Digital Commons Network^™

Multimodal Ai For Ed Chest Pain Triage: Prediction Performance And Operational Impact, Yves Najm Mrad, Molham Aldeiri

Gulf Coast Division GME Research Day 2026

No abstract provided.

Guitar Amplifier Directivity, Rachel C. Edelman, Brian E. Anderson, Samuel D. Bellows, Timothy W. Leishman

Directivity

No abstract provided.

Trustworthy Multimodal Ai For Medical Imaging: Enhancing Diagnosis, Reasoning, And Human-Agent Interaction In Extended Reality, Jai Prakash Veerla

Computer Science and Engineering Dissertations

The transition from traditional microscopy to digital pathology has digitized diagnostic data, yet clinical workflows remain constrained by two-dimensional screens and passive, opaque analysis tools that fail to capture the spatial complexity of biological systems. While Foundation Models now promise to reason across histology and genomics, a critical disconnect persists between the richness of this data and the limited cognitive bandwidth of clinicians, who currently lack the immersive interfaces and trustworthy agents necessary to utilize it effectively. This dissertation presents a unified framework for "Embodied Agentic AI," establishing a pipeline that augments physician capabilities through immersive visualization, robust security, and …

Seeing Success Through Functional Vision: Screening, Education, And Intervention Within Mtss For Kindergarten Students, Falynne Marie Rzezuski

OTD Capstones

Visual skills are essential for participation in early academic tasks including reading, writing, classroom engagement, and learning. However, functional vision difficulties often go unrecognized in kindergarten students, potentially affecting their academic performance and ability to learn within educational settings. The purpose of this capstone project was to develop and pilot a functional vision screening tool and program using a multi-tiered system of supports (MTSS) framework for kindergarten students. A literature review informed the development of the project, including the creation of the functional visual screening tool, integration within MTSS, Tier 1 and Tier 2 interventions, and educational resources for educators …

Improving Medical Diagnostics With Vision-Language Models: Convex Hull-Based Uncertainty Analysis, Ferhat Ozgur Catak, Murat Kuzlu, Taylor Patrick, Michel Audette

Engineering Technology Faculty Publications

In recent years, vision-language models (VLMs) have been applied to various fields, including healthcare, education, finance, and manufacturing, with remarkable performance. However, concerns remain regarding VLMs' consistency and uncertainty, particularly in critical applications such as healthcare, which demand a high level of trust and reliability. This paper proposes a novel approach to evaluate uncertainty in VLMs' responses using a convex hull approach on a healthcare application for visual question answering (VQA). For any VLM, temperature refers to a sampling parameter used in probabilistic generation, which controls the randomness of the model's output. The LLM-CXR model is selected as the medical …

Maxgrnet: A Multi-Axis Vision Transformer With Improved Generalization For Eye Disease Classification Using Explainable Ai With Insertion-Deletion Operations On Fundus Images, Md Mehedi Hasan Santo, Fuyad Hasan Bhoyan, Fuad Ibne Jashim Farhad, Fahmid Al Farid, Sovon Chakraborty, Md Humaion Kabir Mehedi, Jia Uddin, Hezerul Bin Abdul Karim

Computer Science Faculty Publications

Eye diseases, including diabetic retinopathy (DR), glaucoma, and cataracts, represent a major global health concern and can lead to severe visual impairment or blindness if not identified in a timely manner. This study proposes a novel eye disease classification framework based on a multi-axis vision transformer (MaxViT) applied to color fundus images with Explainable Artificial Intelligence (XAI) techniques to enhance model transparency. The proposed architecture integrates transformer-based attention mechanisms with Global Response Normalization (GRN)-based multi-layer perceptron (MLP) layers to capture complex spatial and contextual relationships within fundus images effectively. The model was evaluated on a publicly available eye disease classification …

Privacy-Preserving Federated Learning With Optimized Ensemble Weighting And Knowledge Distillation For Covid-19 Detection From Non-Iid Medical Imaging Data, Richard Annan, Hong Qin, Robert Newman, Madhuri Siddula, Letu Qingge

