Analysis of Melanoma Onset: Assessing Familial Aggregation by Using Estimating Equations and Fitting Variance Components via Bayesian Random Effects Models

We investigate whether relative contributions of genetic and shared environmental factors are associated with an increased risk in melanoma. Data from the Queensland Familial Melanoma Project comprising 15,907 subjects arising from 1912 families were analyzed to estimate the additive genetic, common and unique environmental contributions to variation in the age at onset of melanoma. Two complementary approaches for analyzing correlated time-to-onset family data were considered: the generalized estimating equations (GEE) method in which one can estimate relationship-specific dependence simultaneously with regression coefficients that describe the average population response to changing covariates; and a subject-specific Bayesian mixed model in which heterogeneity in regression parameters is explicitly modeled and the different components of variation may be estimated directly. The proportional hazards and Weibull models were utilized, as both produce natural frameworks for estimating relative risks while adjusting for simultaneous effects of other covariates. A simple Markov Chain Monte Carlo method for covariate imputation of missing data was used and the actual implementation of the Bayesian model was based on Gibbs sampling using the free ware package BUGS. In addition, we also used a Bayesian model to investigate the relative contribution of genetic and environmental effects on the expression of naevi and freckles, which are known risk factors for melanoma.

Handling high level of censoring for endovascular aortic repair risk prediction

Feature selection is important in medical field for many reasons. However, selecting important variables is a difficult task with the presence of censoring that is a unique feature in survival data analysis. This paper proposed an approach to deal with the censoring problem in endovascular aortic repair survival data through Bayesian networks. It was merged and embedded with a hybrid feature selection process that combines cox's univariate analysis with machine learning approaches such as ensemble artificial neural networks to select the most relevant predictive variables. The proposed algorithm was compared with common survival variable selection approaches such as; least absolute shrinkage and selection operator LASSO, and Akaike information criterion AIC methods. The results showed that it was capable of dealing with high censoring in the datasets. Moreover, ensemble classifiers increased the area under the roc curves of the two datasets collected from two centers located in United Kingdom separately. Furthermore, ensembles constructed with center 1 enhanced the concordance index of center 2 prediction compared to the model built with a single network. Although the size of the final reduced model using the neural networks and its ensembles is greater than other methods, the model outperformed the others in both concordance index and sensitivity for center 2 prediction. This indicates the reduced model is more powerful for cross center prediction.

Risk Prediction for Epithelial Ovarian Cancer in 11 United States-Based Case-Control Studies: Incorporation of Epidemiologic Risk Factors and 17 Confirmed Genetic Loci.

Previously developed models for predicting absolute risk of invasive epithelial ovarian cancer have included a limited number of risk factors and have had low discriminatory power (area under the receiver operating characteristic curve (AUC) < 0.60). Because of this, we developed and internally validated a relative risk prediction model that incorporates 17 established epidemiologic risk factors and 17 genome-wide significant single nucleotide polymorphisms (SNPs) using data from 11 case-control studies in the United States (5,793 cases; 9,512 controls) from the Ovarian Cancer Association Consortium (data accrued from 1992 to 2010). We developed a hierarchical logistic regression model for predicting case-control status that included imputation of missing data. We randomly divided the data into an 80% training sample and used the remaining 20% for model evaluation. The AUC for the full model was 0.664. A reduced model without SNPs performed similarly (AUC = 0.649). Both models performed better than a baseline model that included age and study site only (AUC = 0.563). The best predictive power was obtained in the full model among women younger than 50 years of age (AUC = 0.714); however, the addition of SNPs increased the AUC the most for women older than 50 years of age (AUC = 0.638 vs. 0.616). Adapting this improved model to estimate absolute risk and evaluating it in prospective data sets is warranted.

Troponin I and cardiovascular risk prediction in the general population: the BiomarCaRE consortium

AIMS: Our aims were to evaluate the distribution of troponin I concentrations in population cohorts across Europe, to characterize the association with cardiovascular outcomes, to determine the predictive value beyond the variables used in the ESC SCORE, to test a potentially clinically relevant cut-off value, and to evaluate the improved eligibility for statin therapy based on elevated troponin I concentrations retrospectively.

METHODS AND RESULTS: Based on the Biomarkers for Cardiovascular Risk Assessment in Europe (BiomarCaRE) project, we analysed individual level data from 10 prospective population-based studies including 74 738 participants. We investigated the value of adding troponin I levels to conventional risk factors for prediction of cardiovascular disease by calculating measures of discrimination (C-index) and net reclassification improvement (NRI). We further tested the clinical implication of statin therapy based on troponin concentration in 12 956 individuals free of cardiovascular disease in the JUPITER study. Troponin I remained an independent predictor with a hazard ratio of 1.37 for cardiovascular mortality, 1.23 for cardiovascular disease, and 1.24 for total mortality. The addition of troponin I information to a prognostic model for cardiovascular death constructed of ESC SCORE variables increased the C-index discrimination measure by 0.007 and yielded an NRI of 0.048, whereas the addition to prognostic models for cardiovascular disease and total mortality led to lesser C-index discrimination and NRI increment. In individuals above 6 ng/L of troponin I, a concentration near the upper quintile in BiomarCaRE (5.9 ng/L) and JUPITER (5.8 ng/L), rosuvastatin therapy resulted in higher absolute risk reduction compared with individuals <6 ng/L of troponin I, whereas the relative risk reduction was similar.

