Yize Zhao

Multiple imputation in the presence of high-dimensional data.

Missing data are frequently encountered in biomedical, epidemiologic and social research. It is well known that a naive analysis without adequate handling of missing data may lead to bias and/or loss of efficiency. Partly due to its ease of use, multiple imputation has become increasingly popular in practice for handling missing data. However, it is unclear what is the best strategy to conduct multiple imputation in the presence of high-dimensional data. To answer this question, we investigate several approaches of using regularized regression and Bayesian lasso regression to impute missing values in the presence of high-dimensional data. We compare the performance of these methods through numerical studies, in which we also evaluate the impact of the dimension of the data, the size of the true active set for imputation, and the strength of correlation. Our numerical studies show that in the presence of high-dimensional data the standard multiple imputation approach performs poorly and the imputation approach using Bayesian lasso regression achieves, in most cases, better performance than the other imputation methods including the standard imputation approach using the correctly specified imputation model. Our results suggest that Bayesian lasso regression and its extensions are better suited for multiple imputation in the presence of high-dimensional data than the other regression methods.

Very high-dose cholecalciferol and arteriovenous fistula maturation in ESRD: a randomized, double-blind, placebo-controlled pilot study.

Purpose While vitamin D is critical for optimal skeletal health, it also appears to play a significant role in vascular homeostasis. This pilot study compared arteriovenous (AV) access outcomes following cholecalciferol supplementation compared to placebo in end-stage renal disease patients preparing to undergo AV access creation. Methods A total of 52 adult hemodialysis patients preparing for arteriovenous fistula (AVF) creation were randomized to receive perioperative high-dose cholecalciferol versus placebo in this double-blind, randomized, placebo-controlled pilot study. The primary outcome was mean response to high-dose oral cholecalciferol versus placebo, and secondary outcome AV access maturation at 6 months. Logistic regression was used to assess the association between AV access maturation and baseline, posttreatment and overall change in vitamin D concentration. Results A total of 45% of cholecalciferol-treated and 54% of placebo-treated patients were successfully using their AVF or arteriovenous graft (AVG) at 6 months (p=0.8). Baseline serum concentrations of 25(OH)D and 1,25(OH)2D did not differ between those who experienced AVF or AVG maturation and those who did not (p=0.22 and 0.59, respectively). Similarly, there was no relationship between AVF or AVG maturation and posttreatment serum 25(OH)D and 1,25(OH)2D concentration (p=0.24 and 0.51, respectively). Conclusions Perioperative high-dose vitamin D3 therapy does correct 25(OH)D level but does not appear to have an association with AV access maturation rates. Future research may include extended preoperative vitamin D3 therapy in a larger population or in certain subpopulations at high risk for AVF failure.

Immediate Allergic Reactions to Gadolinium-based Contrast Agents: A Systematic Review and Meta-Analysis

Purpose To perform a systematic review and meta-analysis to determine if there are differences in rates of immediate allergic events between classes of gadolinium-based contrast agents (GBCAs). Materials and Methods PubMed and Google Scholar databases were searched for studies in which rates of immediate adverse events to GBCAs were reported. The American College of Radiology classification system was used to characterize allergic-like events as mild, moderate, or severe, and the total number of administrations of each GBCA was recorded. Where necessary, authors of studies were contacted to clarify data and eliminate physiologic reactions. Relative risks of GBCA types were estimated by using the Mantel-Haenszel type method. Results Nine studies in which immediate reactions to GBCA were recorded from a total of 716 978 administrations of GBCA met the criteria for inclusion and exclusion. The overall rate of patients who had immediate allergic-like reactions was 9.2 per 10 000 administrations and the overall rate of severe immediate allergic-like reactions was 0.52 per 10 000 administrations.. The nonionic linear chelate gadodiamide had the lowest rate of reactions, at 1.5 (95% confidence interval [CI]: 0.74, 2.4) per 10 000 administrations, which was significantly less than that of linear ionic GBCAs at 8.3 (95% CI: 7.5, 9.2) per 10 000 administrations (relative risk, 0.19 [95% CI: 0.099, 0.36]; P < .00001) and less than that for nonionic macrocyclic GBCAs at 16 (95% CI: 14, 19) per 10 000 administrations (relative risk, 0.12 [95% CI: 0.05, 0.31]; P < .001). GBCAs known to be associated with protein binding had a higher rate of reactions, at 17 (95% CI: 15, 20) per 10 000 administrations compared with the same chelate classification without protein binding, at 5.2 (95% CI: 4.5, 6.0) per 10 000 administrations (relative risk, 3.1 [95% CI: 2.4, 3.8]; P < .0001). Conclusion These data show the lowest rate of immediate allergic adverse events with use of the nonionic linear GBCA gadodiamide in comparison with those of ionic linear or nonionic macrocyclic GBCAs. A higher rate of immediate allergic adverse events was associated with ionicity, protein binding, and macrocyclic structure.