Computer Science Faculty Publications

Medical imaging enables rapid and accurate diagnosis of COVID-19, with CT scans proving especially effective. However, data privacy concerns limit collaborative model development across hospitals. To address this issue, we introduce a novel federated learning framework. It is referred to as Independent Knowledge Distillation with post-Ensemble Federated Learning (IKDEFL). Differential Privacy (DP) is integrated into the framework to improve privacy guarantees. Three DP mechanisms are evaluated. These include Fixed Gaussian, Gaussian Adaptive, and Tree Adaptive. The evaluation has been conducted on heterogeneous and Non-Independent and Identically Distributed (Non-IID) datasets. These datasets reflect real-world hospital scenarios. Results show that IKDEFL significantly …

An Investigation Of Federated Gnns Under Aggregation, Data Poisoning, And Differential Privacy For Icu Length-Of-Stay Prediction, Shakib Mahmud Dipto, Soumya Banerjee, Sandip Roy, Ahmad F. Al Musawi, Preetam Ghosh, Sachin Shetty, Pratip Rana

Computer Science Faculty Publications

Accurate prediction of ICU Length of Stay (LoS) is essential for clinical decision-making and healthcare resource management. Graph Neural Networks (GNNs), such as GraphSAGE, offer a natural fit by capturing patient data from Electronic Health Records (EHRs) through graph structures. However, the distributed and sensitive nature of this data raises both privacy and legal concerns regarding the aggregation and training of GNN models. This additionally leads to issues with data imbalance and model robustness. In this study, we perform an analysis of the Federated Graph Neural Network (GNN-FL) framework to enable decentralized learning on EHRs derived from the MIMIC-III dataset. …

Advances And Challenges In Digitally Connected Point-Of-Care Biosensing, Abdellatif Ait Lahcen, Jegan Rajendran, Gymama Slaughter

Center for Bioelectronics Publications

Point-of-care (POC) biosensors are undergoing a paradigm shift from isolated diagnostic tools to digitally connected, intelligent platforms that enable continuous and decentralized healthcare delivery. This review critically examines recent advances in wearable, implantable, and portable biosensors, highlighting how integration with wireless communication, the Internet of Medical Things (IoMT), and artificial intelligence is transforming their functionality and clinical utility. Particular attention is given to innovations such as smartphone-enabled interfaces, cloud-based analytics, and machine learning-assisted analysis, which collectively enhance sensitivity, specificity, and user accessibility across diverse healthcare settings, from personalized home monitoring and bedside diagnostics to deployment in resource-limited regions. The review …

Guidelines For Standard Basic Notations In Applied Statistics, Abhaya Indrayan, Shivani Saini Ms

COBRA Preprint Series

Whereas some statistical notations are standard and uniformly used by different workers, many are not. Varying notations lead to confusion among the readers, particularly those engaged with applied statistics material, such as medical professionals. This communication proposes that all basic notations be standardized so that the same notations are consistently used by different authors, in different books, journals, and articles for the benefit of those who are not rigorously trained statisticians. Guidelines for such standard notations are also provided. The lead must be taken by statisticians.

Understanding The Impacts Of Food Insecurity On Education Outcomes In Ohio, Maria El Biri, Sreya Tummalapalli

Scholarship in Medicine - All Papers

Background: Food insecurity has been a growing concern in the United States, and prior research has shown how food insecurity in youth can correspond to negative psychosocial outcomes. Additionally, there are known disparities with access to food based on living in rural or urban counties. Objective: The goal of this study was to determine how differences in food security can impact youth educational outcomes in Ohio. Methods: Data from County Health Rankings & Roadmaps were obtained on variables such as access to healthy foods, food insecurity, high school graduation rates, average grade performance, and percentage of the population living in …

Investigating The Role Of Humic Acid In The Adsorption Mechanics Of Acetaminophen On Potassium Persulfate-Aged Polyethylene Terephthalate (Pet), Andrew Littleton, Maria Danielle Garrett, Phd

SPARK Symposium Presentations

Pharmaceutical contaminants such as acetaminophen (APAP) are showing a rising presence in aquatic environments, where their interactions with microplastics (MPs) can potentially modulate natural degradation mechanisms. Concurrent presence of the two substances has been shown to potentiate increase their individual harmful effects. This study investigates whether oxidative aging and humic-acid surface modification of PET microplastics influence APAP adsorption.