CONCLUSION: In individuals free of cardiovascular disease, the addition of troponin I to variables of established risk score improves prediction of cardiovascular death and cardiovascular disease.

Common polygenic variation enhances risk prediction for Alzheimer's disease.

The identification of subjects at high risk for Alzheimer’s disease is important for prognosis and early intervention. We investigated the polygenic architecture of Alzheimer’s disease and the accuracy of Alzheimer’s disease prediction models, including and excluding the polygenic component in the model. This study used genotype data from the powerful dataset comprising 17 008 cases and 37 154 controls obtained from the International Genomics of Alzheimer’s Project (IGAP). Polygenic score analysis tested whether the alleles identified to associate with disease in one sample set were significantly enriched in the cases relative to the controls in an independent sample. The disease prediction accuracy was investigated in a subset of the IGAP data, a sample of 3049 cases and 1554 controls (for whom APOE genotype data were available) by means of sensitivity, specificity, area under the receiver operating characteristic curve (AUC) and positive and negative predictive values. We observed significant evidence for a polygenic component enriched in Alzheimer’s disease (P = 4.9 × 10−26). This enrichment remained significant after APOE and other genome-wide associated regions were excluded (P = 3.4 × 10−19). The best prediction accuracy AUC = 78.2% (95% confidence interval 77–80%) was achieved by a logistic regression model with APOE, the polygenic score, sex and age as predictors. In conclusion, Alzheimer’s disease has a significant polygenic component, which has predictive utility for Alzheimer’s disease risk and could be a valuable research tool complementing experimental designs, including preventative clinical trials, stem cell selection and high/low risk clinical studies. In modelling a range of sample disease prevalences, we found that polygenic scores almost doubles case prediction from chance with increased prediction at polygenic extremes.

Risk Prediction In Cardiovascular Epidemiology: Considerations for Modeling Composite Endpoints

Thesis (Master's)--University of Washington, 2016-08

Incorporating weather into regionwide safety planning prediction models

Predicting safety on roadways is standard practice for road safety professionals and has a corresponding extensive literature. The majority of safety prediction models are estimated using roadway segment and intersection (microscale) data, while more recently efforts have been undertaken to predict safety at the planning level (macroscale). Safety prediction models typically include roadway, operations, and exposure variables—factors known to affect safety in fundamental ways. Environmental variables, in particular variables attempting to capture the effect of rain on road safety, are difficult to obtain and have rarely been considered. In the few cases weather variables have been included, historical averages rather than actual weather conditions during which crashes are observed have been used. Without the inclusion of weather related variables researchers have had difficulty explaining regional differences in the safety performance of various entities (e.g. intersections, road segments, highways, etc.) As part of the NCHRP 8-44 research effort, researchers developed PLANSAFE, or planning level safety prediction models. These models make use of socio-economic, demographic, and roadway variables for predicting planning level safety. Accounting for regional differences - similar to the experience for microscale safety models - has been problematic during the development of planning level safety prediction models. More specifically, without weather related variables there is an insufficient set of variables for explaining safety differences across regions and states. Furthermore, omitted variable bias resulting from excluding these important variables may adversely impact the coefficients of included variables, thus contributing to difficulty in model interpretation and accuracy. This paper summarizes the results of an effort to include weather related variables, particularly various measures of rainfall, into accident frequency prediction and the prediction of the frequency of fatal and/or injury degree of severity crash models. The purpose of the study was to determine whether these variables do in fact improve overall goodness of fit of the models, whether these variables may explain some or all of observed regional differences, and identifying the estimated effects of rainfall on safety. The models are based on Traffic Analysis Zone level datasets from Michigan, and Pima and Maricopa Counties in Arizona. Numerous rain-related variables were found to be statistically significant, selected rain related variables improved the overall goodness of fit, and inclusion of these variables reduced the portion of the model explained by the constant in the base models without weather variables. Rain tends to diminish safety, as expected, in fairly complex ways, depending on rain frequency and intensity.

Development of accident prediction models for rural highway intersections

A study was done to develop macrolevel crash prediction models that can be used to understand and identify effective countermeasures for improving signalized highway intersections and multilane stop-controlled highway intersections in rural areas. Poisson and negative binomial regression models were fit to intersection crash data from Georgia, California, and Michigan. To assess the suitability of the models, several goodness-of-fit measures were computed. The statistical models were then used to shed light on the relationships between crash occurrence and traffic and geometric features of the rural signalized intersections. The results revealed that traffic flow variables significantly affected the overall safety performance of the intersections regardless of intersection type and that the geometric features of intersections varied across intersection type and also influenced crash type.

