Comparative effectiveness studies to improve clinical outcomes in end stage renal disease: the DEcIDE patient outcomes in end stage renal disease study.

BACKGROUND: Evidence is lacking to inform providers' and patients' decisions about many common treatment strategies for patients with end stage renal disease (ESRD). METHODS/DESIGN: The DEcIDE Patient Outcomes in ESRD Study is funded by the United States (US) Agency for Health Care Research and Quality to study the comparative effectiveness of: 1) antihypertensive therapies, 2) early versus later initiation of dialysis, and 3) intravenous iron therapies on clinical outcomes in patients with ESRD. Ongoing studies utilize four existing, nationally representative cohorts of patients with ESRD, including (1) the Choices for Healthy Outcomes in Caring for ESRD study (1041 incident dialysis patients recruited from October 1995 to June 1999 with complete outcome ascertainment through 2009), (2) the Dialysis Clinic Inc (45,124 incident dialysis patients initiating and receiving their care from 2003-2010 with complete outcome ascertainment through 2010), (3) the United States Renal Data System (333,308 incident dialysis patients from 2006-2009 with complete outcome ascertainment through 2010), and (4) the Cleveland Clinic Foundation Chronic Kidney Disease Registry (53,399 patients with chronic kidney disease with outcome ascertainment from 2005 through 2009). We ascertain patient reported outcomes (i.e., health-related quality of life), morbidity, and mortality using clinical and administrative data, and data obtained from national death indices. We use advanced statistical methods (e.g., propensity scoring and marginal structural modeling) to account for potential biases of our study designs. All data are de-identified for analyses. The conduct of studies and dissemination of findings are guided by input from Stakeholders in the ESRD community. DISCUSSION: The DEcIDE Patient Outcomes in ESRD Study will provide needed evidence regarding the effectiveness of common treatments employed for dialysis patients. Carefully planned dissemination strategies to the ESRD community will enhance studies' impact on clinical care and patients' outcomes.

R Markdown: Integrating A Reproducible Analysis Tool into Introductory Statistics

Nolan and Temple Lang argue that “the ability to express statistical computations is an es- sential skill.” A key related capacity is the ability to conduct and present data analysis in a way that another person can understand and replicate. The copy-and-paste workflow that is an artifact of antiquated user-interface design makes reproducibility of statistical analysis more difficult, especially as data become increasingly complex and statistical methods become increasingly sophisticated. R Markdown is a new technology that makes creating fully-reproducible statistical analysis simple and painless. It provides a solution suitable not only for cutting edge research, but also for use in an introductory statistics course. We present experiential and statistical evidence that R Markdown can be used effectively in introductory statistics courses, and discuss its role in the rapidly-changing world of statistical computation.

Real-Time and Data-Driven Operation Optimization and Knowledge Discovery for an Enterprise Information System

An enterprise information system (EIS) is an integrated data-applications platform characterized by diverse, heterogeneous, and distributed data sources. For many enterprises, a number of business processes still depend heavily on static rule-based methods and extensive human expertise. Enterprises are faced with the need for optimizing operation scheduling, improving resource utilization, discovering useful knowledge, and making data-driven decisions.

This thesis research is focused on real-time optimization and knowledge discovery that addresses workflow optimization, resource allocation, as well as data-driven predictions of process-execution times, order fulfillment, and enterprise service-level performance. In contrast to prior work on data analytics techniques for enterprise performance optimization, the emphasis here is on realizing scalable and real-time enterprise intelligence based on a combination of heterogeneous system simulation, combinatorial optimization, machine-learning algorithms, and statistical methods.

On-demand digital-print service is a representative enterprise requiring a powerful EIS.We use real-life data from Reischling Press, Inc. (RPI), a digit-print-service provider (PSP), to evaluate our optimization algorithms.

In order to handle the increase in volume and diversity of demands, we first present a high-performance, scalable, and real-time production scheduling algorithm for production automation based on an incremental genetic algorithm (IGA). The objective of this algorithm is to optimize the order dispatching sequence and balance resource utilization. Compared to prior work, this solution is scalable for a high volume of orders and it provides fast scheduling solutions for orders that require complex fulfillment procedures. Experimental results highlight its potential benefit in reducing production inefficiencies and enhancing the productivity of an enterprise.

We next discuss analysis and prediction of different attributes involved in hierarchical components of an enterprise. We start from a study of the fundamental processes related to real-time prediction. Our process-execution time and process status prediction models integrate statistical methods with machine-learning algorithms. In addition to improved prediction accuracy compared to stand-alone machine-learning algorithms, it also performs a probabilistic estimation of the predicted status. An order generally consists of multiple series and parallel processes. We next introduce an order-fulfillment prediction model that combines advantages of multiple classification models by incorporating flexible decision-integration mechanisms. Experimental results show that adopting due dates recommended by the model can significantly reduce enterprise late-delivery ratio. Finally, we investigate service-level attributes that reflect the overall performance of an enterprise. We analyze and decompose time-series data into different components according to their hierarchical periodic nature, perform correlation analysis,

and develop univariate prediction models for each component as well as multivariate models for correlated components. Predictions for the original time series are aggregated from the predictions of its components. In addition to a significant increase in mid-term prediction accuracy, this distributed modeling strategy also improves short-term time-series prediction accuracy.

