Sepsis-trained macrophages promote antitumoral tissue-resident T cells.

Sepsis induces immune alterations, which last for months after the resolution of illness. The effect of this immunological reprogramming on the risk of developing cancer is unclear. Here we use a national claims database to show that sepsis survivors had a lower cumulative incidence of cancers than matched nonsevere infection survivors. We identify a chemokine network released from sepsis-trained resident macrophages that triggers tissue residency of T cells via CCR2 and CXCR6 stimulations as the immune mechanism responsible for this decreased risk of de novo tumor development after sepsis cure. While nonseptic inflammation does not provoke this network, laminarin injection could therapeutically reproduce the protective sepsis effect. This chemokine network and CXCR6 tissue-resident T cell accumulation were detected in humans with sepsis and were associated with prolonged survival in humans with cancer. These findings identify a therapeutically relevant antitumor consequence of sepsis-induced trained immunity.

Latent pathway-based Bayesian models to identify intervenable factors of racial disparities in breast cancer stage at diagnosis.

PURPOSE: We built Bayesian Network (BN) models to explain roles of different patient-specific factors affecting racial differences in breast cancer stage at diagnosis, and to identify healthcare related factors that can be intervened to reduce racial health disparities. METHODS: We studied women age 67-74 with initial diagnosis of breast cancer during 2006-2014 in the National Cancer Institute's SEER-Medicare dataset. Our models included four measured variables (tumor grade, hormone receptor status, screening utilization and biopsy delay) expressed through two latent pathways-a tumor biology path, and health-care access/utilization path. We used various Bayesian model assessment tools to evaluate these two latent pathways as well as each of the four measured variables in explaining racial disparities in stage-at-diagnosis. RESULTS: Among 3,010 Black non-Hispanic (NH) and 30,310 White NH breast cancer patients, respectively 70.2% vs 76.9% were initially diagnosed at local stage, 25.3% vs 20.3% with regional stage, and 4.56% vs 2.80% with distant stage-at-diagnosis. Overall, BN performed approximately 4.7 times better than Classification And Regression Tree (CART) (Breiman L, Friedman JH, Stone CJ, Olshen RA. Classification and regression trees. CRC press; 1984) in predicting stage-at-diagnosis. The utilization of screening mammography is the most prominent contributor to the accuracy of the BN model. Hormone receptor (HR) status and tumor grade are useful for explaining racial disparity in stage-at diagnosis, while log-delay in biopsy impeded good prediction. CONCLUSIONS: Mammography utilization had a significant effect on racial differences in breast cancer stage-at-diagnosis, while tumor biology factors had less impact. Biopsy delay also aided in predicting local and regional stages-at-diagnosis for Black NH women but not for white NH women.

A note on median regression for complex surveys.

There is a great need for statistical methods for analyzing skewed responses in complex sample surveys. Quantile regression is a logical option in addressing this problem but is often accompanied by incorrect variance estimation. We show how the variance can be estimated correctly by including the survey design in the variance estimation process. In a simulation study, we illustrate that the variance of the median regression estimator has a very small relative bias with appropriate coverage probability. The motivation for our work stems from the National Health and Nutrition Examination Survey where we demonstrate the impact of our results on iodine deficiency in females compared with males adjusting for other covariates.

Bayesian regression analysis of skewed tensor responses.

Tensor regression analysis is finding vast emerging applications in a variety of clinical settings, including neuroimaging, genomics, and dental medicine. The motivation for this paper is a study of periodontal disease (PD) with an order-3 tensor response: multiple biomarkers measured at prespecified tooth-sites within each tooth, for each participant. A careful investigation would reveal considerable skewness in the responses, in addition to response missingness. To mitigate the shortcomings of existing analysis tools, we propose a new Bayesian tensor response regression method that facilitates interpretation of covariate effects on both marginal and joint distributions of highly skewed tensor responses, and accommodates missing-at-random responses under a closure property of our tensor model. Furthermore, we present a prudent evaluation of the overall covariate effects while identifying their possible variations on only a sparse subset of the tensor components. Our method promises Markov chain Monte Carlo (MCMC) tools that are readily implementable. We illustrate substantial advantages of our proposal over existing methods via simulation studies and application to a real data set derived from a clinical study of PD. The R package BSTN available in GitHub implements our model.

Bayesian additive regression trees for multivariate skewed responses.

This paper introduces a nonparametric regression approach for univariate and multivariate skewed responses using Bayesian additive regression trees (BART). Existing BART methods use ensembles of decision trees to model a mean function, and have become popular recently due to their high prediction accuracy and ease of use. The usual assumption of a univariate Gaussian error distribution, however, is restrictive in many biomedical applications. Motivated by an oral health study, we provide a useful extension of BART, the skewBART model, to address this problem. We then extend skewBART to allow for multivariate responses, with information shared across the decision trees associated with different responses within the same subject. The methodology accommodates within-subject association, and allows varying skewness parameters for the varying multivariate responses. We illustrate the benefits of our multivariate skewBART proposal over existing alternatives via simulation studies and application to the oral health dataset with bivariate highly skewed responses. Our methodology is implementable via the R package skewBART, available on GitHub.

