A5065405793- Bayesian Methods and Mixture Models
- Statistical Methods and Inference
- Statistical Methods and Bayesian Inference
- Gene expression and cancer classification
- Functional Brain Connectivity Studies
- Neural dynamics and brain function
- Advanced MRI Techniques and Applications
- Radiomics and Machine Learning in Medical Imaging
- Gut microbiota and health
- Advanced Radiotherapy Techniques
- Statistical Methods in Clinical Trials
- Advanced Neuroimaging Techniques and Applications
- Bioinformatics and Genomic Networks
- Soil Geostatistics and Mapping
- Growth Hormone and Insulin-like Growth Factors
- Radiation Therapy and Dosimetry
- Advanced X-ray and CT Imaging
- Genetic and phenotypic traits in livestock
- AI in cancer detection
- Advanced Clustering Algorithms Research
- Mesenchymal stem cell research
- Colorectal Cancer Screening and Detection
- Neural Networks and Applications
- Cancer survivorship and care
- Spatial and Panel Data Analysis
University of California, Los Angeles
2022-2025
UCLA Health
2024
Politecnico di Milano
2023
University of California, Irvine
2016-2022
University of New Hampshire
2020
The University of Texas MD Anderson Cancer Center
2006-2018
University of Houston
2018
UC Irvine Health
2017
Rice University
2014-2016
University of Iowa
2016
Many models for the study of point-referenced data explicitly introduce spatial random effects to capture residual association.These are customarily modelled as a zeromean stationary Gaussian process.The Dirichlet process introduced by Gelfand et al. (2005) produces which is neither nor stationary.Rather, it varies about that assumed be and Gaussian.The arises probability-weighted collection surfaces.This can limiting modelling inferential purposes since insists realization must one these...
Despite increasing data on the impact of microbiome cancer, dynamics and role in infection during therapy for acute myelogenous leukemia (AML) are unknown. Therefore, authors sought to determine correlations between composition infectious outcomes patients with AML who were receiving induction chemotherapy (IC).Buccal fecal specimens (478 samples) collected twice weekly from 34 undergoing IC. Oral stool microbiomes characterized by 16S ribosomal RNA V4 sequencing using an Illumina MiSeq...
This article develops a unified theoretical and computational framework for false discovery control in multiple testing of spatial signals. We consider both point-wise cluster-wise analyses, derive oracle procedures which optimally the rate, exceedance cluster respectively. A data-driven finite approximation strategy is developed to mimic on continuous domain. Our are asymptotically valid can be effectively implemented using Bayesian algorithms analysis large data sets. Numerical results...
For more than two decades, national career development programs (CDPs) have addressed underrepresentation of women faculty in academic medicine through and leadership curricula. We evaluated CDP participation impact on retention.We used Association American Medical Colleges data to compare 3268 attending CDPs from 1988 2008 with 17,834 40,319 men nonparticipant similar participants degree, rank, first year appointment home institution. Measuring rank departure last position held or December...
Understanding longitudinal variability of the microbiome in ill patients is critical to moving microbiome-based measurements and therapeutics into clinical practice. However, vast majority data regarding stability are derived from healthy subjects. Herein, we sought determine intra-patient temporal microbiota variability, factors driving such its impact an extensive cohort hospitalized cancer during chemotherapy. The stool (n = 365) oral 483) samples 59 with acute myeloid leukemia (AML)...
Summary In functional data analysis, curves or surfaces are observed, up to measurement error, at a finite set of locations, for, say, sample n individuals. Often, the homogeneous, except perhaps for individual-specific regions that provide heterogeneous behaviour (e.g. ‘damaged’ areas irregular shape on an otherwise smooth surface). Motivated by applications with this nature, we propose Bayesian mixture model, aim dimension reduction, representing through smaller canonical curves. We novel...
The Human Microbiome has been variously associated with the immune-regulatory mechanisms involved in prevention or development of many non-infectious human diseases such as autoimmunity, allergy and cancer. Integrative approaches which aim at associating composition microbiome other available information, clinical covariates environmental predictors, are paramount to develop a more complete understanding role disease development.In this manuscript, we propose Bayesian Dirichlet-Multinomial...