In summary, this thesis research has led to a set of characterization, optimization, and prediction tools for an EIS to derive insightful knowledge from data and use them as guidance for production management. It is expected to provide solutions for enterprises to increase reconfigurability, accomplish more automated procedures, and obtain data-driven recommendations or effective decisions.

Evaluating marker-guided treatment selection strategies

© 2014, The International Biometric Society.A potential venue to improve healthcare efficiency is to effectively tailor individualized treatment strategies by incorporating patient level predictor information such as environmental exposure, biological, and genetic marker measurements. Many useful statistical methods for deriving individualized treatment rules (ITR) have become available in recent years. Prior to adopting any ITR in clinical practice, it is crucial to evaluate its value in improving patient outcomes. Existing methods for quantifying such values mainly consider either a single marker or semi-parametric methods that are subject to bias under model misspecification. In this article, we consider a general setting with multiple markers and propose a two-step robust method to derive ITRs and evaluate their values. We also propose procedures for comparing different ITRs, which can be used to quantify the incremental value of new markers in improving treatment selection. While working models are used in step I to approximate optimal ITRs, we add a layer of calibration to guard against model misspecification and further assess the value of the ITR non-parametrically, which ensures the validity of the inference. To account for the sampling variability of the estimated rules and their corresponding values, we propose a resampling procedure to provide valid confidence intervals for the value functions as well as for the incremental value of new markers for treatment selection. Our proposals are examined through extensive simulation studies and illustrated with the data from a clinical trial that studies the effects of two drug combinations on HIV-1 infected patients.

The Jama legal narrative. Part II: A foray into concepts of improbability

In judicial decision making, the doctrine of chances takes explicitly into account the odds. There is more to forensic statistics, as well as various probabilistic approaches which taken together form the object of an enduring controversy in the scholarship of legal evidence. In this paper, we reconsider the circumstances of the Jama murder and inquiry (dealt with in Part I of this paper: "The Jama Model. On Legal Narratives and Interpretation Patterns"), to illustrate yet another kind of probability or improbability. What is improbable about the Jama story, is actually a given, which contributes in terms of dramatic underlining. In literary theory, concepts of narratives being probable or improbable date back from the eighteenth century, when both prescientific and scientific probability was infiltrating several domains, including law. An understanding of such a backdrop throughout the history of ideas is, I claim, necessary for AI researchers who may be tempted to apply statistical methods to legal evidence. The debate for or against probability (and especially bayesian probability) in accounts of evidence has been flouishing among legal scholars. Nowadays both the the Bayesians (e.g. Peter Tillers) and Bayesioskeptics (e.g. Ron Allen) among those legal scholars whoare involved in the controversy are willing to give AI researchers a chance to prove itself and strive towards models of plausibility that would go beyond probability as narrowly meant. This debate within law, in turn, has illustrious precedents: take Voltaire, he was critical of the application or probability even to litigation in civil cases; take Boole, he was a starry-eyed believer in probability applications to judicial decision making (Rosoni 1995). Not unlike Boole, the founding father of computing, nowadays computer scientists approaching the field may happen to do so without full awareness of the pitfalls. Hence, the usefulness of the conceptual landscape I sketch here.

The Jama legal narrative part II: A foray into concepts of improbability

In judicial decision making, the doctrine of chances takes explicitly into account the odds. There is more to forensic statistics, as well as various probabilistic approaches, which taken together form the object of an enduring controversy in the scholarship of legal evidence. In this paper, I reconsider the circumstances of the Jama murder and inquiry (dealt with in Part I of this paper: 'The JAMA Model and Narrative Interpretation Patterns'), to illustrate yet another kind of probability or improbability. What is improbable about the Jama story is actually a given, which contributes in terms of dramatic underlining. In literary theory, concepts of narratives being probable or improbable date back from the eighteenth century, when both prescientific and scientific probability were infiltrating several domains, including law. An understanding of such a backdrop throughout the history of ideas is, I claim, necessary for Artificial Intelligence (AI) researchers who may be tempted to apply statistical methods to legal evidence. The debate for or against probability (and especially Bayesian probability) in accounts of evidence has been flourishing among legal scholars; nowadays both the Bayesians (e.g. Peter Tillers) and the Bayesio-skeptics (e.g. Ron Allen), among those legal scholars who are involved in the controversy, are willing to give AI research a chance to prove itself and strive towards models of plausibility that would go beyond probability as narrowly meant. This debate within law, in turn, has illustrious precedents: take Voltaire, he was critical of the application of probability even to litigation in civil cases; take Boole, he was a starry-eyed believer in probability applications to judicial decision making. Not unlike Boole, the founding father of computing, nowadays computer scientists approaching the field may happen to do so without full awareness of the pitfalls. Hence, the usefulness of the conceptual landscape I sketch here.