Semiparametric analysis of clustered interval-censored survival data using soft Bayesian additive regression trees (SBART).

Popular parametric and semiparametric hazards regression models for clustered survival data are inappropriate and inadequate when the unknown effects of different covariates and clustering are complex. This calls for a flexible modeling framework to yield efficient survival prediction. Moreover, for some survival studies involving time to occurrence of some asymptomatic events, survival times are typically interval censored between consecutive clinical inspections. In this article, we propose a robust semiparametric model for clustered interval-censored survival data under a paradigm of Bayesian ensemble learning, called soft Bayesian additive regression trees or SBART (Linero and Yang, 2018), which combines multiple sparse (soft) decision trees to attain excellent predictive accuracy. We develop a novel semiparametric hazards regression model by modeling the hazard function as a product of a parametric baseline hazard function and a nonparametric component that uses SBART to incorporate clustering, unknown functional forms of the main effects, and interaction effects of various covariates. In addition to being applicable for left-censored, right-censored, and interval-censored survival data, our methodology is implemented using a data augmentation scheme which allows for existing Bayesian backfitting algorithms to be used. We illustrate the practical implementation and advantages of our method via simulation studies and an analysis of a prostate cancer surgery study where dependence on the experience and skill level of the physicians leads to clustering of survival times. We conclude by discussing our method's applicability in studies involving high-dimensional data with complex underlying associations.

Median regression models for clustered, interval-censored survival data - An application to prostate surgery study.

Genitourinary surgeons and oncologists are particularly interested in whether a robotic surgery improves times to Prostate Specific Antigen (PSA) recurrence compared to a non-robotic surgery for removing the cancerous prostate. Time to PSA recurrence is an example of a survival time that is typically interval-censored between two consecutive clinical inspections with opposite test results. In addition, success of medical devices and technologies often depends on factors such as experience and skill level of the medical service providers, thus leading to clustering of these survival times. For analyzing the effects of surgery types and other covariates on median of clustered interval-censored time to post-surgery PSA recurrence, we present three competing novel models and associated frequentist and Bayesian analyses. The first model is based on a transform-both-sides of survival time with Gaussian random effects to account for the within-cluster association. Our second model assumes an approximate marginal Laplace distribution for the transformed log-survival times with a Gaussian copula to accommodate clustering. Our third model is a special case of the second model with Laplace distribution for the marginal log-survival times and Gaussian copula for the within-cluster association. Simulation studies establish the second model to be highly robust against extreme observations while estimating median regression coefficients. We provide a comprehensive comparison among these three competing models based on the model properties and the computational ease of their Frequentist and Bayesian analysis. We also illustrate the practical implementations and uses of these methods via analysis of a simulated clustered interval-censored data-set similar in design to a post-surgery PSA recurrence study.

Bayesian analysis of survival data with missing censoring indicators.

In some large clinical studies, it may be impractical to perform the physical examination to every subject at his/her last monitoring time in order to diagnose the occurrence of the event of interest. This gives rise to survival data with missing censoring indicators where the probability of missing may depend on time of last monitoring and some covariates. We present a fully Bayesian semi-parametric method for such survival data to estimate regression parameters of the proportional hazards model of Cox. Theoretical investigation and simulation studies show that our method performs better than competing methods. We apply the proposed method to analyze the survival data with missing censoring indicators from the Orofacial Pain: Prospective Evaluation and Risk Assessment study.

Improved dropClust R package with integrative analysis support for scRNA-seq data.

SUMMARY: DropClust leverages Locality Sensitive Hashing (LSH) to speed up clustering of large scale single cell expression data. Here we present the improved dropClust, a complete R package that is, fast, interoperable and minimally resource intensive. The new dropClust features a novel batch effect removal algorithm that allows integrative analysis of single cell RNA-seq (scRNA-seq) datasets. AVAILABILITY AND IMPLEMENTATION: dropClust is freely available at https://github.com/debsin/dropClust as an R package. A lightweight online version of the dropClust is available at https://debsinha.shinyapps.io/dropClust/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Semiparametric mixed-scale models using shared Bayesian forests.

