In this study I analyzed the pattern of settlement for known Medio period (A.D. 1200–1450) sites in the Casas Grandes region of Chihuahua, Mexico. Locational data acquired from survey projects in the Casas Grandes region were evaluated within a Geographic Information Systems (GIS) framework to reveal patterns in settlement and site distribution. Environmental and cultural variables, including aspect, cost distance to nearest ballcourt, ecoregion, elevation, local relief, cost distance to nearest oven, cost distance to Paquimé, slope, soil, terrain texture, topographic position index, cost distance to nearest trincheras, vegetation, vegetation variety to 100 meters, vegetation variety to 500 meters, cost distance to nearest intermittent lake, cost distance to nearest intermittent stream, cost distance to nearest perennial lake, and cost distance to nearest perennial stream were calculated for each site in this region. It was expected that the relationships of correspondence between known sites and these variables would provide a quantitative framework that could be used to model the locational probability of unknown sites in the region. Through the use of GIS and statistical analyses, the results of this study were used to produce an archaeological site sensitivity map for this region of northern Mexico.

Slurry transport is a key material handling technology in a number of industries. In oilsands ore transport, slurry pipelining also promotes conditioning to release and aerate bitumen prior to separation. Reliability of slurry transport pipelines is a major ongoing problem for operating companies due to unexpected piping failures, even when conservative maintenance strategies are employed. To date, no accurate model has been developed to predict wear rates in slurry transport pipelines, although previous studies have shown that important variables include flow rate, slurry density, and particle size distribution. This work investigates erosion wear mechanisms causing inner pipe wall wear due to sand slurry flow in a horizontal section of pipe under steady state conditions. A corresponding lumped-parameter erosion wear model is presented based on simplification of the physics of oilsands slurry flow. An apparatus was designed and developed to measure the forces acting on the pipe inner wall to monitor forces related to erosion in a laboratory-scale sand slurry loop, and preliminary results are presented with recommendations for future work. / Engineering Management

Physiologically based pharmacokinetic (PBPK) modeling is a tool used in drug discovery and human health risk assessment. PBPK models are mathematical representations of the anatomy, physiology and biochemistry of an organism. PBPK models, using both compound and physiologic inputs, are used to predict a drug’s pharmacokinetics in various situations. Tissue to plasma partition coefficients (Kp), a key PBPK model input, define the steady state concentration differential between the tissue and plasma and are used to predict the volume of distribution. Experimental determination of these parameters once limited the development of PBPK models however in silico prediction methods were introduced to overcome this issue. The developed algorithms vary in input parameters and prediction accuracy and none are considered standard, warranting further research. Chapter 2 presents a newly developed Kp prediction algorithm that requires only readily available input parameters. Using a test dataset, this Kp prediction algorithm demonstrated good prediction accuracy and greater prediction accuracy than preexisting algorithms. Chapter 3 introduced a decision tree based Kp prediction method. In this novel approach, six previously published algorithms, including the one developed in Chapter 2, were utilized. The aim of the developed classifier was to identify the most accurate tissue-specific Kp prediction algorithm for a new drug. A dataset consisting of 122 drugs was used to train the classifier and identify the most accurate Kp prediction algorithm for a certain physico-chemical space. Three versions of tissue specific classifiers were developed and were dependent on the necessary inputs. The use of the classifier resulted in a better prediction accuracy as compared to the use of any single Kp prediction algorithm for all tissues; the current mode of use in PBPK model building. With built-in estimation equations for those input parameters not necessarily available, this Kp prediction tool will provide Kp prediction when only limited input parameters are available. The two presented innovative methods will improve tissue distribution prediction accuracy thus enhancing the confidence in PBPK modeling outputs.

The thesis examines sequential mining approaches in the context of treatment recommendation for Gliblastoma (GBM) patients. GBM is the most lethal and biologically the most aggressive forms of brain tumor with median survival of approximately 1 year. A significant challenge in treating such rare forms of cancer is to make the best decision about optimal treatment plans for patients after standard of care. We tailor the existing sequential mining approaches by adding constraints to mine significant treatment options for cancer patients. The goal of the work is to analyze which treatment patterns play a role in prolonging the survival period of patients. In addition to the treatment analysis, we also discover some interesting clinical and genomic factors, which influence the survival period of patients. A treatment advisor tool has been developed based on the predictive features discovered. This tool is used to recommend treatment guidelines for a new patient based on the treatments meted out to other patients sharing clinical similarity with the new patient. The recommendations are also guided by the influential treatment patterns discovered in the study. The tool is based on the notion of patient similarity and uses a weighted function to calculate the same. The recommendations made by the tool may influence the clinicians to have the patients record some vital data on their own. With the progression of the treatment the clinicians may want to add to or modify some of the vital data elements previously decided to be recorded. In such a case a static database would not be very efficient to record the data since manual intervention is inevitable to incorporate the changes in the database structure. To solve this problem we have developed a dynamic database evolution framework, which uses a form based interface to interact with the clinician to add or modify the data elements in a database. The clinicians are flexible to create a new form for patients or modify existing forms based on a patient’s condition. As a result, appropriate schema modifications would be done in the relational database at the backend to incorporate these changes maintaining relational consistency.