Abstract Objective The process of cancer‐related breast reconstruction is typically multi‐staged and can take months to years complete, yet few studies have examined patient psychosocial well‐being during the process. We investigated effects timing stage on body image quality life at specific time points Methods In this cross‐sectional study, 216 patients were grouped into four reconstructive stages: pre‐reconstruction, completed 1, 2, final stages. Multiple regression analyses roles...
The clinical and biological effects of metabolic alterations in cancer are not fully understood.In high-grade serous ovarian (HGSOC) samples (n = 101), over 170 metabolites were profiled compared with normal tissues 15). To determine NAT8L gene expression across different types, we analyzed the RNA types using RNASeqV2 data available from open access Cancer Genome Atlas (TCGA) website (http://www.cbioportal.org/public-portal/). Using siRNA, molecular techniques histological analysis,...
Dynamic functional connectivity, i.e., the study of how interactions among brain regions change dynamically over course an fMRI experiment, has recently received wide interest in neuroimaging literature. Current approaches for studying dynamic connectivity often rely on ad-hoc inference, with time courses segmented by a sequence sliding windows. We propose principled Bayesian approach to which is based estimation varying networks. Our method utilizes hidden Markov model classification latent...
In this paper we propose a unified, probabilistically coherent framework for the analysis of task-related brain activity in multi-subject fMRI experiments. This is distinct from two-stage "group analysis" approaches traditionally considered literature, which separate inference on individual time courses at population level. our modeling approach consider spatiotemporal linear regression model and specifically account between-subjects heterogeneity neuronal via spatially informed...
Atypical femoral fractures (AFFs) are rare adverse events attributed to bisphosphonate (BP) use. Few cases of AFF in cancer have been described; the aim this study is identify incidence and risk factors for a large center. This retrospective was conducted at MD Anderson Cancer Center. The rate among BP users calculated from January 1, 2004 through December 31, 2013. control group (n = 51) included 2 or 3 patients on BPs matched age (≤1 year) gender. Logistic regression analysis used assess...
We discuss a Bayesian discovery procedure for multiple comparison problems. show that under coherent decision theoretic framework, loss function combining true positive and false counts leads to rule based on threshold of the posterior probability alternative. Under semi-parametric model data, we Bayes can be approximated by optimal (ODP), recently introduced Storey (2007a). Improving approximation us (BDP), which exploits shrinkage in clusters implied assumed nonparametric model. compare...
In geostatistics, it is common to model spatially distributed phenomena through an underlying stationary and isotropic spatial process. However, these assumptions are often untenable in practice because of the influence local effects correlation structure. Therefore, has been prolonged interest literature provide flexible effective ways non-stationarity effects. Arguably, due nature problem, we might envision that structure would be highly dependent on characteristics domain study, namely...
Objectives Body image is a critical issue for cancer patients undergoing reconstructive surgery, as they can experience disfigurement and functional impairment. Distress related to appearance changes lead various psychosocial difficulties, are often reluctant discuss these issues with their healthcare team. Our goals were design evaluate screening tool aid providers in identifying who may benefit from referral specialized care treat body concerns. Methods We designed brief four-item...
In this paper we present a Bayesian hierarchical modeling approach for imaging genetics, where the interest lies in linking brain connectivity across multiple individuals to their genetic information. We have available data from functional magnetic resonance (fMRI) study on schizophrenia. Our goals are identify regions of (ROIs) with discriminating activation patterns between schizophrenic patients and healthy controls, relate ROIs' activations information single nucleotide polymorphisms...
While some individuals can defy the lure of temptation, many others find appetizing food irresistible. The goal this study was to investigate neuropsychological mechanisms that increase individuals' vulnerability cue-induced eating. Using ERPs, a direct measure brain activity, we showed with larger late positive potentials in response food-related cues than erotic images are more susceptible eating and, presence palatable option, eat twice as much opposite reactivity profile. By highlighting...
Background: Three national career development programs (CDPs)-Early and Mid-Career Programs sponsored by the Association of American Medical Colleges Hedwig van Ameringen Executive Leadership in Academic Medicine Drexel University-seek to expand gender diversity faculty institutional leadership academic medical centers. Over 20 years success continued need are evident sustained interest investment individuals institutions. However, their impact on promotion rank remains unknown. The purpose...