This paper demonstrates the advantages of sharing information about unknown features of covariates across multiple model components in various nonparametric regression problems including multivariate, heteroscedastic, and semicontinuous responses. In this paper, we present a methodology which allows for information to be shared nonparametrically across various model components using Bayesian sum-of-tree models. Our simulation results demonstrate that sharing of information across related model components is often very beneficial, particularly in sparse high-dimensional problems in which variable selection must be conducted. We illustrate our methodology by analyzing medical expenditure data from the Medical Expenditure Panel Survey (MEPS). To facilitate the Bayesian nonparametric regression analysis, we develop two novel models for analyzing the MEPS data using Bayesian additive regression trees-a heteroskedastic log-normal hurdle model with a "shrink-toward-homoskedasticity" prior and a gamma hurdle model.

dropClust: efficient clustering of ultra-large scRNA-seq data.

Droplet based single cell transcriptomics has recently enabled parallel screening of tens of thousands of single cells. Clustering methods that scale for such high dimensional data without compromising accuracy are scarce. We exploit Locality Sensitive Hashing, an approximate nearest neighbour search technique to develop a de novo clustering algorithm for large-scale single cell data. On a number of real datasets, dropClust outperformed the existing best practice methods in terms of execution time, clustering accuracy and detectability of minor cell sub-types.

Semiparametric Bayesian latent variable regression for skewed multivariate data.

For many real-life studies with skewed multivariate responses, the level of skewness and association structure assumptions are essential for evaluating the covariate effects on the response and its predictive distribution. We present a novel semiparametric multivariate model and associated Bayesian analysis for multivariate skewed responses. Similar to multivariate Gaussian densities, this multivariate model is closed under marginalization, allows a wide class of multivariate associations, and has meaningful physical interpretations of skewness levels and covariate effects on the marginal density. Other desirable properties of our model include the Markov Chain Monte Carlo computation through available statistical software, and the assurance of consistent Bayesian estimates of the parameters and the nonparametric error density under a set of plausible prior assumptions. We illustrate the practical advantages of our methods over existing alternatives via simulation studies and the analysis of a clinical study on periodontal disease.

Categorical Data Analysis Using a Skewed Weibull Regression Model.

In this paper, we present a Weibull link (skewed) model for categorical response data arising from binomial as well as multinomial model. We show that, for such types of categorical data, the most commonly used models (logit, probit and complementary log-log) can be obtained as limiting cases. We further compare the proposed model with some other asymmetrical models. The Bayesian as well as frequentist estimation procedures for binomial and multinomial data responses are presented in detail. The analysis of two datasets to show the efficiency of the proposed model is performed.

Bayesian partial linear model for skewed longitudinal data.

Unlike majority of current statistical models and methods focusing on mean response for highly skewed longitudinal data, we present a novel model for such data accommodating a partially linear median regression function, a skewed error distribution and within subject association structures. We provide theoretical justifications for our methods including asymptotic properties of the posterior and associated semiparametric Bayesian estimators. We also provide simulation studies to investigate the finite sample properties of our methods. Several advantages of our method compared with existing methods are demonstrated via analysis of a cardiotoxicity study of children of HIV-infected mothers.

Approximate median regression for complex survey data with skewed response.

The ready availability of public-use data from various large national complex surveys has immense potential for the assessment of population characteristics using regression models. Complex surveys can be used to identify risk factors for important diseases such as cancer. Existing statistical methods based on estimating equations and/or utilizing resampling methods are often not valid with survey data due to complex survey design features. That is, stratification, multistage sampling, and weighting. In this article, we accommodate these design features in the analysis of highly skewed response variables arising from large complex surveys. Specifically, we propose a double-transform-both-sides (DTBS)'based estimating equations approach to estimate the median regression parameters of the highly skewed response; the DTBS approach applies the same Box-Cox type transformation twice to both the outcome and regression function. The usual sandwich variance estimate can be used in our approach, whereas a resampling approach would be needed for a pseudo-likelihood based on minimizing absolute deviations (MAD). Furthermore, the approach is relatively robust to the true underlying distribution, and has much smaller mean square error than a MAD approach. The method is motivated by an analysis of laboratory data on urinary iodine (UI) concentration from the National Health and Nutrition Examination Survey.

Almost efficient estimation of relative risk regression.

Relative risks (RRs) are often considered the preferred measures of association in prospective studies, especially when the binary outcome of interest is common. In particular, many researchers regard RRs to be more intuitively interpretable than odds ratios. Although RR regression is a special case of generalized linear models, specifically with a log link function for the binomial (or Bernoulli) outcome, the resulting log-binomial regression does not respect the natural parameter constraints. Because log-binomial regression does not ensure that predicted probabilities are mapped to the [0,1] range, maximum likelihood (ML) estimation is often subject to numerical instability that leads to convergence problems. To circumvent these problems, a number of alternative approaches for estimating RR regression parameters have been proposed. One approach that has been widely studied is the use of Poisson regression estimating equations. The estimating equations for Poisson regression yield consistent, albeit inefficient, estimators of the RR regression parameters. We consider the relative efficiency of the Poisson regression estimator and develop an alternative, almost efficient estimator for the RR regression parameters. The proposed method uses near-optimal weights based on a Maclaurin series (Taylor series expanded around zero) approximation to the true Bernoulli or binomial weight function. This yields an almost efficient estimator while avoiding convergence problems. We examine the asymptotic relative efficiency of the proposed estimator for an increase in the number of terms in the series. Using simulations, we demonstrate the potential for convergence problems with standard ML estimation of the log-binomial regression model and illustrate how this is overcome using the proposed estimator. We apply the proposed estimator to a study of predictors of pre-operative use of beta blockers among patients undergoing colorectal surgery after diagnosis of colon cancer.

