Medicine and Health Sciences Commons^™

Connectivity Differences Between Gulf War Illness (Gwi) Phenotypes During A Test Of Attention, Tomas Clarke, Jessie Jamieson, Patrick Malone, Rakib U. Rayhan, Stuart Washington, John W. Vanmeter, James N. Baraniuk

Department of Mathematics: Faculty Publications

One quarter of veterans returning from the 1990–1991 Persian Gulf War have developed Gulf War Illness (GWI) with chronic pain, fatigue, cognitive and gastrointestinal dysfunction. Exertion leads to characteristic, delayed onset exacerbations that are not relieved by sleep. We have modeled exertional exhaustion by comparing magnetic resonance images from before and after submaximal exercise. One third of the 27 GWI participants had brain stem atrophy and developed postural tachycardia after exercise (START: Stress Test Activated Reversible Tachycardia). The remainder activated basal ganglia and anterior insulae during a cognitive task (STOPP: Stress Test Originated Phantom Perception). Here, the role of attention …

Enhancing Clinical Concept Extraction With Contextual Embeddings., Yuqi Si, Jingqi Wang, Hua Xu, Kirk Roberts

Student and Faculty Publications

OBJECTIVE: Neural network-based representations ("embeddings") have dramatically advanced natural language processing (NLP) tasks, including clinical NLP tasks such as concept extraction. Recently, however, more advanced embedding methods and representations (eg, ELMo, BERT) have further pushed the state of the art in NLP, yet there are no common best practices for how to integrate these representations into clinical tasks. The purpose of this study, then, is to explore the space of possible options in utilizing these new models for clinical concept extraction, including comparing these to traditional word embedding methods (word2vec, GloVe, fastText).

MATERIALS AND METHODS: Both off-the-shelf, open-domain embeddings and …

Enhancing Timeliness Of Drug Overdose Mortality Surveillance: A Machine Learning Approach, Patrick J. Ward, Peter J. Rock, Svetla Slavova, April M. Young, Terry L. Bunn, Ramakanth Kavuluru

Kentucky Injury Prevention and Research Center Faculty Publications

BACKGROUND: Timely data is key to effective public health responses to epidemics. Drug overdose deaths are identified in surveillance systems through ICD-10 codes present on death certificates. ICD-10 coding takes time, but free-text information is available on death certificates prior to ICD-10 coding. The objective of this study was to develop a machine learning method to classify free-text death certificates as drug overdoses to provide faster drug overdose mortality surveillance.

METHODS: Using 2017–2018 Kentucky death certificate data, free-text fields were tokenized and features were created from these tokens using natural language processing (NLP). Word, bigram, and trigram features were created …

An Analysis Of The Rajasthan Public Health System’S Response To The 2019 Dengue Insurgence, Luke Bryan

Independent Study Project (ISP) Collection

Dengue virus is in a pandemic status and is a major public health issue in the modern world. The mosquito-borne disease is largely prevalent in Asia and specifically India, where more than half of the states are considered to have complete presence of the dengue virus. The intricate infrastructure of the Indian public health system looks for dengue cases at all levels and reports to the integrated disease surveillance programme (IDSP).

Analyses of the IDSP and trends of dengue cases was done in response to dengue outbreaks throughout the state. Geographic information system (GIS) maps were created to evaluate a …

Advances In Gene Ontology Utilization Improve Statistical Power Of Annotation Enrichment, Eugene Waverly Hinderer Iii, Robert M. Flight, Rashmi Dubey, James N. Macleod, Hunter N. B. Moseley

Maxwell H. Gluck Equine Research Center Faculty Publications

Gene-annotation enrichment is a common method for utilizing ontology-based annotations in gene and gene-product centric knowledgebases. Effective utilization of these annotations requires inferring semantic linkages by tracing paths through edges in the ontological graph, referred to as relations. However, some relations are semantically problematic with respect to scope, necessitating their omission or modification lest erroneous term mappings occur. To address these issues, we created the Gene Ontology Categorization Suite, or GOcats—a novel tool that organizes the Gene Ontology into subgraphs representing user-defined concepts, while ensuring that all appropriate relations are congruent with respect to scoping semantics. Here, we demonstrate the …

Biological Pathway Involvement In Melanoma Heterogeneity And Drug-Induced Resistance, Sarah V. Pack

STAR Program Research Presentations

Tumors develop resistance to numerous drug therapies, and this remains a major obstacle in treating many types of non-surgical cancers. Melanoma provides a good model system for studying drug resistance in cancer due to its high propensity to incur resistance after a significant initial response to a drug. Genes that are highly expressed in melanoma cancer cells have been studied, but in order to further understand the collective function of these highly expressed genes we must analyze gene sets, or pathways. A single gene’s function is rarely independent of other genes, and pathway analysis takes this into account.