Modelling the effect of temperature on product reliability

Reliability of electronic parts is a major concern for many manufacturers, since early failures in the field can cost an enormous amount to repair - in many cases far more than the original cost of the product. A great deal of effort is expended by manufacturers to determine the failure rates for a process or the fraction of parts that will fail in a period of time. It is widely recognized that the traditional approach to reliability predictions for electronic systems are not suitable for today's products. This approach, based on statistical methods only, does not address the physics governing the failure mechanisms in electronic systems. This paper discusses virtual prototyping technologies which can predict the physics taking place and relate this to appropriate failure mechanisms. Simulation results illustrate the effect of temperature on the assembly process of an electronic package and the lifetime of a flip-chip package.

Computational approach for reliable and robust system-in-package design

A computational modelling approach integrated with optimisation and statistical methods that can aid the development of reliable and robust electronic packages and systems is presented. The design for reliability methodology is demonstrated for the design of a SiP structure. In this study the focus is on the procedure for representing the uncertainties in the package design parameters, their impact on reliability and robustness of the package design and how these can be included in the design optimisation modelling framework. The analysis of thermo-mechanical behaviour of the package is conducted using non-linear transient finite element simulations. Key system responses of interest, the fatigue life-time of the lead-free solder interconnects and warpage of the package, are predicted and used subsequently for design purposes. The design tasks are to identify the optimal SiP designs by varying several package input parameters so that the reliability and the robustness of the package are improved and in the same time specified performance criteria are also satisfied

Uncertainty analysis to minimise risk in designing micro-electronics manufacturing processes

A design methodology based on numerical modelling, integrated with optimisation techniques and statistical methods, to aid the process control of micro and nano-electronics based manufacturing processes is presented in this paper. The design methodology is demonstrated for a micro-machining process called Focused Ion Beam (FIB). This process has been modelled to help understand how a pre-defined geometry of micro- and nano- structures can be achieved using this technology. The process performance is characterised on the basis of developed Reduced Order Models (ROM) and are generated using results from a mathematical model of the Focused Ion Beam and Design of Experiment (DoE) methods. Two ion beam sources, Argon and Gallium ions, have been used to compare and quantify the process variable uncertainties that can be observed during the milling process. The evaluations of the process performance takes into account the uncertainties and variations of the process variables and are used to identify their impact on the reliability and quality of the fabricated structure. An optimisation based design task is to identify the optimal process conditions, by varying the process variables, so that certain quality objectives and requirements are achieved and imposed constraints are satisfied. The software tools used and developed to demonstrate the design methodology are also presented.

Optimisation methodology for risk mitigation in advanced micro-system electronics manufacturing

This paper presents a design methodology based on numerical modelling, integrated with optimisation techniques and statistical methods, to aid the development of new advanced technologies in the area of micro and nano systems. The design methodology is demonstrated for a micro-machining process called Focused Ion Beam (FIB). This process has been modelled to provide knowledge of how a pre-defined geometry can be achieved through this direct milling. The geometry characterisation is obtained using a Reduced Order Models (ROM), generated from the results of a mathematical model of the Focused Ion Beam, and Design of Experiment (DoE) methods. In this work, the focus is on the design flow methodology which includes an approach on how to include process parameter uncertainties into the process optimisation modelling framework. A discussion on the impact of the process parameters, and their variations, on the quality and performance of the fabricated structure is also presented. The design task is to identify the optimal process conditions, by altering the process parameters, so that certain reliability and confidence of the application is achieved and the imposed constraints are satisfied. The software tools used and developed to demonstrate the design methodology are also presented.

Parameterisation of bivalve functional traits for mechanistic eco-physiological dynamic energy budget (DEB) models