In this study, UV-aging was reproduced using an iron (II)-activated potassium persulfate (Fe(II)-KPS) oxidation system. Aqueous dissolved organic matter (DOM) is simulated using multi-hour exposure to humic acid. The MPs are then removed from the solution to examine adsorption mechanisms. While most …

Assessment Of Doxorubicin And Etoposide Effects On Cardiotoxicity Using Daphnia Magna As A Model Organism​, Jacob P. Bealle, Andrea Florian

SPARK Symposium Presentations

Chemotherapeutic agents such as doxorubicin and etoposide are widely used in cancer treatment but are known to produce cardiotoxic side effects that can limit their clinical use. Doxorubicin has been strongly associated with dose-dependent cardiac damage, and etoposide has also been reported to produce cardiotoxic effects although the cardiotoxic effects of etoposide are not as well studied. Daphnia magna is a useful model organism for cardiotoxicity studies because its transparent body allows direct observation of heart rate and provides a living system for detecting physiological responses to exposure. The purpose of this study was to investigate the cardiotoxic effects of …

Potential Environmental Triggers Of Goodpasture's Disease And The Role Of The Sulfimine Crosslink, Colton S. Miller, Andrea Florian, Elena Pokidysheva

SPARK Symposium Presentations

Goodpasture’s syndrome (GP) is an autoimmune disorder that primarily affects kidneys and lungs. The main issue for patients with Goodpasture's syndrome is the binding of autoantibodies to the glomerular basement membrane (GBM), which hinders the filtration of blood. A key characteristic of Goodpasture's syndrome is the presence of autoantibodies that target the NC1 domain of the α345 isoform of type IV collagen, a crucial component of the GBM that provides structural support and is critical for filtration function. Sulfilimine bonds crosslink the collagen IV NC1 hexamers, contributing to the stabilization of these structures. A recent clinical case of recurring Goodpasture's …

J Am Coll Dent 2026 92 3

Journal of the American College of Dentists

The Journal of the American College of Dentists (JACD) publishes scholarly articles, editorials, essays, and reflections addressing the ethical, professional, and social dimensions of dentistry. The Journal serves as a forum for advancing ethics, professionalism, leadership, and excellence within the dental community. By fostering dialogue across disciplines and perspectives, JACD provides readers with insights that encourage ethical, professional practice, lifelong learning, and service to the public, reinforcing dentistry’s commitment to advancing oral healthcare and the common good.

Bridging The Knowledge-Practice Gap In Breast Cancer Awareness: A Nationwide Online Cross-Sectional Kap Study Among Adult Females In Nigeria, Madinat Hassan, Taofeek Tope Adegboyega, Bilkisu Usman Farouk, Sunday Zeal Bala, Rachael Olufunmilayo Oduyemi, Kazeem Owolabi, Munir Sani, Miracle Uwa Livinus, Hannatu Usman Ayuba, Sadiq Hassan, Ifeyinwa Maureen Okeke, Abednego Shekari, Murtala Jibril

Chemistry & Biochemistry Faculty Publications

Background and Aims

Breast cancer (BCa) is a major cause of cancer morbidity and mortality among women in Nigeria, with late presentation contributing to poor outcomes. This study assessed knowledge, attitudes, and willingness to perform breast self-examination (BSE) among adult females in Nigeria and examined associated factors.