Our objective …

Rising Rural Body-Mass Index Is The Main Driver Of The Global Obesity Epidemic In Adults, Con Burns, Tara Coppinger, Janette Walton, Et Al

Publications

Body-mass index (BMI) has increased steadily in most countries in parallel with a rise in the proportion of the population who live in cities1,2. This has led to a widely reported view that urbanization is one of the most important drivers of the global rise in obesity3,4,5,6. Here we use 2,009 population-based studies, with measurements of height and weight in more than 112 million adults, to report national, regional and global trends in mean BMI segregated by place of residence (a rural or urban area) from 1985 to …

Supervised Dimension Reduction For Large-Scale "Omics" Data With Censored Survival Outcomes Under Possible Non-Proportional Hazards, Lauren Spirko-Burns, Karthik Devarajan

COBRA Preprint Series

The past two decades have witnessed significant advances in high-throughput ``omics" technologies such as genomics, proteomics, metabolomics, transcriptomics and radiomics. These technologies have enabled simultaneous measurement of the expression levels of tens of thousands of features from individual patient samples and have generated enormous amounts of data that require analysis and interpretation. One specific area of interest has been in studying the relationship between these features and patient outcomes, such as overall and recurrence-free survival, with the goal of developing a predictive ``omics" profile. Large-scale studies often suffer from the presence of a large fraction of censored observations and potential …

Impact Of The Affordable Care Act On Colorectal Cancer Screening, Incidence, And Survival In Kentucky, Tong Gan, Heather F. Sinner, Samuel C. Walling, Quan Chen, Bin Huang, Thomas C. Tucker, Jitesh A. Patel, B. Mark Evers, Avinash S. Bhakta

Surgery Faculty Publications

Background

Kentucky ranks first in the US in cancer incidence and mortality. Compounded by high poverty levels and a high rate of medically uninsured, cancer rates are even worse in Appalachian Kentucky. Being one of the first states to adopt the Affordable Care Act (ACA) Medicaid expansion, insurance coverage markedly increased for Kentucky residents. The purpose of our study was to determine the impact of Medicaid expansion on colorectal cancer (CRC) screening, diagnosis, and survival in Kentucky.

Study Design

The Kentucky Cabinet for Health and Family Services and the Kentucky Cancer Registry were queried for individuals (≥20 years) undergoing CRC …

Radiation Dose Estimation By Completely Automated Interpretation Of The Dicentric Chromosome Assay, Peter Rogan, Yanxin Li, Ben Shirley, Ruth Wilkins, Farrah Norton, Joan Knoll

Biochemistry Publications

Accuracy of the automated dicentric chromosome (DC) assay relies on metaphase image selection. This study validates a software framework to find the best image selection models that mitigate inter-sample variability. Evaluation methods to determine model quality include the Poisson goodness-of-fit of DC distributions for each sample, residuals after calibration curve fitting and leave-one-out dose estimation errors. The process iteratively searches a pool of selection model candidates by modifying statistical and filter cut-offs to rank the best candidates according to their respective evaluation scores. Evaluation scores minimize the sum of squared errors relative to the actual radiation dose of the calibration …

Data Collection Curated With An Application Ontology Describes The Methods And Results Upon Performing An Ex-Vivo Voltage-Clamp Assay On Outer Hair Cells Of The Mammalian Cochlea, Brenda Farrell, Jason Bengtson

Research Data

This data collection describes the electrical properties of outer hair cells isolated from the mammalian cochlea of the domestic guinea pig. This data was obtained by performing whole-cell patch clamp voltage clamp assay on cells and monitoring the electrical admittance during a DC voltage ramp. The membrane capacitance was then calculated at each membrane potential from this admittance, and the voltage-independent and voltage-dependent membrane capacitance was determined upon further analysis. In some case the DC conductance was also measured by interrogation of the cell with voltage-step function which was calculated from the change in the mean steady-state current with respect …

Deep Patient Representation Of Clinical Notes Via Multi-Task Learning For Mortality Prediction., Yuqi Si, Kirk Roberts

Student and Faculty Publications

We propose a deep learning-based multi-task learning (MTL) architecture focusing on patient mortality predictions from clinical notes. The MTL framework enables the model to learn a patient representation that generalizes to a variety of clinical prediction tasks. Moreover, we demonstrate how MTL enables small but consistent gains on a single classification task (e.g., in-hospital mortality prediction) simply by incorporating related tasks (e.g., 30-day and 1-year mortality prediction) into the MTL framework. To accomplish this, we utilize a multi-level Convolutional Neural Network (CNN) associated with a MTL loss component. The model is evaluated with 3, 5, and 20 tasks and is …