Mechanistic models such as those based on dynamic energy budget (DEB) theory are emergent ecomechanics tools to investigate the extent of fitness in organisms through changes in life history traits as explained by bioenergetic principles. The rapid growth in interest around this approach originates from the mechanistic characteristics of DEB, which are based on a number of rules dictating the use of mass and energy flow through organisms. One apparent bottleneck in DEB applications comes from the estimations of DEB parameters which are based on mathematical and statistical methods (covariation method). The parameterisation process begins with the knowledge of some functional traits of a target organism (e. g. embryo, sexual maturity and ultimate body size, feeding and assimilation rates, maintenance costs), identified from the literature or laboratory experiments. However, considering the prominent role of the mechanistic approach in ecology, the reduction of possible uncertainties is an important objective. We propose a revaluation of the laboratory procedures commonly used in ecological studies to estimate DEB parameters in marine bivalves. Our experimental organism was Brachidontes pharaonis. We supported our proposal with a validation exercise which compared life history traits as obtained by DEBs (implemented with parameters obtained using classical laboratory methods) with the actual set of species traits obtained in the field. Correspondence between the 2 approaches was very high (>95%) with respect to estimating both size and fitness. Our results demonstrate a good agreement between field data and model output for the effect of temperature and food density on age-size curve, maximum body size and total gamete production per life span. The mechanistic approach is a promising method of providing accurate predictions in a world that is under in creasing anthropogenic pressure.

Phenotypical characterization in "Plasmopara halstedii" (sunflower downy mildew) isolates of several races

Phenotypic variation (morphological and pathogenic characters), and genetic variability were studied in 50 isolates of seven Plasmopara halstedii (sunflower downy mildew) races 100, 300, 304, 314, 710, 704 and 714. There were significant morphological, aggressiveness, and genetic differences for pathogen isolates. However, there was no relationship between morphology of zoosporangia and sporangiophores and pathogenic and genetic characteristics for the races used in our study. Also, our results provided evidence that no relation between pathogenic traits and multilocus haplotypes may be established in P. halstedii. The hypothesis explaining the absence of relationships among phenotypic and genetic characteristics is discussed.

Pl2 resistance gene differentiates the pathogenicity in four "Plasmopara halstedii" (sunflower downy mildew) races 304, 704, 314 and 714

In order to clarify the role of Pl2 resistance gene in differentiation the pathogenicity in Plasmopara halstedii (sunflower downy mildew), analyses were carried out in four pathotypes: isolates of races 304 and 314 that do not overcome Pl2 gene, and isolates of races 704 and 714 that can overcome Pl2 gene. Based on the reaction for the P. halstedii isolates to sunflower hybrids varying only in Pl resistance genes, isolates of races 704 and 714 were more virulent than isolates of races 304 and 314. Index of aggressiveness was calculated for pathogen isolates and revealed the presence of significant differences between isolates of races 304 and 314 (more aggressive) and isolates of races 704 and 714 (less aggressive). There were morphological and genetic variations for the four P. halstedii isolates without a correlation with pathogenic diversity. The importance of the Pl2 resistance gene to differentiate the pathogenicity in sunflower downy mildew was discussed.

Environmental context explains Lévy and Brownian movement patterns of marine predators

An optimal search theory, the so-called Levy-flight foraging hypothesis(1), predicts that predators should adopt search strategies known as Levy flights where prey is sparse and distributed unpredictably, but that Brownian movement is sufficiently efficient for locating abundant prey(2-4). Empirical studies have generated controversy because the accuracy of statistical methods that have been used to identify Levy behaviour has recently been questioned(5,6). Consequently, whether foragers exhibit Levy flights in the wild remains unclear. Crucially, moreover, it has not been tested whether observed movement patterns across natural landscapes having different expected resource distributions conform to the theory's central predictions. Here we use maximum-likelihood methods to test for Levy patterns in relation to environmental gradients in the largest animal movement data set assembled for this purpose. Strong support was found for Levy search patterns across 14 species of open-ocean predatory fish (sharks, tuna, billfish and ocean sunfish), with some individuals switching between Levy and Brownian movement as they traversed different habitat types. We tested the spatial occurrence of these two principal patterns and found Levy behaviour to be associated with less productive waters (sparser prey) and Brownian movements to be associated with productive shelf or convergence-front habitats (abundant prey). These results are consistent with the Levy-flight foraging hypothesis(1,7), supporting the contention(8,9) that organism search strategies naturally evolved in such a way that they exploit optimal Levy patterns.

Xanthoria parietina as a biomonitor of airborne heavy metal pollution in forest sites in the North East of Morocco

Xanthoria parietina, common foliose lichen, growing in its natural habitat, was analysed for the concentration of five heavy metals (Fe, Cr, Zn, Pb and Cu) from different forest sites of North East of Morocco (Kenitra, Sidi Boughaba, Mkhinza, Ceinture Verte near Temara city, Skhirate, Bouznika and Mohammedia). The quantification was carried out by inductively coupled plasma - atomic emission spectrometry (ICP-AES). Results were highly significant p<0,001. The concentration of metals is correlated with the vehicular activity and urbanization. The total metal concentration is highest at the Kenitra area, followed by Ceinture Verte site near Temara city, which experience heavy traffic throughout the year. Scanning electron microscopy (SEM) of particulate matter on lichen of Xanthoria parietina was assessed as a complementary technique to wet chemical analysis for source apportionment of airborne contaminant. Analysis revealed high level of Cu, Cr, Zn and Pb in samples near roads.