Digital Commons Network^™

A Comparative Study Of Recent Large Language Models On Generating Hospital Discharge Summaries For Lung Cancer Patients, Yiming Li, Fang Li, Na Hong, Manqi Li, Kirk Roberts, Licong Cui, Cui Tao, Hua Xu

Faculty, Staff and Student Publications

Objective: Generating discharge summaries is a crucial yet time-consuming task in clinical practice, essential for conveying pertinent patient information and facilitating continuity of care. Recent advancements in large language models (LLMs) have significantly enhanced their capability in understanding and summarizing complex medical texts. This research aims to explore how LLMs can alleviate the burden of manual summarization, streamline workflow efficiencies, and support informed decision-making in healthcare settings.

Materials and methods: Clinical notes from a cohort of 1,099 lung cancer patients were utilized, with a subset of 50 patients for testing purposes, and 102 patients used for model fine-tuning. This study …

Using Genai And Blockchain For Enhanced User Experience In Metaverse-Based Therapy Sessions, Diana Hawashin, Khaled Salah, Raja Jayaraman, Samer Ellaham, Ibrar Yaqoob

Industrial Engineering: Faculty & Staff Publications

As awareness of mental health issues rises, the demand for accessible and effective therapy becomes more urgent. However, existing digital therapy platforms fall short of providing personalization and real-time interaction, often leading to generic and ineffective responses that fail to meet individual psychological needs. These platforms rely on costly therapists or inadequately trained assistants, which limits their effectiveness. Additionally, the centralized systems used to manage therapy sessions lack adequate traceability, trust, and security, which are critical for users' confidence in the process. In this paper, we present a blockchain-based solution integrated with Generative Artificial Intelligence (GenAI) to deliver superior Metaverse-based …

Is R&D Rivalry Slowing The Growth Of Productive Firms?, Yoshiki Ando, James Bessen, Xiupeng Wang

Faculty Scholarship

The reallocation of jobs to more productive firms is a substantial component of aggregate productivity growth, yet job reallocation rates have declined substantially in the United States. This paper explores the hypothesis that greater technological rivalry has exacerbated adjustment costs, slowing reallocation. Using microdata at the US Census and estimates of technological rivalry in firm growth regressions, we find that technological rivalry slows firm responses to productivity shocks. Firms do not expand as rapidly in the face of higher obsolescence risk. Estimating counterfactual firm growth from 1997-2018, we find that growing technological rivalry accounts for most of the decline in …

Outcomes And Resource Utilization In Hyperkalemic Emergency Department Patients Treated With Patiromer Or Sodium Zirconium Cyclosilicate., William Frank Peacock, Zubaid Rafique, Julie Gayle, James Neuenschwander, Harold Brown, Jennifer Kammerer, Jeffrey Budden, Ning Rosenthal

Ambulatory and Primary Care Articles

OBJECTIVES: Hyperkalemia (HK) is a life-threatening condition commonly treated in emergency department (ED). Real-world outcomes associated with ED administration of potassium binders are limited. This study assessed ED discharge disposition and resource utilization in hyperkalemic ED patients treated with patiromer or sodium zirconium cyclosilicate (SZC).

METHODS: We performed a retrospective cohort study using discharge data from 230 hospitals in the Premier PINC AI Healthcare Database. ED patients were included if they were ≥18 years old, had potassium ≥5 mEq/L, and received patiromer/SZC during January 1, 2019 to December 31, 2021. Descriptive statistics and multivariable logistic regression analysis were used to …

Remote Detection Of Pest Damage And Tree Health In Tart Cherry, Christina Klara Lilligren

All Graduate Theses and Dissertations, Fall 2023 to Present

With the increasing affordability of technology, using technological advancements to assess tree health might soon become a possibility in low input crops such as tart cherry. We evaluated the ability of drone-mounted multispectral cameras, ceptometry

(canopy density), and soil conductivity meters (soil texture) to predict pest occurrence and remotely detect tree health. Pest scouting data were compared to the different technological datasets to identify the possibility of use for pest detection. While drone-mounted multispectral cameras were able to identify chlorotic trees, powdery mildew was not reliably detectable under a management threshold with current multispectral camera technology. Trees with low canopy …

Unwritten Rules: Black Utahns’ Experience With De Facto Segregation In Utah, 1940-1965, Jasmine Mercedes Lowe

All Graduate Theses and Dissertations, Fall 2023 to Present

This thesis examines life in Utah during the Jim Crow era, utilizing oral history interviews with African Americans who lived in the state between 1940 and 1965. The interviewees selected for this project describe their personal experiences with housing, employment, public spaces, medical assistance, and education discrimination.