Methodology for developing real-time motorway traffic risk identification models using individual-vehicle data

Most of existing motorway traffic safety studies using disaggregate traffic flow data aim at developing models for identifying real-time traffic risks by comparing pre-crash and non-crash conditions. One of serious shortcomings in those studies is that non-crash conditions are arbitrarily selected and hence, not representative, i.e. selected non-crash data might not be the right data comparable with pre-crash data; the non-crash/pre-crash ratio is arbitrarily decided and neglects the abundance of non-crash over pre-crash conditions; etc. Here, we present a methodology for developing a real-time MotorwaY Traffic Risk Identification Model (MyTRIM) using individual vehicle data, meteorological data, and crash data. Non-crash data are clustered into groups called traffic regimes. Thereafter, pre-crash data are classified into regimes to match with relevant non-crash data. Among totally eight traffic regimes obtained, four highly risky regimes were identified; three regime-based Risk Identification Models (RIM) with sufficient pre-crash data were developed. MyTRIM memorizes the latest risk evolution identified by RIM to predict near future risks. Traffic practitioners can decide MyTRIM’s memory size based on the trade-off between detection and false alarm rates. Decreasing the memory size from 5 to 1 precipitates the increase of detection rate from 65.0% to 100.0% and of false alarm rate from 0.21% to 3.68%. Moreover, critical factors in differentiating pre-crash and non-crash conditions are recognized and usable for developing preventive measures. MyTRIM can be used by practitioners in real-time as an independent tool to make online decision or integrated with existing traffic management systems.

Corporate credit risk prediction under stochastic volatility and jumps

This paper examines the impact of allowing for stochastic volatility and jumps (SVJ) in a structural model on corporate credit risk prediction. The results from a simulation study verify the better performance of the SVJ model compared with the commonly used Merton model, and three sources are provided to explain the superiority. The empirical analysis on two real samples further ascertains the importance of recognizing the stochastic volatility and jumps by showing that the SVJ model decreases bias in spread prediction from the Merton model, and better explains the time variation in actual CDS spreads. The improvements are found particularly apparent in small firms or when the market is turbulent such as the recent financial crisis.

An evaluation of the effectiveness of Value-at-Risk (VaR) models for Australian banks under Basel III

This study compares Value-at-Risk (VaR) measures for Australian banks over a period that includes the Global Financial Crisis (GFC) to determine whether the methodology and parameter selection are important for capital adequacy holdings that will ultimately support a bank in a crisis period. VaR methodology promoted under Basel II was largely criticised during the GFC for its failure to capture downside risk. However, results from this study indicate that 1-year parametric and historical models produce better measures of VaR than models with longer time frames. VaR estimates produced using Monte Carlo simulations show a high percentage of violations but with lower average magnitude of a violation when they occur. VaR estimates produced by the ARMA GARCH model also show a relatively high percentage of violations, however, the average magnitude of a violation is quite low. Our findings support the design of the revised Basel II VaR methodology which has also been adopted under Basel III.

Eliciting and encoding expert knowledge on variable selection into classical or Bayesian species distribution models

The quality of species distribution models (SDMs) relies to a large degree on the quality of the input data, from bioclimatic indices to environmental and habitat descriptors (Austin, 2002). Recent reviews of SDM techniques, have sought to optimize predictive performance e.g. Elith et al., 2006. In general SDMs employ one of three approaches to variable selection. The simplest approach relies on the expert to select the variables, as in environmental niche models Nix, 1986 or a generalized linear model without variable selection (Miller and Franklin, 2002). A second approach explicitly incorporates variable selection into model fitting, which allows examination of particular combinations of variables. Examples include generalized linear or additive models with variable selection (Hastie et al. 2002); or classification trees with complexity or model based pruning (Breiman et al., 1984, Zeileis, 2008). A third approach uses model averaging, to summarize the overall contribution of a variable, without considering particular combinations. Examples include neural networks, boosted or bagged regression trees and Maximum Entropy as compared in Elith et al. 2006. Typically, users of SDMs will either consider a small number of variable sets, via the first approach, or else supply all of the candidate variables (often numbering more than a hundred) to the second or third approaches. Bayesian SDMs exist, with several methods for eliciting and encoding priors on model parameters (see review in Low Choy et al. 2010). However few methods have been published for informative variable selection; one example is Bayesian trees (O’Leary 2008). Here we report an elicitation protocol that helps makes explicit a priori expert judgements on the quality of candidate variables. This protocol can be flexibly applied to any of the three approaches to variable selection, described above, Bayesian or otherwise. We demonstrate how this information can be obtained then used to guide variable selection in classical or machine learning SDMs, or to define priors within Bayesian SDMs.