Bayesian functional data analysis over dependent regions and its application for identification of differentially methylated regions.

We consider a Bayesian functional data analysis for observations measured as extremely long sequences. Splitting the sequence into several small windows with manageable lengths, the windows may not be independent especially when they are neighboring each other. We propose to utilize Bayesian smoothing splines to estimate individual functional patterns within each window and to establish transition models for parameters involved in each window to address the dependence structure between windows. The functional difference of groups of individuals at each window can be evaluated by the Bayes factor based on Markov Chain Monte Carlo samples in the analysis. In this paper, we examine the proposed method through simulation studies and apply it to identify differentially methylated genetic regions in TCGA lung adenocarcinoma data.

Recreational physical activity before and during pregnancy and placental DNA methylation-an epigenome-wide association study.

BACKGROUND: Physical activity (PA) prior to and during pregnancy may have intergenerational effects on offspring health through placental epigenetic modifications. We are unaware of epidemiologic studies on longitudinal PA and placental DNA methylation. OBJECTIVES: We evaluated the association between PA before and during pregnancy and placental DNA methylation. METHODS: Placental tissues were obtained at delivery and methylation was measured using HumanMethylation450 Beadchips for participants in the Eunice Kennedy Shriver National Institute of Child Health and Human Development Fetal Growth Studies-Singletons among 298 participants. Using the Pregnancy Physical Activity Questionnaire, women recalled periconception PA (past 12 mo) at 8-13 wk of gestation and PA since last visit at 4 follow-up visits at 16-22, 24-29, 30-33, and 34-37 wk. We conducted linear regression for associations of PA at each visit with methylation controlling for false discovery rate (FDR). Top 100 CpGs were queried for enrichment of functional pathways using Ingenuity Pathway Analysis. RESULTS: Periconception PA was significantly associated with 1 CpG site. PA since last visit for visits 1-4 was associated with 2, 2, 8, and 0 CpGs (log fold changes ranging from -0.0319 to 0.0080, after controlling for FDR). The largest change in methylation occurred at a site in TIMP2 , which is known to encode a protein critical for vasodilation, placentation, and uterine expansion during pregnancy (log fold change: -0.05; 95% CI: -0.06, -0.03 per metabolic equivalent of task-h/wk at 30-33 wk). Most significantly enriched pathways include cardiac hypertrophy signaling, B-cell receptor signaling, and netrin signaling. Significant CpGs and enriched pathways varied by visit. CONCLUSIONS: Recreational PA in the year prior and during pregnancy was associated with placental DNA methylation. The associated CpG sites varied based on timing of PA. If replicated, the findings may inform the mechanisms underlying the impacts of PA on placenta health. This study was registered at clinicaltrials.gov as NCT00912132.

Predictors of 30-Day Unplanned Readmission After Carotid Artery Stenting Using Artificial Intelligence.

INTRODUCTION: This study aimed to describe the rates and causes of unplanned readmissions within 30 days following carotid artery stenting (CAS) and to use artificial intelligence machine learning analysis for creating a prediction model for short-term readmissions. The prediction of unplanned readmissions after index CAS remains challenging. There is a need to leverage deep machine learning algorithms in order to develop robust prediction tools for early readmissions. METHODS: Patients undergoing inpatient CAS during the year 2017 in the US Nationwide Readmission Database (NRD) were evaluated for the rates, predictors, and costs of unplanned 30-day readmission. Logistic regression, support vector machine (SVM), deep neural network (DNN), random forest, and decision tree models were evaluated to generate a robust prediction model. RESULTS: We identified 16,745 patients who underwent CAS, of whom 7.4% were readmitted within 30 days. Depression [p < 0.001, OR 1.461 (95% CI 1.231-1.735)], heart failure [p < 0.001, OR 1.619 (95% CI 1.363-1.922)], cancer [p < 0.001, OR 1.631 (95% CI 1.286-2.068)], in-hospital bleeding [p = 0.039, OR 1.641 (95% CI 1.026-2.626)], and coagulation disorders [p = 0.007, OR 1.412 (95% CI 1.100-1.813)] were the strongest predictors of readmission. The artificial intelligence machine learning DNN prediction model has a C-statistic value of 0.79 (validation 0.73) in predicting the patients who might have all-cause unplanned readmission within 30 days of the index CAS discharge. CONCLUSIONS: Machine learning derived models may effectively identify high-risk patients for intervention strategies that may reduce unplanned readmissions post carotid artery stenting. CENTRAL ILLUSTRATION: Figure 2: ROC and AUPRC analysis of DNN prediction model with other classification models on 30-day readmission data for CAS subjects.

We present a novel deep neural network-based artificial intelligence prediction model to help identify a subgroup of patients undergoing carotid artery stenting who are at risk for short-term unplanned readmissions. Prior studies have attempted to develop prediction models but have used mainly logistic regression models and have low prediction ability. The novel model presented in this study boasts 79% capability to accurately predict individuals for unplanned readmissions post carotid artery stenting within 30 days of discharge.