MUIDSI Comprehensive Exam — Measuring Geodiversity in Remotely-Sensed Imagery: Deep Spatial Change Detection Methods for Dataset Bias Mitigation and Visual Landscape Characterization

Amid explosive growth in availability of multimodal remotely sensed imagery (RSI) data from a constellation of overhead sensors, a lack of understanding persists concerning the actual content of these data sources, in particular the nature of spatial variation in the visual and contextual features in the landscape being imaged. Whether described as spatial domain shift, geographic feature variance or simply geodiversity, this gap of knowledge about RSI dataset content comes with important implications.  On one hand, there is a lack of tools to evaluate heterogeneity and representativeness of objects classes found in labeled RSI training datasets, in particular methods for regional…

Comprehensive Exam: Using subgroup discovery techniques to identify a high-risk group of suicide attempts among people with diabetes

In 2019, 37.3 million Americans had diabetes mellitus, and 1.2 million Americans aged 18 and older had attempted suicide in the past year. According to previous studies, people with type 1 diabetes were three to four times more likely to attempt suicide, and newly diagnosed with type 2 diabetes were two times more likely to attempt suicide when compared with the general population. However, understanding the relationship between suicide attempts and other risk factors for people with diabetes is still lacking. In medical research, the data mining technique has become a promising way to effectively analyze high-dimensional data by extracting…

Comprehensive Exam: Accelerating Data-Driven Discovery In Type 1 Diabetes:An Informatics-Based Approach

Type 1 diabetes (T1D) is an immune-associated or immune-mediated chronic disease characterized by the progressive failure or targeted destruction of insulin-producing beta (β) cells in the pancreas. Management of the disease is challenging, involving lifelong exogeneous insulin replacement and 24/7 blood glucose monitoring. Although more than 1.6 million Americans are living with T1D, most diabetes research is currently focused on type 2 diabetes (T2D), which accounts for approximately 90% of diabetes cases. The expanding availability, granularity, and size of real-world health data, however, is opening unprecedented opportunities to use health informatics to advance T1D research that is computationally innovative and responsive…

Computational Subgroups Stratification and Precision Drug Repositioning Using Explainable Artificial Intelligence

Enabling precision medicine requires developing robust patient stratification methods and identifying drugs tailored to homogeneous subgroups of patients from a heterogeneous population. Once discovering these subgroups, we can align patients and medications more specifically to achieve precision-based therapy. Developing de novo drugs is expensive and time-consuming with an ultimately low FDA approval rate. These limitations make developing new drugs for a small portion of a disease population unfeasible. Therefore, drug repositioning (DR) is an essential alternative for developing new drugs for a disease subpopulation. DR reduces the time, cost, and risk associated with a new drug. It is essential to develop data-driven approaches…

Comprehensive Exam Announcement – A Case-Control based Genomic Analysis of Chronic Obstructive Pulmonary Disease

Chronic Obstructive Pulmonary Disease (COPD) is a respiratory illness that affects millions of people all over the world. It is a major cause of chronic morbidity and mortality and a serious global public health problem. COPD is the fourth leading cause of death worldwide. Although the environmental causes of COPD which predominantly include cigarette smoking are well-documented, to this date the genetic underpinnings of COPD remain largely unknown. Furthermore, in the current landscape of a respiratory pandemic, COPD patients are at a much higher risk for developing other respiratory illnesses and co-morbidities. In this study we use genomic data from…

Thyroid Cancer Informatics

Survival prediction is important both to clinicians and patients; ensuring the best course of treatment is selected to manage the thyroid cancer. In 2018, there was an estimated half a million new thyroid cancer diagnoses and 41,071 deaths. Unlike other tumors whose mortality has decreased over the last two decades, thyroid cancer mortality rates have increased. Existing risk stratification systems fail to account for microcarcinomas, which accounted for 28.6 percent of thyroid cancer diagnoses and 32.5 percent of papillary thyroid cancer diagnoses. They are also based upon a varying combination of 10 variables and have not considered newly identified variables available in current research. Additionally,…

A Case-Control based Genomic Analysis of Chronic Obstructive Pulmonary Disease

Chronic Obstructive Pulmonary Disease (COPD) is a respiratory illness that affects millions of people all over the world. It is a major cause of chronic morbidity and mortality and a serious global public health problem. COPD is the fourth leading cause of death worldwide. Although the environmental causes of COPD which predominantly include cigarette smoking are well-documented, to this date the genetic underpinnings of COPD remain largely unknown. Furthermore, in the current landscape of a respiratory pandemic, COPD patients are at a much higher risk for developing other respiratory illnesses and co-morbidities. In this study we use genomic data from…

Using Big Data to Identify Possible External Risk Factors for Poorly Understood Cancers

Worldwide, cancer is the second leading cause of death (Cancer, 2012). There were 17 million new cases and 9.6 million cancer deaths worldwide in 2018, including approximately 1.7 million new U.S. cases and 600,000 U.S. cancer deaths (Cancer Facts & Figures 2018 | American Cancer Society, 2018; Worldwide Cancer Statistics, 2019). The worldwide incidence of cancer is expected to increase to 27.5 million per year by 2040 (Worldwide Cancer Statistics, 2019). The U.S. expects an increase to over 1.9 million new cases per year by 2020 due to an aging Caucasian population and a growing African American population (CDC – Expected New Cancer Cases and Deaths in…

An Evaluation of Physician Burnout by EMR Use Characterization and Correlation

Burnout disproportionately affects healthcare workers and continues to rise.  This condition potentially contributes to cost, quality and patient safety risk in an already overburdened United States healthcare system.  While the causes of burnout are complex, evidence exists pointing to Electronic Medical Record use (EMR) as one major contributor due to the increased clerical burden that decreases patient contact time and contributes to disruption for the provider.  The growth and consolidation of large-scale EMR vendors has given rise to enterprise-scale electronic medical records with workflows applied across disparate venues and specialties, further complicating the ability to optimize the physician EMR experience and leading…