The initiatives of open space conservation, as outlined in the Sonoran Desert Conservation Plan, have been implemented through the purchase of nearly 65 thousand acres by Pima County. This land abuts sections of grazing leases held by state and federal agencies, forming largely unfragmented landscapes surrounding the city's urban core. Much of the outlying acreage is rural historic working ranches, now managed as open space conservation preserves. Ranches are landscapes of low-intensity impact, where the archaeological record of centuries of human land use is well preserved. Much of the land, however, remains relatively unstudied. To refine spatial predictions of archaeologically sensitive areas in southern Pima County, I use multivariate logistic regression to develop predictive models of probable archaeological site locations for three time periods at Rancho Seco as a case study. Results suggest portions Rancho Seco might contain additional Preceramic and Historic cultural resources but additional data collection is needed.

No description available.

Physiologically based pharmacokinetic (PBPK) modeling is a tool used in drug discovery and human health risk assessment. PBPK models are mathematical representations of the anatomy, physiology and biochemistry of an organism. PBPK models, using both compound and physiologic inputs, are used to predict a drug’s pharmacokinetics in various situations. Tissue to plasma partition coefficients (Kp), a key PBPK model input, define the steady state concentration differential between the tissue and plasma and are used to predict the volume of distribution. Experimental determination of these parameters once limited the development of PBPK models however in silico prediction methods were introduced to overcome this issue. The developed algorithms vary in input parameters and prediction accuracy and none are considered standard, warranting further research. Chapter 2 presents a newly developed Kp prediction algorithm that requires only readily available input parameters. Using a test dataset, this Kp prediction algorithm demonstrated good prediction accuracy and greater prediction accuracy than preexisting algorithms. Chapter 3 introduced a decision tree based Kp prediction method. In this novel approach, six previously published algorithms, including the one developed in Chapter 2, were utilized. The aim of the developed classifier was to identify the most accurate tissue-specific Kp prediction algorithm for a new drug. A dataset consisting of 122 drugs was used to train the classifier and identify the most accurate Kp prediction algorithm for a certain physico-chemical space. Three versions of tissue specific classifiers were developed and were dependent on the necessary inputs. The use of the classifier resulted in a better prediction accuracy as compared to the use of any single Kp prediction algorithm for all tissues; the current mode of use in PBPK model building. With built-in estimation equations for those input parameters not necessarily available, this Kp prediction tool will provide Kp prediction when only limited input parameters are available. The two presented innovative methods will improve tissue distribution prediction accuracy thus enhancing the confidence in PBPK modeling outputs.

INTRODUCTION: Abdominal pain and diarrhea are two of the most common pediatric complaints. They are often associated with a diagnosis of Crohn Disease or Ulcerative Colitis, collectively known as inflammatory bowel disease (IBD). IBD is set of diseases with ill-defined pathogenesis but similar clinical presentation. Clinicians rely on colonoscopic evaluation to distinguish between the two disorders, and the rate of colonoscopies has been increasing over the past several years. With the risks and costs associated with colonoscopic evaluation, our study sought to identify physiologic variables with significant predictive value in order to better determine those most likely to have an abnormal colonoscopy. Those variables could then be incorporated into a predictive model to stratify the risk of a patient having an abnormal colonoscopy and be used as a decision assist tool for physicians. METHODS: We conducted a retrospective cohort study examining 443 patients who underwent a colonoscopy between the years of 2012 and 2016 at Boston Children’s Hospital. Data on demographics, lab work, and stool studies was collected into an online database for three separate data sets. It was analyzed using SAS 9.4 and logistic regression was performed to identify four variables with the most predictive value relating to abnormal colonoscopy. Those variables were incorporated into a predictive model. RESULTS: Several variables were determined to be statistically significant in the prediction of abnormal colonoscopy. The four variables with the most predictive value based on calculated odds ratios were family history of IBD in a first-degree relative, serum albumin, fecal lactoferrin, and platelet count. When ROC curves were generated to validate the model using the four variables for each of the data sets, the area under the ROC curve was used to assess the robustness of the predictive model. The area under the curve (AUC) for the training data set was .81, the first validation set was .79, and the second validation set was .6. DISCUSSION: ROC curves were generated for each of the data sets in order to assess the predictive ability of the model, and the AUCS were calculated. An AUC of 1.0 would indicate a predictive model with perfect predictability. The AUC of the model building set at .81 and the first validation set at .79 are indicative of a predictive model with strong predictive value. The second validation set, used to assess the success of the model on an external data set, had an AUC of .6, which is less robust in its predictive value but is of more predictive utility than a coin flip. CONCLUSION: Logistic regression yielded a parsimonious model consisting of four variables with the strongest predictive value in terms of having an abnormal colonoscopy. The variables are metrics that are routinely collected as part of ambulatory and inpatient clinic visits. When the model was validated using an external data set, it did not perform as well as expected based on the results of the training and first validation set. If the robustness of the model can be improved when validated using an external data set, it could be of great clinical utility to physicians as a decision assist tool and help to limit the number of less clinically indicated colonoscopies being performed in the future.

abstract: 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. / Dissertation/Thesis / Doctoral Dissertation Biomedical Informatics 2017

This study examines the different skills necessary for PGA tour players to succeed at specific annual tournaments, in order to create a predictive model for DraftKings PGA contests. The model takes into account data from the PGA Tour ShotLink Intelligence Program. The predictive model is created each week based on past results from the specific tournament in question, with the hope of predicting a group of twenty-five players who should be successful based on their statistical profile. The results of the model are detailed in this paper, which covers the first nine weeks of the 2017 PGA Tour season, with a net profit of $45,070. Despite a positive profit there is not enough information to prove significance, so the model would need to be carried out for many more weeks to be conclusive. Ultimately, the study shows that each PGA Tour course is slightly different, which means certain players should be more successful at certain courses, which is valuable information for predicting future outcomes.