Unveiling Insights From Complexity: Advanced Computational Techniques For High-Dimensional Medical Data, Devin P. Eddington

All Graduate Theses and Dissertations, Fall 2023 to Present

Healthcare generates vast amounts of data daily, from genetic profiles to hospital records, but much of it remains untapped due to its complexity. This dissertation develops new computational tools to unlock this data’s potential, aiming to improve patient care and medical research. Five projects tackle different challenges: Project 1 creates Deep MAGIC, a method to fill in missing genetic and image data accurately, vital for understanding diseases like cancer. Project 2 analyzes how the COVID-19 pandemic disrupted surgeries, finding a 27% drop and temporary complication rises in 2020, guiding future crisis planning. Projects 3 and 4 study kidney disease trials, …

Precision Agriculture Applications In Tart Cherries: Yield Mapping Technologies And Remote Sensing For Water Stress Estimation, Anderson Luiz Dos Santos Safre

All Graduate Theses and Dissertations, Fall 2023 to Present

Tart cherry is an important specialty crop in the United States, particularly in Utah where the area dedicated to tart cherry cultivation is larger than any other fruit grown in the state. However, growers face increasing challenges due to rising land prices, limited water availability, and extreme weather events. These factors make it essential to adopt new technologies that improve efficiency and sustainability. Precision agriculture, which uses data-driven tools to manage crops more effectively, can help address these challenges. However, most tart cherry orchards still rely on traditional practices due to a lack of specialized technologies for this crop. This …

The Scintillator Surface Detector Of The Pierre Auger Observatory, A. Abdul Halim, P. Abreu, M. Aglietta, I. Allekotte, K. Almeida Cheminant, A. Almela, B. Fick, K. Nguyen, D. Nitz, Et Al.

Michigan Tech Publications

Data collected so far by the Pierre Auger Observatory have enabled major advances in ultrahigh energy cosmic ray physics and demonstrated that improved determination of masses of primary cosmic-ray particles, preferably on an event-by-event basis, is necessary for understanding their origin and nature. Improvement in primary mass measurements was the main motivation for the upgrade of the Pierre Auger Observatory, called AugerPrime. As part of this upgrade, scintillator detectors are added to the existing water-Cherenkov surface detector stations. By making use of the differences in detector response to the electromagnetic particles and muons between scintillator and water-Cherenkov detectors, the electromagnetic …

Development Of A Machine Learning Framework For An Irrigation Decision Support System, Eric Wilkening, Derek M. Heeren, Yeyin Shi, Laila A. Puntel, Guillermo R. Balboa, Abia Katimbo, Kuan Zhang, Precious Nneka Amori, Bruno Lena

Department of Agricultural and Biological Systems Engineering: Faculty Publications

Currently used irrigation scheduling techniques often require significant human intervention and are time consuming, particularly for variable rate irrigation. This research aimed to develop a conceptual framework that incorporates disparate data sources leveraging both mechanistic and machine learning (ML) approaches. The overarching objective is to utilize the growing availability of data and technology to manage irrigation more precisely, which will minimize negative impacts of irrigation on our water resources. An initial irrigation machine learning model was proposed and tested in this study as a key component of an edge-cloud computing and federated learning decision-making framework. The specific objectives were (1) …

Risk Perceptions And Water Governance: Experiences Of Irrigation Companies In The Great Salt Lake Basin Of Northern Utah, United States, Bailey M. Holdaway

All Graduate Theses and Dissertations, Fall 2023 to Present

Irrigation companies are important water management entities in the Western US. However, these companies often face barriers when managing water. Particularly as the state of Utah grows and water resources are drying, there is much finger pointing at those in irrigation and agriculture for better water management. However, pointing fingers without the participation of these companies often does not lead to effective water management outcomes. Therefore, it is important to understand the role of these irrigation companies, and particularly how they are approaching water management.