Comparison of MRI segmentation techniques for measuring liver cyst volumes in autosomal dominant polycystic kidney disease

Purpose: To compare segmentation methods for measuring liver cyst volumes in ADPKD. Methods: Liver cyst volumes in 42 ADPKD patients were measured using region growing, thresholding and cyst diameter techniques. Manual segmentation was the reference standard. ACCEPTED MANUSCRIPTPURPOSE To compare MRI segmentation methods for measuring liver cyst volumes in autosomal dominant polycystic kidney disease (ADPKD). METHODS Liver cyst volumes in 42 ADPKD patients were measured using region growing, thresholding and cyst diameter techniques. Manual segmentation was the reference standard. RESULTS Root mean square deviation was 113, 155, and 500 for cyst diameter, thresholding and region growing respectively. Thresholding error for cyst volumes below 500ml was 550% vs 17% for cyst volumes above 500ml (p<0.001). CONCLUSION For measuring volume of a small number of cysts, cyst diameter and manual segmentation methods are recommended. For severe disease with numerous, large hepatic cysts, thresholding is an acceptable alternative.

A BAYESIAN NONPARAMETRIC MIXTURE MODEL FOR SELECTING GENES AND GENE SUBNETWORKS.

It is very challenging to select informative features from tens of thousands of measured features in high-throughput data analysis. Recently, several parametric/regression models have been developed utilizing the gene network information to select genes or pathways strongly associated with a clinical/biological outcome. Alternatively, in this paper, we propose a nonparametric Bayesian model for gene selection incorporating network information. In addition to identifying genes that have a strong association with a clinical outcome, our model can select genes with particular expressional behavior, in which case the regression models are not directly applicable. We show that our proposed model is equivalent to an infinity mixture model for which we develop a posterior computation algorithm based on Markov chain Monte Carlo (MCMC) methods. We also propose two fast computing algorithms that approximate the posterior simulation with good accuracy but relatively low computational cost. We illustrate our methods on simulation studies and the analysis of Spellman yeast cell cycle microarray data.

Dentate Nucleus Signal Intensity Decrease on T1-weighted MR Images after Switching from Gadopentate Dimeglumine to Gadobutrol

Purpose To determine if the increased dentate nucleus signal intensity following six or more doses of a linear gadolinium-based contrast agent (GBCA) (gadopentetate dimeglumine) changes at follow-up examinations performed with a macrocyclic GBCA (gadobutrol). Materials and Methods This retrospective study included 13 patients with increased dentate nucleus signal intensity following at least six (range, 6-18) gadopentetate dimeglumine administrations who then underwent at least 12 months of follow-up imaging with multiple (range, 3-29) gadobutrol-enhanced magnetic resonance (MR) examinations. Dentate nucleus-to-pons and dentate nucleus-to-cerebellar peduncle signal intensity ratios were measured by two radiologists blinded to all patient information, and changes were analyzed by using the paired t test and linear regression. Results The mean dentate nucleus-to-pons and dentate nucleus-to-cerebellar peduncle signal intensity ratios increased after gadopentetate dimeglumine administration, from 0.98 ± 0.03 to 1.10 ± 0.03 (P < .0001) and from 0.98 ± 0.030 to 1.09 ± 0.02 (P < .0001), respectively. With gadobutrol, the mean dentate nucleus-to-pons and dentate nucleus-to-cerebellar peduncle signal intensity ratios decreased to 1.03 ± 0.03 and 1.02 ± 0.04, respectively (P < .0001). With use of a mixed effects model linear regression allowing for each patient to have a different y intercept, mean dentate nucleus-to-pons and dentate nucleus-to-cerebellar peduncle signal intensity ratios decreased with follow-up time (dentate nucleus-to-pons: slope = -0.2% per month [95% confidence interval: -0.0024, -0.0015], R2 = 0.58, P < .0001 for nonzero slope; dentate nucleus-to-cerebellar peduncle: slope = -0.2% per month [95% confidence interval: -0.0024, -0.0015], R2 = 0.61, P < .0001 for nonzero slope). Conclusion Dentate signal intensity increased with at least six gadopentetate dimeglumine-enhanced MR examinations and decreased after switching from a linear (gadopentetate dimeglumine) to a macrocyclic (gadobutrol) GBCA.