Methods

We conducted a descriptive cross-sectional online survey between February 16 and April 30, 2024. A structured, pretested questionnaire was disseminated through digital platforms, yielding 711 consenting adult female respondents from all six geopolitical zones. Knowledge, attitude, and willingness-to-perform-BSE measures were analyzed using descriptive statistics, linear regression, and binary logistic regression. Associations were …

Training Set Augmentation And Biology-Aware Harmonization Improve Radiomic Models For Lung Cancer Prediction In Indeterminate Nodules, Claire Huchthausen, Menglin Shi, Gabriel De Sousa, James Larner, Einsley Janowski, Jonathan Colen, Krishni Wijesooriya

Data Science Faculty Publications

CT radiomics-based machine learning has potential to predict lung cancer in pulmonary nodules (PNs) earlier than standard-of-care methods. Low malignancy rates in early-development PNs and variable image acquisition hinder development of radiomic models for diagnosing these PNs. To address these challenges, we augmented training using later-development PNs and harmonized for acquisition effects. We examine early-development benign and malignant PNs (n = 106) below the sensitivity of standard-of-care diagnosis. Classifiers predicting malignancy performed near chance when trained on ComBat-harmonized radiomic features from only early-development PNs. We then augmented training with later-development benign and malignant PNs (n = 225). We evaluated whether …

When Climate Change Forces Flight: Legal Duties In The Age Of Retreat, Mark P. Nevitt

Faculty Articles

In the face of climate-driven disasters, government officials and individuals alike must decide whether to invest in climate-exposed areas or retreat. This Article analyzes emerging legal and policy issues associated with both climate retreat (when the government relocates people and infrastructure away from climate-exposed areas) and abandonment (when individuals leave climate-exposed areas, following natural disasters or otherwise). I argue that government-driven climate retreat must consider four overlapping legal duties, raising novel questions in an era of climate destabilization. First, does the government have an affirmative duty to rescue its citizens, and is this duty transformed by the government’s role in …

Mitigating The Effects Of Technology Use In The Classroom: An Occupational Therapy Approach, Hannah E. Ibach

Occupational Therapy Capstones

Background: The average child spends three times the recommended time on technology, which is leading to a wide range of consequences affecting education, such as fine motor, cognitive, and social deficits (Christensen, 2021; McGough, 2021; Qi et al., 2023). Parents and teachers play a crucial role in helping children be prepared for their education, yet many are not aware of the impacts of too much technology use (Srivastava, 2022). Developing strong foundational skills early in childhood is critical for setting the stage for long-term educational success. When skills are nurtured from a young age, children are better prepared to adapt …

Radial And Carotid Arterial Pulse Signals For Assessing Cardiovascular Function At Rest And During Post-Exercise Recovery In A Heart Transplant Patient: A Case Study, Md Mahfuzur Rahman, Mamun Hasan, Jennifer F. May, John M. Herre, Leryn Reynolds, Zhili Hao

Mechanical & Aerospace Engineering Faculty Publications

Aim: This study investigates the feasibility of using radial and carotid arterial pulse signals to assess cardiovascular (CV) function at rest and during post-exercise recovery in a heart transplant (HTx) patient. Method: Two micro-fabricated tactile sensors were used to simultaneously acquire arterial pulse signals at the radial artery (RA) and carotid artery (CA). Measurements were taken at rest and at multiple time points post-exercise on three subjects: an HTx patient, a percutaneous coronary intervention (PCI; coronary stent) patient and a healthy control. An SDOF-TF-based time-frequency analysis algorithm was applied to extract a comprehensive set of CV parameters, including heart rate …

Dynamic Modeling Of The Earth's Trapped Proton Environment, Xiaojing Xu, Steve R. Blattnig, Francis F. Badavi, Martha S. Clowdsley, Edward J. Semones

Physics Faculty Publications

Context: Reliable prediction of space radiation exposure is critical for safeguarding spacecraft systems and ensuring astronaut health during missions. Accurate radiation risk assessment for space mission requires advanced models of the Earth’s trapped proton environment. These models must reflect temporal variations driven by geomagnetic field evolution and solar cycle modulation. Existing static models, such as AP8 and IRENE-AP9, are not designed to fully capture these evolving conditions. Aims: This paper presents a dynamic modeling method for the prediction of trapped proton fluxes, which incorporate time-dependent variations due to geomagnetic field evolution and solar cycle fluctuations. Methods: The …

