Engineering Commons^™

Mining High Impact Combinations Of Conditions From The Medical Expenditure Panel Survey, Arjun Mohan

Masters Theses

The condition of multimorbidity — the presence of two or more medical conditions in an individual — is a growing phenomenon worldwide. In the United States, multimorbid patients represent more than a third of the population and the trend is steadily increasing in an already aging population. There is thus a pressing need to understand the patterns in which multimorbidity occurs, and to better understand the nature of the care that is required to be provided to such patients.

In this thesis, we use data from the Medical Expenditure Panel Survey (MEPS) from the years 2011 to 2015 to identify …

A Machine Learning Approach For Predicting Clinical Trial Patient Enrollment In Drug Development Portfolio Demand Planning, Ahmed Shoieb

Masters Theses

One of the biggest challenges the clinical research industry currently faces is the accurate forecasting of patient enrollment (namely if and when a clinical trial will achieve full enrollment), as the stochastic behavior of enrollment can significantly contribute to delays in the development of new drugs, increases in duration and costs of clinical trials, and the over- or under- estimation of clinical supply. This study proposes a Machine Learning model using a Fully Convolutional Network (FCN) that is trained on a dataset of 100,000 patient enrollment data points including patient age, patient gender, patient disease, investigational product, study phase, blinded …

Markov Decision Process Approach To Strategize National Breast Cancer Screening Policy In Data-Limited Settings, Vijeta Deshpande

Masters Theses

Early diagnosis is a promising strategy to reduce premature mortalities and for optimal use of resources. But the absence of mathematical models specific to the data settings in LMIC’s impedes the construction of economic analysis necessary for decision-makers in the development of cancer control programs. This thesis presents a new methodology for parameterizing the natural history model of breast cancer based on data availabilities in low and middle income countries, and formulation of a control optimization problem to find the optimal screening schedule for mammography screening, solved using dynamic programming. As harms and benefits are known to increase with the …

A Computational Simulation Model For Predicting Infectious Disease Spread Using The Evolving Contact Network Algorithm, Buyannemekh Munkhbat

Masters Theses

Commonly used simulation models for predicting outbreaks of re-emerging infectious diseases (EIDs) take an individual-level or a population-level approach to modeling contact dynamics. These approaches are a trade-off between the ability to incorporate individual-level dynamics and computational efficiency. Agent-based network models (ABNM) use an individual-level approach by simulating the entire population and its contact structure, which increases the ability of adding detailed individual-level characteristics. However, as this method is computationally expensive, ABNMs use scaled-down versions of the full population, which are unsuitable for low prevalence diseases as the number of infected cases would become negligible during scaling-down. Compartmental models use …

Evaluating The Toxicity And Formation Of Halobenzoquinones In Point-Of-Use Chlorinated Drinking Water, Stephanie Hung

Masters Theses

Chlorine has effectively reduced the prevalence of waterborne diseases, however there are secondary consequences to this public health advancement. Disinfection byproducts (DBPs) are chemicals formed when chlorine reacts with natural organic matter (NOM) in water. A new class of DBPs, halobenzoquinones (HBQs), has recently been identified and data suggests it could be potentially carcinogenic and up to 1000 times more toxic than some regulated DBPs. So far, in vitro studies have assessed HBQ toxicity without taking into account its transformation in cell media into potentially less toxic compounds. This study evaluated the toxic effects of one HBQ, 2,6-DCBQ, and its …

A Feasibility Study Of Just-In-Time Asthma Self-Management Intervention, Phillip Charles Scruggs

Masters Theses

Quality asthma care requires not only an initial diagnosis, but long term follow up care and education on long term control. Preventable symptoms continue to reduce the quality of life for chronic asthma sufferers and place an unnecessary burden on emergency services and the health care system at large. A mobile health (mHealth) solution is proposed to effectively improve outcomes for patients while ultimately reducing the overall burden of mismanagement on the healthcare system as a whole. The Just-in-Time Asthma Self- Management and Intervention (JASMIN) system provides a way for a patient or user to track, self-manage, and interact with …

A Decision Support Simulation Model For Bed Management In Healthcare, Raja A. Baru

Masters Theses

"In order to provide access to care in a timely manner, it is necessary to effectively manage the allocation of limited resources such as beds. Bed management is key to the effective delivery of high-quality and low-cost healthcare. An efficient utilization of beds requires a detailed understanding of the hospital's operational behavior. It is necessary to understand the behavior of a hospital in order to make necessary adjustments to its resources, and policies, which can improve patient's access to care. The aim of this research was to develop a discrete event simulation to assist in planning and staff scheduling decisions. …