Pattern discovery of health curves using an ordered probit model with Bayesian smoothing and functional principal component analysis.

This article is motivated by the need for discovering patterns of patients' health based on their daily settings of care to aid the health policy-makers to improve the effectiveness of distributing funding for health services. The hidden process of one's health status is assumed to be a continuous smooth function, called the health curve, ranging from perfectly healthy to dead. The health curves are linked to the categorical setting of care using an ordered probit model and are inferred through Bayesian smoothing. The challenges include the nontrivial constraints on the lower bound of the health status (death) and on the model parameters to ensure model identifiability. We use the Markov chain Monte Carlo method to estimate the parameters and health curves. The functional principal component analysis is applied to the patients' estimated health curves to discover common health patterns. The proposed method is demonstrated through an application to patients hospitalized from strokes in Ontario. Whilst this paper focuses on the method's application to a health care problem, the proposed model and its implementation have the potential to be applied to many application domains in which the response variable is ordinal and there is a hidden process. Our implementation is available at https://github.com/liangliangwangsfu/healthCurveCode.

Particle Gibbs sampling for Bayesian phylogenetic inference.

MOTIVATION: The combinatorial sequential Monte Carlo (CSMC) has been demonstrated to be an efficient complementary method to the standard Markov chain Monte Carlo (MCMC) for Bayesian phylogenetic tree inference using biological sequences. It is appealing to combine the CSMC and MCMC in the framework of the particle Gibbs (PG) sampler to jointly estimate the phylogenetic trees and evolutionary parameters. However, the Markov chain of the PG may mix poorly for high dimensional problems (e.g. phylogenetic trees). Some remedies, including the PG with ancestor sampling and the interacting particle MCMC, have been proposed to improve the PG. But they either cannot be applied to or remain inefficient for the combinatorial tree space. RESULTS: We introduce a novel CSMC method by proposing a more efficient proposal distribution. It also can be combined into the PG sampler framework to infer parameters in the evolutionary model. The new algorithm can be easily parallelized by allocating samples over different computing cores. We validate that the developed CSMC can sample trees more efficiently in various PG samplers via numerical experiments. AVAILABILITY AND IMPLEMENTATION: The implementation of our method and the data underlying this article are available at https://github.com/liangliangwangsfu/phyloPMCMC. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

An Annealed Sequential Monte Carlo Method for Bayesian Phylogenetics.

We describe an "embarrassingly parallel" method for Bayesian phylogenetic inference, annealed Sequential Monte Carlo (SMC), based on recent advances in the SMC literature such as adaptive determination of annealing parameters. The algorithm provides an approximate posterior distribution over trees and evolutionary parameters as well as an unbiased estimator for the marginal likelihood. This unbiasedness property can be used for the purpose of testing the correctness of posterior simulation software. We evaluate the performance of phylogenetic annealed SMC by reviewing and comparing with other computational Bayesian phylogenetic methods, in particular, different marginal likelihood estimation methods. Unlike previous SMC methods in phylogenetics, our annealed method can utilize standard Markov chain Monte Carlo (MCMC) tree moves and hence benefit from the large inventory of such moves available in the literature. Consequently, the annealed SMC method should be relatively easy to incorporate into existing phylogenetic software packages based on MCMC algorithms. We illustrate our method using simulation studies and real data analysis.

The ability of ADC measurements in the assessment of patients with stage I endometrial carcinoma based on three risk categories.

BACKGROUND: Better selection of patients with intermediate and high-risk stage I endometrial carcinoma (EC) for lymphadenectomy has an important effect on the prognosis. PURPOSE: To investigate the role of apparent diffusion coefficient (ADC) measurements in the assessment of stage I EC patients based on three risk categories. MATERIAL AND METHODS: We retrospectively studied 80 patients with EC and 28 cervical cancer patients with normal endometrium. 1.5-T conventional magnetic resonance imaging (MRI) and diffusion-weighted imaging (DWI) (b = 0, 1000 s/mm2) were performed, and ADC values were calculated. Sixty-eight stage I EC patients were divided into three groups: low-risk EC (group 1); intermediate-risk EC (group 2); and high-risk EC (group 3). The remaining 12 EC patients were in stages II and III. Intraclass coefficient, Mann-Whitney U test, Kruskal-Wallis test, and receiver operating characteristics were used for statistical analysis. RESULTS: The mean ADC values ( × 10-3 mm2 /s) were 0.851 ± 0.131, 0.734 ± 0.108, and 0.710 ± 0.108 for groups 1, 2 and 3, respectively. Significant statistical differences were achieved for the three groups ( P = 0.0005). The mean ADC values of group 1 were significantly lower than those in group 2 + 3 (0.725 ± 0.106; P = 0.0001). For the prediction of groups 2 + 3, the area under the curve of 0.786 and the cut-off value of ≤ 0.742 were identified, with a sensitivity, specificity, and accuracy of 66.67%, 84.09%, and 73.53%, respectively. CONCLUSION: ADC measurements may have the potential to select intermediate-risk and high-risk stage I EC patients for lymphadenectomy.

Joint modelling for organ transplantation outcomes for patients with diabetes and the end-stage renal disease.

This article is motivated by jointly modelling longitudinal and time-to-event clinical data of patients with diabetes and end-stage renal disease. All patients are on the waiting list for the pancreas transplant after kidney transplant, and some of them have a pancreas transplant before kidney transplant failure or death. Scant literature has studied the dynamical joint relationship of the estimated glomerular filtration rates trajectory, the effect of pancreas transplant, and time-to-event outcomes, although it remains an important clinical question. In an attempt to describe the association in the multiple outcomes, we propose a new joint model with a longitudinal submodel and an accelerated failure time submodel, which are linked by some latent variables. The accelerated failure time submodel is used to determine the relationship of the time-to-event outcome with all predictors. In addition, the piecewise linear function in the survival submodel is used to calculate the dynamic hazard ratio curve of a time-dependent side event, because the effect of the side event on the time-to-event outcome is non-proportional. The model parameters are estimated with a Monte Carlo EM algorithm. The finite sample performance of the proposed method is investigated in simulation studies. Our method is demonstrated by fitting the joint model for the clinical data of 13,635 patients with diabetes and the end-stage renal disease.