveraging information from external sources to enhance the analysis of small-scale studies. While much attention has focused on univariate survival data, correlated survival data are prevalent in epidemiological investigations. In this article, we propose a unified framework to improve the estimation of the marginal accelerated failure time model with correlated survival data by integrating additional information given in the form of covariate effects evaluated in a reduced accelerated failure time model. Such auxiliary information can be summarized by using valid estimating equations and hence can then be combined with the internal linear rank-estimating equations via the generalized method of moments. We investigate the asymptotic properties of the proposed estimator and show that it is more efficient than the conventional estimator using internal data only. When population heterogeneity exists, we revise the proposed estimation procedure and present a shrinkage estimator to protect against bias and loss of efficiency. Moreover, the proposed estimation procedure can be further refined to accommodate the non-negligible uncertainty in the auxiliary information, leading to more trustable inference conclusions. Simulation results demonstrate the finite sample performance of the proposed methods, and empirical application on the Prostate, Lung, Colorectal, and Ovarian Cancer Screening Trial substantiates its practical relevance.

Motivated by a small sample example in neonatal onset multisystem inflammatory disease (NOMID), we propose a method that can be used when the interest is testing for an association between a changes in disease progression with start of treatment compared to historical disease progression prior to treatment. Our method estimates the longitudinal trajectory of the outcome variable and adds an interaction term between an intervention indicator variable and the time since initiation of the intervention. This method is appropriate for a situation in which the intervention slows or arrests the effect of the disease on the outcome, as is the case in our motivating example. By simulation in small samples and restricted sets of treatment initiation times, we show that the generalized estimating equations (GEE) formulation with small sample adjustments can bound the Type I error rate better than GEE and linear mixed models without small sample adjustments. Permutation tests (permuting the time of treatment initiation) is another valid approach that can also be useful. We illustrate the methodology through an application to a prospective cohort of NOMID patients enrolled at the NIH clinical center.

As a favorable alternative to the censored quantile regression, censored expectile regression has been popular in survival analysis due to its flexibility in modeling the heterogeneous effect of covariates. The existing weighted expectile regression (WER) method assumes that the censoring variable and covariates are independent, and that the covariates effects has a global linear structure. However, these two assumptions are too restrictive to capture the complex and nonlinear pattern of the underlying covariates effects. In this article, we developed a novel weighted expectile regression neural networks (WERNN) method by incorporating the deep neural network structure into the censored expectile regression framework. To handle the random censoring, we employ the inverse probability of censoring weighting (IPCW) technique in the expectile loss function. The proposed WERNN method is flexible enough to fit nonlinear patterns and therefore achieves more accurate prediction performance than the existing WER method for right censored data. Our findings are supported by extensive Monte Carlo simulation studies and a real data application.

Mendelian randomization is an instrumental variable method that utilizes genetic information to investigate the causal effect of a modifiable exposure on an outcome. In most cases, the exposure changes over time. Understanding the time-varying causal effect of the exposure can yield detailed insights into mechanistic effects and the potential impact of public health interventions. Recently, a growing number of Mendelian randomization studies have attempted to explore time-varying causal effects. However, the proposed approaches oversimplify temporal information and rely on overly restrictive structural assumptions, limiting their reliability in addressing time-varying causal problems. This article considers a novel approach to estimate time-varying effects through continuous-time modelling by combining functional principal component analysis and weak-instrument-robust techniques. Our method effectively utilizes available data without making strong structural assumptions and can be applied in general settings where the exposure measurements occur at different timepoints for different individuals. We demonstrate through simulations that our proposed method performs well in estimating time-varying effects and provides reliable inference when the time-varying effect form is correctly specified. The method could theoretically be used to estimate arbitrarily complex time-varying effects. However, there is a trade-off between model complexity and instrument strength. Estimating complex time-varying effects requires instruments that are unrealistically strong. We illustrate the application of this method in a case study examining the time-varying effects of systolic blood pressure on urea levels.

Network meta-analysis (NMA) combines evidence from multiple trials to compare the effectiveness of a set of interventions. In many areas of research, interventions are often complex, made up of multiple components or features. This makes it difficult to define a common set of interventions on which to perform the analysis. One approach to this problem is component network meta-analysis (CNMA) which uses a meta-regression framework to define each intervention as a subset of components whose individual effects combine additively. In this article, we are motivated by a systematic review of complex interventions to prevent obesity in children. Due to considerable heterogeneity across the trials, these interventions cannot be expressed as a subset of components but instead are coded against a framework of characteristic features. To analyse these data, we develop a bespoke CNMA-inspired model that allows us to identify the most important features of interventions. We define a meta-regression model with covariates on three levels: intervention, study, and follow-up time, as well as flexible interaction terms. By specifying different regression structures for trials with and without a control arm, we relax the assumption from previous CNMA models that a control arm is the absence of intervention components. Furthermore, we derive a correlation structure that accounts for trials with multiple intervention arms and multiple follow-up times. Although, our model was developed for the specifics of the obesity data set, it has wider applicability to any set of complex interventions that can be coded according to a set of shared features.