Testing for independence in J×K contingency tables with complex sample survey data.

The test of independence of row and column variables in a (J×K) contingency table is a widely used statistical test in many areas of application. For complex survey samples, use of the standard Pearson chi-squared test is inappropriate due to correlation among units within the same cluster. Rao and Scott (1981, Journal of the American Statistical Association 76, 221-230) proposed an approach in which the standard Pearson chi-squared statistic is multiplied by a design effect to adjust for the complex survey design. Unfortunately, this test fails to exist when one of the observed cell counts equals zero. Even with the large samples typical of many complex surveys, zero cell counts can occur for rare events, small domains, or contingency tables with a large number of cells. Here, we propose Wald and score test statistics for independence based on weighted least squares estimating equations. In contrast to the Rao-Scott test statistic, the proposed Wald and score test statistics always exist. In simulations, the score test is found to perform best with respect to type I error. The proposed method is motivated by, and applied to, post surgical complications data from the United States' Nationwide Inpatient Sample (NIS) complex survey of hospitals in 2008.

Using the jackknife for estimation in log link Bernoulli regression models.

Bernoulli (or binomial) regression using a generalized linear model with a log link function, where the exponentiated regression parameters have interpretation as relative risks, is often more appropriate than logistic regression for prospective studies with common outcomes. In particular, many researchers regard relative risks to be more intuitively interpretable than odds ratios. However, for the log link, when the outcome is very prevalent, the likelihood may not have a unique maximum. To circumvent this problem, a 'COPY method' has been proposed, which is equivalent to creating for each subject an additional observation with the same covariates except the response variable has the outcome values interchanged (1's changed to 0's and 0's changed to 1's). The original response is given weight close to 1, while the new observation is given a positive weight close to 0; this approach always leads to convergence of the maximum likelihood algorithm, except for problems with convergence due to multicollinearity among covariates. Even though this method produces a unique maximum, when the outcome is very prevalent, and/or the sample size is relatively small, the COPY method can yield biased estimates. Here, we propose using the jackknife as a bias-reduction approach for the COPY method. The proposed method is motivated by a study of patients undergoing colorectal cancer surgery.

Association of maternal blood pressure in pregnancy with blood pressure of their offspring through adolescence.

This article looks at the association of maternal blood pressure with the blood pressure of the offspring from birth to childhood. The Barker hypothesis states that maternal and "in utero" attributes during pregnancy affect a child's cardiovascular health throughout life. We present an analysis of a unique dataset that consists of three distinct developmental processes: maternal cardiovascular health during pregnancy; fetal development; and child's cardiovascular health from birth to 14 years. This study explored whether a mother's blood pressure reading in pregnancy predicts fetal development and determines if this in turn is related to the future cardiovascular health of the child. This article uses data that have been collected prospectively from a Jamaican cohort which involves the following three developmental processes: (1) maternal cardiovascular health during pregnancy which is the blood pressure and anthropometric measurements at seven time-points on the mother during pregnancy; (2) fetal development which consists of ultrasound measurements of the fetus taken at six time-points during pregnancy; and (3) child's cardiovascular health which consists of the child's blood pressure measurements at 24 time-points from birth to 14 years. The inter-relationship of these three processes was examined using linear mixed effects models. Our analyses indicated that attributes later in childhood development, such as child's weight, child's baseline systolic blood pressure (SBP), age and sex, predict the future cardiovascular health of children. The results also indicated that maternal attributes in pregnancy, such as mother's baseline SBP and SBP change, predicted significantly child's SBP over time.

Bayesian analysis of recurrent event with dependent termination: an application to a heart transplant study.

For a heart transplant patient, the risk of graft rejection and risk of death are likely to be associated. Two fully specified Bayesian models for recurrent events with dependent termination are applied to investigate the potential relationships between these two types of risk as well as association with risk factors. We particularly focus on the choice of priors, selection of the appropriate prediction model, and prediction methods for these two types of risk for an individual patient. Our prediction tools can be easily implemented and helpful to physicians for setting heart transplant patients' biopsy schedule.