Real-Space Imaging Of The Electron-Pair Density Hole In Molecular Auger-Meitner Decay, Mats Simmermacher, Nathan Goff, Andres Moreno Carrascosa, Elke Fasshauer, Thomas Northey, Lingyu Ma, Haiwang Yong, Brian Stankus, Asami Odate, Xuan Xu, Wenping Du, Kyle Acheson, Joseph C. Cooper, Daniel Ratner, Mengning Liang, Ruaridh Forbes, Michael P. Minitti, Adam Kirrander, Peter M. Weber

Physics Faculty Publications

Electrons in matter can rearrange extremely quickly under external perturbations, underpinning subsequent structural and chemical transformations. Coulomb interactions between neighbouring electrons often shape this response, giving rise to correlated motion and strongly affecting the distribution of electrons in the system. Here we show that non-resonant hard X-ray scattering can directly access changes in the radial electron-pair density during the rapid rearrangement of core and valence electrons. We do this by studying sulfur hexafluoride molecules undergoing Auger–Meitner decay. We exploit a second-order interaction between the X-ray photons and the molecules to trigger and probe the decay dynamics with a single pulse, …

Integrative Approaches And Data Analysis For Single-Cell Rna Sequencing Data, Teng Long

Computer Science and Engineering Dissertations

The rapid growth of single-cell RNA sequencing and transcriptomic datasets has created major computational challenges in causal discovery, representation learning, and biologically faithful data generation. To address these challenges, this dissertation presents three complementary deep learning frameworks for the analysis and modeling of transcriptomic data. Together, these methods form an integrative computational toolkit for understanding complex biological systems from high-dimensional and heterogeneous gene expression data.

First, this dissertation introduces DAG-VAERL, a causal discovery framework that integrates variational autoencoders, graph neural networks, reinforcement learning, and attention mechanisms to infer directed acyclic graphs for gene regulatory network analysis. DAG-VAERL improves causal structure …

Dose-Dependent Developmental Toxicity Of Cisplatin In Zebrafish Embryos, Reagan D. Sellers, Katherine T. Doucet, Jinhee Park, Andrea Florian

SPARK Symposium Presentations

Cisplatin is a widely used chemotherapy drug for treating various types of cancer. Although cisplatin is effective in killing cancer, it can also cause toxic side effects in normal tissues. Because cisplatin can cross the placental barrier, its use during pregnancy is generally avoided, particularly during early embryonic stages of fetal development. Exposure to cytotoxic drugs during embryogenesis may lead to developmental abnormalities, birth defects, or pregnancy complications. Understanding how cisplatin affects early development is therefore important.          
       Zebrafish (Danio rerio) are an established model for studying developmental toxicity due to their rapid external development, transparent embryos, and genetic similarity to …

Effects Of Glucagon And Insulin On Sw480 Colorectal Cancer Cells In Combination With Cisplatin, Sarah M. Gabous, Andrea Florian

SPARK Symposium Presentations

Colorectal cancer is known to be one of the most common forms of cancer in the world. Over time, treatment responses are affected by various metabolic changes along with chemotherapies. Glucagon signaling and Insulin are linked to colorectal cancer and have also been shown to affect tumor growth, as well as the chemotherapy drug response.In this experimental study, the purpose was to determine whether glucagon and insulin decrease the viability of SW480 colorectal cancer cells during cisplatin (CDDP) treatment. CRC cells were treated with cisplatin alone and in combination with either glucagon or insulin, and cell viability was measured to …

Simulating Social Attitudes With Llms: Accuracy, Demographic Effects, And Refusal Behavior In The Sensitive Domain Of Suicide Prevention, Cristina J. Perez, Michael P. Vasquez Jr., Philippe J. Giabbanelli, Patrick Y. Wu