Hierarchical Feature Selection Incorporating Known and Novel Biological Information: Identifying Genomic Features Related to Prostate Cancer Recurrence

ABSTRACT Our work is motivated by a prostate cancer study aimed at identifying mRNA and miRNA biomarkers that are predictive of cancer recurrence after prostatectomy. It has been shown in the literature that incorporating known biological information on pathway memberships and interactions among biomarkers improves feature selection of high-dimensional biomarkers in relation to disease risk. Biological information is often represented by graphs or networks, in which biomarkers are represented by nodes and interactions among them are represented by edges; however, biological information is often not fully known. For example, the role of microRNAs (miRNAs) in regulating gene expression is not fully understood and the miRNA regulatory network is not fully established, in which case new strategies are needed for feature selection. To this end, we treat unknown biological information as missing data (i.e., missing edges in graphs), different from commonly encountered missing data problems where variable values are missing. We propose a new concept of imputing unknown biological information based on observed data and define the imputed information as the novel biological information. In addition, we propose a hierarchical group penalty to encourage sparsity and feature selection at both the pathway level and the within-pathway level, which, combined with the imputation step, allows for incorporation of known and novel biological information. While it is applicable to general regression settings, we develop and investigate the proposed approach in the context of semiparametric accelerated failure time models motivated by our data example. Data application and simulation studies show that incorporation of novel biological information improves performance in risk prediction and feature selection and the proposed penalty outperforms the extensions of several existing penalties. Supplementary materials for this article are available online.

Variable selection in the presence of missing data: imputation-based methods

Variable selection plays an essential role in regression analysis as it identifies important variables that associated with outcomes and is known to improve predictive accuracy of resulting models. Variable selection methods have been widely investigated for fully observed data. However, in the presence of missing data, methods for variable selection need to be carefully designed to account for missing data mechanisms and statistical techniques used for handling missing data. Since imputation is arguably the most popular method for handling missing data due to its ease of use, statistical methods for variable selection that are combined with imputation are of particular interest. These methods, valid used under the assumptions of missing at random (MAR) and missing completely at random (MCAR), largely fall into three general strategies. The first strategy applies existing variable selection methods to each imputed dataset and then combine variable selection results across all imputed datasets. The second strategy applies existing variable selection methods to stacked imputed datasets. The third variable selection strategy combines resampling techniques such as bootstrap with imputation. Despite recent advances, this area remains under-developed and offers fertile ground for further research.

Complex liver cysts in Autosomal Dominant Polycystic Kidney Disease

PURPOSE To determine prevalence of complex liver cysts in Autosomal Dominant Polycystic Kidney Disease (ADPKD). METHODS Abdominal MRI in 186 ADPKD subjects were evaluated by two independent observers to determine prevalence of complex liver cysts. RESULTS 23 (12%) of subjects, had at least 1 complex cyst. Only 8 (4%) were reported to have a complex cyst prospectively, representing an under-reporting rate of 65%. Median total cyst volume was 66-times greater for subjects with complex cysts compared to subjects without (p<0.0001). CONCLUSION Complex hepatic cysts were observed in 12% of ADPKD cases, occurring more frequently in livers with extensive cystic involvement.

Modeling clinical outcome using multiple correlated functional biomarkers: A Bayesian approach

In some biomedical studies, biomarkers are measured repeatedly along some spatial structure or over time and are subject to measurement error. In these studies, it is often of interest to evaluate associations between a clinical endpoint and these biomarkers (also known as functional biomarkers). There are potentially two levels of correlation in such data, namely, between repeated measurements of a biomarker from the same subject and between multiple biomarkers from the same subject; none of the existing methods accounts for correlation between multiple functional biomarkers. We propose a Bayesian approach to model a clinical outcome of interest (e.g. risk for colorectal cancer) in the presence of multiple functional biomarkers while accounting for potential correlation. Our simulations show that the proposed approach achieves good performance in finite samples under various settings. In the presence of substantial or moderate correlation, the proposed approach outperforms an existing approach that does not account for correlation. The proposed approach is applied to a study of biomarkers of risk for colorectal neoplasms and our results show that the risk for colorectal cancer is associated with two functional biomarkers, APC and TGF-α, in particular, with their values in the region between the proliferating and differentiating zones of colorectal crypts.