Matching Items (4)
Filtering by
- All Subjects: Biostatistics
- Creators: Dinu, Valentin
Description
This work involved the analysis of a public health system, and the design, development and deployment of enterprise informatics architecture, and sustainable community methods to address problems with the current public health system. Specifically, assessment of the Nationally Notifiable Disease Surveillance System (NNDSS) was instrumental in forming the design of the current implementation at the Southern Nevada Health District (SNHD). The result of the system deployment at SNHD was considered as a basis for projecting the practical application and benefits of an enterprise architecture. This approach has resulted in a sustainable platform to enhance the practice of public health by improving the quality and timeliness of data, effectiveness of an investigation, and reporting across the continuum.
ContributorsKriseman, Jeffrey Michael (Author) / Dinu, Valentin (Thesis advisor) / Greenes, Robert (Committee member) / Johnson, William (Committee member) / Arizona State University (Publisher)
Created2012
Description
The living world we inhabit and observe is extraordinarily complex. From the perspective of a person analyzing data about the living world, complexity is most commonly encountered in two forms: 1) in the sheer size of the datasets that must be analyzed and the physical number of mathematical computations necessary to obtain an answer and 2) in the underlying structure of the data, which does not conform to classical normal theory statistical assumptions and includes clustering and unobserved latent constructs. Until recently, the methods and tools necessary to effectively address the complexity of biomedical data were not ordinarily available. The utility of four methods--High Performance Computing, Monte Carlo Simulations, Multi-Level Modeling and Structural Equation Modeling--designed to help make sense of complex biomedical data are presented here.
ContributorsBrown, Justin Reed (Author) / Dinu, Valentin (Thesis advisor) / Johnson, William (Committee member) / Petitti, Diana (Committee member) / Arizona State University (Publisher)
Created2012
Description
Immunosignaturing is a technology that allows the humoral immune response to be observed through the binding of antibodies to random sequence peptides. The immunosignaturing microarray is based on complex mixtures of antibodies binding to arrays of random sequence peptides in a multiplexed fashion. There are computational and statistical challenges to the analysis of immunosignaturing data. The overall aim of my dissertation is to develop novel computational and statistical methods for immunosignaturing data to access its potential for diagnostics and drug discovery. Firstly, I discovered that a classification algorithm Naive Bayes which leverages the biological independence of the probes on our array in such a way as to gather more information outperforms other classification algorithms due to speed and accuracy. Secondly, using this classifier, I then tested the specificity and sensitivity of immunosignaturing platform for its ability to resolve four different diseases (pancreatic cancer, pancreatitis, type 2 diabetes and panIN) that target the same organ (pancreas). These diseases were separated with >90% specificity from controls and from each other. Thirdly, I observed that the immunosignature of type 2 diabetes and cardiovascular complications are unique, consistent, and reproducible and can be separated by 100% accuracy from controls. But when these two complications arise in the same person, the resultant immunosignature is quite different in that of individuals with only one disease. I developed a method to trace back from informative random peptides in disease signatures to the potential antigen(s). Hence, I built a decipher system to trace random peptides in type 1 diabetes immunosignature to known antigens. Immunosignaturing, unlike the ELISA, has the ability to not only detect the presence of response but also absence of response during a disease. I observed, not only higher but also lower peptides intensities can be mapped to antigens in type 1 diabetes. To study immunosignaturing potential for population diagnostics, I studied effect of age, gender and geographical location on immunosignaturing data. For its potential to be a health monitoring technology, I proposed a single metric Coefficient of Variation that has shown potential to change significantly when a person enters a disease state.
ContributorsKukreja, Muskan (Author) / Johnston, Stephen Albert (Thesis advisor) / Stafford, Phillip (Committee member) / Dinu, Valentin (Committee member) / Arizona State University (Publisher)
Created2012
Description
Random forest (RF) is a popular and powerful technique nowadays. It can be used for classification, regression and unsupervised clustering. In its original form introduced by Leo Breiman, RF is used as a predictive model to generate predictions for new observations. Recent researches have proposed several methods based on RF for feature selection and for generating prediction intervals. However, they are limited in their applicability and accuracy. In this dissertation, RF is applied to build a predictive model for a complex dataset, and used as the basis for two novel methods for biomarker discovery and generating prediction interval.
Firstly, a biodosimetry is developed using RF to determine absorbed radiation dose from gene expression measured from blood samples of potentially exposed individuals. To improve the prediction accuracy of the biodosimetry, day-specific models were built to deal with day interaction effect and a technique of nested modeling was proposed. The nested models can fit this complex data of large variability and non-linear relationships.
Secondly, a panel of biomarkers was selected using a data-driven feature selection method as well as handpick, considering prior knowledge and other constraints. To incorporate domain knowledge, a method called Know-GRRF was developed based on guided regularized RF. This method can incorporate domain knowledge as a penalized term to regulate selection of candidate features in RF. It adds more flexibility to data-driven feature selection and can improve the interpretability of models. Know-GRRF showed significant improvement in cross-species prediction when cross-species correlation was used to guide selection of biomarkers. The method can also compete with existing methods using intrinsic data characteristics as alternative of domain knowledge in simulated datasets.
Lastly, a novel non-parametric method, RFerr, was developed to generate prediction interval using RF regression. This method is widely applicable to any predictive models and was shown to have better coverage and precision than existing methods on the real-world radiation dataset, as well as benchmark and simulated datasets.
Firstly, a biodosimetry is developed using RF to determine absorbed radiation dose from gene expression measured from blood samples of potentially exposed individuals. To improve the prediction accuracy of the biodosimetry, day-specific models were built to deal with day interaction effect and a technique of nested modeling was proposed. The nested models can fit this complex data of large variability and non-linear relationships.
Secondly, a panel of biomarkers was selected using a data-driven feature selection method as well as handpick, considering prior knowledge and other constraints. To incorporate domain knowledge, a method called Know-GRRF was developed based on guided regularized RF. This method can incorporate domain knowledge as a penalized term to regulate selection of candidate features in RF. It adds more flexibility to data-driven feature selection and can improve the interpretability of models. Know-GRRF showed significant improvement in cross-species prediction when cross-species correlation was used to guide selection of biomarkers. The method can also compete with existing methods using intrinsic data characteristics as alternative of domain knowledge in simulated datasets.
Lastly, a novel non-parametric method, RFerr, was developed to generate prediction interval using RF regression. This method is widely applicable to any predictive models and was shown to have better coverage and precision than existing methods on the real-world radiation dataset, as well as benchmark and simulated datasets.
ContributorsGuan, Xin (Author) / Liu, Li (Thesis advisor) / Runger, George C. (Thesis advisor) / Dinu, Valentin (Committee member) / Arizona State University (Publisher)
Created2017