VMASC Publications

Large language models (LLMs) are increasingly used to simulate public opinion, yet their validity in sensitive policy domains remains underexplored. We evaluate whether LLMs can reproduce attitudes toward suicide prevention policies using 32 questions drawn from seven nationally representative U.S. surveys (2023-2025). We systematically vary demographic conditioning (race/ethnicity, gender, age, education, income, party), prompt framing (direct elicitation, respondent embodiment, specialist embodiment), and model architecture (GPT-5 Nano, DeepSeek V3.2, Meta Llama 3.1 8B, Mistral Small 24B). Across 811,560 prompts, the mean absolute error—the average gap between predicted and human response distributions—is 23 percentage points. We also find that LLM responses to …

Bayesian Multivariate Modelling Of Lone Star (Amblyomma Americanum) Tick Life Stage Abundance And Temporal Trends To Inform Public Health Risk In Virginia, Thabo Lephoto, Henry Mwambi, Oliver Bodhlyera, Holly Gaff

Biological Sciences Faculty Publications

The increasing abundance of ticks poses a growing public health concern due to heightened human exposure to tick bites. The lone star tick (Amblyomma americanum: Ixodida: Ixodidae), a common human-biting species in the United States, has expanded its range in recent years. However, how its different life stages vary across time, habitats, and locations remains insufficiently understood. We analyzed tick abundance data collected in southeastern Virginia between 2009 and 2018, focusing on larval, nymphal, and adult life stages. A Bayesian multivariate modelling framework was used to examine seasonal patterns, habitat effects, spatial variation, and biological links between life stages. Two …

An Ensemble Classifier For Ordinal Outcomes In High-Dimensional Genomics Data, Heranga K. Rathnasekara, Sinjini Sikdar

Mathematics & Statistics Faculty Publications

Analysis of genomics data for predicting disease outcomes is a fast-growing field in medical research. There often exist categorical, specifically, ordinal outcomes that need to be predicted based on genomic profiles. This has led to recent development of some high-dimensional ordinal classification methods that can address the large dimensionality of the genomic covariate set. These high-dimensional ordinal models tend to vary widely in their performance depending on the data they are applied to and the evaluation criteria used. In this article, we outline an ensemble ordinal classifier that integrates different ordinal modeling approaches through bootstrap-based model evaluation, multi-metric performance assessment, …

Expanded Scorpionate And Siderophore-Inspired Ligands: From Foundational Designs To Modern Applications, Austin Winfield Medley, Trandon Allen Bender

Chemistry & Biochemistry Faculty Publications

Scorpionate ligands have been advanced significantly through systematic modifications of their apical atoms and heterocyclic arms, expanding their structural diversity and chemical reactivity. Recent biologically inspired variants now enable accurate modeling of complex bioinorganic motifs, such as the Fe₄S₄ clusters of nitrogenase, and support enzyme‐like reactivity under mild aqueous conditions. These developments have broadened the impact of scorpionate chemistry across bioinorganic modeling, homogeneous catalysis, and biorthogonal transformations. In particular, expanded tripodal scaffolds provide modular, tunable platforms for mimicking enzyme active sites and probing biological nitrogen fixation pathways. Beyond fundamental insight, these ligands present practical opportunities for sustainable catalysis by enabling …

Investigating The In Vitro Antimicrobial Potential And Comprehensive Computational Studies Of New Schiff Base Derivatives, Abrar Hussain, Shahzaib Akhter, Hammad Nasir, Khurram Shahzad, Muhammad Arfan, Sand Hyun Park

Chemistry & Biochemistry Faculty Publications

Antimicrobial resistance (AMR) is a growing global health threat driven by multidrug-resistant bacteria (Staphylococcus aureus, Pseudomonas aeruginosa), and fungi (Candida albicans, and C. parapsilosis). This study evaluated six novel Schiff base derivatives (HSB-1 to HSB-6) through integrated in vitro antimicrobial activity and comprehensive computational studies. In vitro disk diffusion assay demonstrated the largest zones of inhibition against S. aureus for HSB-6 and HSB-1 (15–17 mm), activity against P. aeruginosa for HSB-5 and HSB-6 (12 mm), and moderate antifungal activity for HSB-4 (8–11 mm). Molecular docking results correlated with the in vitro findings with the binding energy ΔG = −12.3 kcal/mol …