Bayesian nonparametric inference for the overlap coefficient: With an application to disease diagnosis

Diagnostic tests play an important role in medical research and clinical practice. The ultimate goal of a diagnostic test is to distinguish between diseased and nondiseased individuals and before a test is routinely used in practice, it is a pivotal requirement that its ability to discriminate between these two states is thoroughly assessed. The overlap coefficient, which is defined as the proportion of overlap area between two probability density functions, has gained popularity as a summary measure of diagnostic accuracy. We propose two Bayesian nonparametric estimators, based on Dirichlet process mixtures, for estimating the overlap coefficient. We further introduce the covariate-specific overlap coefficient and develop a Bayesian nonparametric approach based on Dirichlet process mixtures of additive normal models for estimating it. A simulation study is conducted to assess the empirical performance of our proposed estimators. Two illustrations are provided: one concerned with the search for biomarkers of ovarian cancer and another one aimed to assess the age-specific accuracy of glucose as a biomarker of diabetes.

Bayesian inference on the number of recurrent events: A joint model of recurrence and survival

The number of recurrent events before a terminating event is often of interest. For instance, death terminates an individual's process of rehospitalizations and the number of rehospitalizations is an important indicator of economic cost. We propose a model in which the number of recurrences before termination is a random variable of interest, enabling inference and prediction on it. Then, conditionally on this number, we specify a joint distribution for recurrence and survival. This novel conditional approach induces dependence between recurrence and survival, which is often present, for instance, due to frailty that affects both. Additional dependence between recurrence and survival is introduced by the specification of a joint distribution on their respective frailty terms. Moreover, through the introduction of an autoregressive model, our approach is able to capture the temporal dependence in the recurrent events trajectory. A non-parametric random effects distribution for the frailty terms accommodates population heterogeneity and allows for data-driven clustering of the subjects. A tailored Gibbs sampler involving reversible jump and slice sampling steps implements posterior inference. We illustrate our model on colorectal cancer data, compare its performance with existing approaches and provide appropriate inference on the number of recurrent events.

Joint modeling of recurrent events and survival: a Bayesian non-parametric approach

Heart failure (HF) is one of the main causes of morbidity, hospitalization, and death in the western world, and the economic burden associated with HF management is relevant and expected to increase in the future. We consider hospitalization data for HF in the most populated Italian Region, Lombardia. Data were extracted from the administrative data warehouse of the regional healthcare system. The main clinical outcome of interest is time to death and research focus is on investigating how recurrent hospitalizations affect the time to event. The main contribution of the article is to develop a joint model for gap times between consecutive rehospitalizations and survival time. The probability models for the gap times and for the survival outcome share a common patient specific frailty term. Using a flexible Dirichlet process model for %Bayesian nonparametric prior as the random-effects distribution accounts for patient heterogeneity in recurrent event trajectories. Moreover, the joint model allows for dependent censoring of gap times by death or administrative reasons and for the correlations between different gap times for the same individual. It is straightforward to include covariates in the survival and/or recurrence process through the specification of appropriate regression terms. The main advantages of the proposed methodology are wide applicability, ease of interpretation, and efficient computations. Posterior inference is implemented through Markov chain Monte Carlo methods.

Bayesian Autoregressive Frailty Models for Inference in Recurrent Events

We propose autoregressive Bayesian semi-parametric models for gap times between recurrent events. The aim is two-fold: inference on the effect of possibly time-varying covariates on the gap times and clustering of individuals based on the time trajectory of the recurrent event. Time-dependency between gap times is taken into account through the specification of an autoregressive component for the frailty parameters influencing the response at different times. The order of the autoregression may be assumed unknown and is an object of inference. We consider two alternative approaches to perform model selection under this scenario. Covariates may be easily included in the regression framework and censoring and missing data are easily accounted for. As the proposed methodologies lie within the class of Dirichlet process mixtures, posterior inference can be performed through efficient MCMC algorithms. We illustrate the approach through simulations and medical applications involving recurrent hospitalizations of cancer patients and successive urinary tract infections.

Bayesian additive regression trees and the General BART model

Bayesian additive regression trees (BART) is a flexible prediction model/machine learning approach that has gained widespread popularity in recent years. As BART becomes more mainstream, there is an increased need for a paper that walks readers through the details of BART, from what it is to why it works. This tutorial is aimed at providing such a resource. In addition to explaining the different components of BART using simple examples, we also discuss a framework, the General BART model that unifies some of the recent BART extensions, including semiparametric models, correlated outcomes, and statistical matching problems in surveys, and models with weaker distributional assumptions. By showing how these models fit into a single framework, we hope to demonstrate a simple way of applying BART to research problems that go beyond the original independent continuous or binary outcomes framework.

Bayesian nonparametric inference for the three-class Youden index and its associated optimal cutoff points

The three-class Youden index serves both as a measure of medical test accuracy and a criterion to choose the optimal pair of cutoff values for classifying subjects into three ordinal disease categories (e.g. no disease, mild disease, advanced disease). We present a Bayesian nonparametric approach for estimating the three-class Youden index and its corresponding optimal cutoff values based on Dirichlet process mixtures, which are robust models that can handle intricate features of distributions for complex data. Results from a simulation study are presented and an application to data from the Trail Making Test to assess cognitive impairment in Parkinson's disease patients is detailed.

Scalable Bayesian nonparametric regression via a Plackett-Luce model for conditional ranks

We present a novel Bayesian nonparametric regression model for covariates X and continuous response variable Y ∈ ℝ. The model is parametrized in terms of marginal distributions for Y and X and a regression function which tunes the stochastic ordering of the conditional distributions F (y|x). By adopting an approximate composite likelihood approach, we show that the resulting posterior inference can be decoupled for the separate components of the model. This procedure can scale to very large datasets and allows for the use of standard, existing, software from Bayesian nonparametric density estimation and Plackett-Luce ranking estimation to be applied. As an illustration, we show an application of our approach to a US Census dataset, with over 1,300,000 data points and more than 100 covariates.

Bayesian population size estimation using Dirichlet process mixtures

We introduce a new Bayesian nonparametric method for estimating the size of a closed population from multiple-recapture data. Our method, based on Dirichlet process mixtures, can accommodate complex patterns of heterogeneity of capture, and can transparently modulate its complexity without a separate model selection step. Additionally, it can handle the massively sparse contingency tables generated by large number of recaptures with moderate sample sizes. We develop an efficient and scalable MCMC algorithm for estimation. We apply our method to simulated data, and to two examples from the literature of estimation of casualties in armed conflicts.

Discriminative variable subsets in Bayesian classification with mixture models, with application in flow cytometry studies

We discuss the evaluation of subsets of variables for the discriminative evidence they provide in multivariate mixture modeling for classification. The novel development of Bayesian classification analysis presented is partly motivated by problems of design and selection of variables in biomolecular studies, particularly involving widely used assays of large-scale single-cell data generated using flow cytometry technology. For such studies and for mixture modeling generally, we define discriminative analysis that overlays fitted mixture models using a natural measure of concordance between mixture component densities, and define an effective and computationally feasible method for assessing and prioritizing subsets of variables according to their roles in discrimination of one or more mixture components. We relate the new discriminative information measures to Bayesian classification probabilities and error rates, and exemplify their use in Bayesian analysis of Dirichlet process mixture models fitted via Markov chain Monte Carlo methods as well as using a novel Bayesian expectation–maximization algorithm. We present a series of theoretical and simulated data examples to fix concepts and exhibit the utility of the approach, and compare with prior approaches. We demonstrate application in the context of automatic classification and discriminative variable selection in high-throughput systems biology using large flow cytometry datasets.