I set out to understand the role of these irrigation companies, specifically in the Great …

Efficacy And Social Validity Of A Modified Good Behavior Game, Milad Najafichaghabouri

All Graduate Theses and Dissertations, Fall 2023 to Present

Teachers regularly face challenging behavior from students in their classrooms. Research shows that the good behavior game (GBG) is a strategy teachers can use in their classrooms to improve student behavior. However, in practice, very few teachers choose to use this strategy in their classrooms. One reason why teachers may not use this intervention regularly is that they find some parts of the intervention to be difficult to implement in the long-term. The purpose of this study was to modify the procedures of the GBG to reduce implementation effort for teachers and assess if the intervention continues to be effective. …

Improving Seasonal Precipitation Forecasts In The Western United States Through Statistical Downscaling, Bradley Vernon

All Graduate Theses and Dissertations, Fall 2023 to Present

Seasonal precipitation forecasts are essential tools for water management, especially in drought-prone areas like the Western United States. While global forecasting systems can predict precipitation months to years in advance, these forecasts are typically produced at a coarse spatial resolution due to high computational costs – especially when multiple forecast iterations, or ensemble members, are included. This coarse resolution limits their ability to capture localized weather features, such as those shaped by the complex terrain of the Intermountain West. Here, analog statistical downscaling is demonstrated as an effective approach to enhance the spatial resolution of operational seasonal forecasts provided by …

Optimization Of The Root Zone In Controlled Environment Agriculture, Brendan Fatzinger

All Graduate Theses and Dissertations, Fall 2023 to Present

Controlled environment agriculture (CEA) helps grow plants in spaces where resources like water and nutrients are limited, such as deserts or spacecraft. Effective management of water in the root zone, the area where plant roots grow, is vital to keeping plants healthy, especially in closed-loop systems where water cannot be wasted, as will be necessary for long-duration space missions.

An improved automated watering system designed for use in space-like environments was developed over several trials. Early designs using suction to draw water through tubes faced problems with uneven watering and roots blocking the tubes. Switching to a system that pushed …

"I Was In The Story": The Relationship Of Oral Storytelling With Student Hope, Narrative Transportation, And Religious Beliefs, Jacob B. Earnest

All Graduate Theses and Dissertations, Fall 2023 to Present

This study investigated the potential relationships with oral storytelling and student narrative transportation levels, student hope levels, and student religious beliefs. The Children’s Hope Scale and the Transportation Scale-Short Form were to assess hope levels and narrative transportation levels in participants. Results suggest that oral storytelling may have a strong relationship with narrative transportation. A relationship with oral storytelling and student religious beliefs is also suggested. Oral storytelling and student hope levels, and the possible connection between student narrative transportation levels and student hope levels, needs further research.

An Embodied Social Demography For Trans And Nonbinary Workers, Jesse Ezra Shircliff

All Graduate Theses and Dissertations, Fall 2023 to Present

Recently, the separation of “sex” and “gender” has seen intense debate in public discourse, stemming from skepticism about the social sciences and the measurement and study of gender specifically. Meanwhile, the United States population is becoming more gender diverse, with roughly 1 in 200 people now identifying as trans gender or gender nonbinary (that is, as a gender that is different from that person’s sex assigned-at-birth or outside of the sex-gender binary). This growing population experiences numerous disadvantages across social life, including obstacles in one particularly important aspect of the American Dream: the right to have and hold a job. …

Evaluating Maternal Polar Bear Denning Habitat Along The Arctic Coastal Plain And Assessing The Potential For Noise Disturbance In Polar Bear Dens, Ethan Ducharme

All Graduate Theses and Dissertations, Fall 2023 to Present

Polar bears (Ursus Maritimus) in northern Alaska are increasingly choosing land instead of sea ice to build their maternity dens. As sea ice continues to decline due to climate change, this shift makes it more important than ever to identify and protect the areas where polar bears dig dens to give birth and raise their cubs. In the first part of my research, I used new satellite-based elevation data to map potential polar bear denning habitat across a large section of Alaska’s Arctic Coastal Plain. This technology allowed me to identify the types of sloped terrain where drifting …

Veils Of Oppression: An Exploration Of Paul Fitzsimmons Eve And His Impact On Enslaved Black Women's Lives, Zoe'swanna K. Mcgee

All Graduate Theses and Dissertations, Fall 2023 to Present

This thesis contributes to the ongoing study of gender, race, and medicine in the United States, focusing on Dr. Paul Fitzsimmons Eve and his practices. By examining the experiences of enslaved black women subjected to his surgical procedures and experiments, medical racism, harm, and exploitation become visible.

Out Of Core And Adaptive Image Blending Approach For Large Scale Image Mosaics, Marcus Quincy

All Graduate Theses and Dissertations, Fall 2023 to Present

When creating large stitched images, like those used in maps made from aerial photos, it’s important to make sure the seams between individual pictures aren’t visible. This process, known as color blending, helps smooth out differences in lighting or weather across the images. But blending very large images, such as those made from many high-resolution aerial photos, can require huge amounts of memory, making it hard to do on a typical computer.

In this work, we developed a method that breaks the problem into smaller pieces, so only a small part of the image needs to be worked on at …

Factors Influencing Cognitive Load: Exploring Affective Elements, Motivational Constructs, And Regulatory Strategies In Learning, Rebecca B. Brockbank

All Graduate Theses and Dissertations, Fall 2023 to Present

There are three separate research papers within this dissertation, each looking at specific elements of learning. The process of learning is a complex phenomenon that includes not just cognitive aspects, but also emotional and motivational aspects. During learning there is an input of information into our cognitive system (i.e., minds). When too much information is given or the information is not presented effectively, this can overload our cognitive system and negatively impact our learning. Understanding how to learn within the parameters of our cognitive system is important. However, learning is more complex than just the simple input and output of …

Role Of Quartz Grain Size And Saturation On Fault Strength And Frictional Healing, Sapana Regmi

All Graduate Theses and Dissertations, Fall 2023 to Present

Rocks near the Earth's surface (less than 5 kilometers deep) often break and grind against one another to create crushed rock materials known as fault gouge. These fault gouges are filled with fragmented particles and broken rocks, which vary in grain size over time and space due to repeated earthquakes. This variation in grain size distribution along fault gouge can affect the strength of the fault, how it slips during an earthquake and how it 'heals' or recovers strength between earthquakes. Further, fault gouges often contain water from underground sources, which can influence how they slip. Previous studies have examined …

Balancing Native Wetland Types And Ecosystem Function Conservation In The Face Of An Aggressive Plant Invader, Aubin A. Douglas

All Graduate Theses and Dissertations, Fall 2023 to Present

Wetlands provide a multitude of ecosystem services that are important to people including water filtration, flood attenuation, carbon sequestration, and recreational opportunities such as birding and hunting. Wetland plants support these services by performing important underlying ecological processes called ecosystem functions which include removing heavy metals from water and providing habitat for migratory birds. The provisioning of these functions varies through space and time, by vegetation type, and via impacts from other factors like climate and management actions. Wetland managers are responsible for maintaining these functions and services within their management complexes to align with their agency’s mandates. Unfortunately, managers …

Queer Convergence: Figurative Abstraction In Contemporary Art., Vincent Young

Electronic Theses and Dissertations

This thesis is an exhibition text for the exhibition of the same name held in Schneider Hall Galleries from May 15 to August 21st, 2025. This exhibition explores the work of three contemporary artists – Joshua Jenkins, Drew Scanlon, and Lalana Fedorschak – and analyzes their artwork through the lens of Queer Convergence. Queer Convergence is an exploration of abstracted images of bodies and how we can read these bodies through a queer lens, arguing that the visual language of bodily overlap, melding, and transformation shows the physical form as a site of continual change shaped by shared experience and …

The Influence Of Psychological, Biological, And Social Determinants On Disordered Eating Behaviors Among U.S. Young Adults: Evidence From Nhanes 2015-2018., Samantha Kaye Gerbine

Electronic Theses and Dissertations

Disordered eating behaviors (DEBs) are influenced by biological, social, and psychological factors, yet research often narrowly focuses on White, college-aged women. This study assessed the predictors and prevalence of DEBs in a nationally representative sample of U.S. young adults using data from the 2015–2018 National Health and Nutrition Examination Survey (NHANES). Survey weights were applied to generate national estimates. Descriptive statistics characterized the sample, and logistic regressions tested biological, social, and psychological predictors of DEBs. A composite risk score was developed using variables retained in the final model. The unweighted sample (n = 1,062) represented 64 million U.S. young adults. …

Genes That Matter: Survival Modeling In Tcga-Brca With Treatment Interactions., David Pratt

Electronic Theses and Dissertations

High-dimensional genomic data offer both promise and challenges for identifying clinically relevant biomarkers. This study developed a parallelized survival modeling pipeline to identify genes associated with overall survival in breast cancer, with a focus on gene-by-treatment interactions and patient heterogeneity. RNA-Seq data from female patients in the TCGA-BRCA cohort were analyzed. Univariate Cox proportional hazards models were used to screen genes, adjusting for age, race/ethnicity, treatment status, and cancer stage. A LASSO-penalized Cox regression was fit across 2000 random seeds to assess feature stability. Genes were filtered by expression level, statistical significance, and hazard ratios (effect sizes) in either direction, …

Eng 1001g-017 College Composition I Critical Reading & Source Based Writing, Daniel Bobie

Fall 2025

No abstract provided.

Dust Observations Of Occulting Galaxy Pair Vv 191., Clayton Robertson

Electronic Theses and Dissertations

The presence of dust grains as part of the the interstellar medium (ISM) in galaxies is an all-impactful entity in astronomy due its influence on light, and therefore observations. Unlike a true blackbody, dust absorbs, reflects, reddens, and scatters light within a line of sight. We quantify this phenomena with attenuation: the difference between the observed and true magnitudes of an astronomical object due to dust. Therefore, to map dust attenuation, one needs a known background source of light. In the serendipitous case of partially overlapping –occulting– galaxies, the background galaxy serves as the known light source and the transmission …

Owl Integrations Soil Monitor, Derek Chau, Armaan Kahlon

Electrical Engineering

This paper examines the design process and results concerning the OWL Integrations soil monitor. Disaster relief relies heavily on digital communications, especially in environments where conventional methods (e.g. Wi-Fi, cellular, fiber optics) are unusable. To help emergency services assess disaster-stricken areas, a soil monitoring system was developed using LilyGo T-Beams (ESP32), programmed with specialized firmware known as the ClusterDuck Protocol to collect data pertaining to moisture and temperature. The project is sponsored by OWL Integrations, with help from the Cal Poly Electrical Engineering (EE) Department. Results show positive prospects, with the product able to make 4 km transmissions, operate for …

Exploring The Effect Of Social Determinants Of Health (Sdoh) Factors On The Time To Kidney Transplant Evaluation Completion For African American End Stage Renal Disease (Esrd) Patients, Kesha Levesque

MUSC Theses and Dissertations

Purpose – The purpose of this dissertation is to investigate the relationship between demographics and Social Determinants of Health (SDOH) variables on diagnostic testing time completion in patients being evaluated for kidney transplant waitlisting.

Aims - Compared to White Americans, African Americans who are eligible to receive a kidney transplant are less likely to complete the required testing in order to be placed on the kidney transplant waiting list which puts African Americans at risk for morbidity and mortality due to prolonged exposure to dialysis. The COVID-19 pandemic was directly associated with a decrease in the number of patients placed …

The Bandages Problem, James E. Marengo, Joseph G. Voelkel, David L. Farnsworth

Articles

A new probability problem, named the Bandages Problem, is described and solved. The problem involves repeatedly selecting and removing an item at random from a finite population that initially consists of a known configuration of single and paired items. For each selection, the probability that the chosen item is single is found. Generalizations are suggested.