Digital Commons Network^™

Large Language Model-Assisted Research Question Development In Public Health: A Case Study In The Special Supplemental Nutrition Program For Women, Infants, And Children (Wic), Qi Zhang, Bidusha Neupane, Priyanka Patel, Futun N. Alkhalifah, Yi He, Leslie Hodges

Health Behavior, Policy & Management Faculty Publications

Objective:

To assess the feasibility of using large language models (LLMs) to develop research questions about changes to the Special Supplemental Nutrition Program for Women, Infants, and Children (WIC) food packages.

Design:

We conducted a controlled experiment using ChatGPT-4 and its plugin, MixerBox Scholarly, to generate research questions based on a section of the USDA summary of the final public comments on the WIC revision. Five questions weekly for three weeks were generated using LLMs under two conditions: fed with or without relevant literature. The experiment generated 90 questions, which were evaluated using the FINER criteria (Feasibility, Innovation, Novelty, Ethics, …

The Crucial Role Of Machine Learning Models In Predicting Current Childhood Asthma: Model Comparison, Calibration, And Shap-Based Interpretation, Aditya Chakraborty, A. K.M. Raquibul Bashar

Epidemiology, Biostatistics, & Environmental Health Faculty Publications

Background: Asthma is one of the most prominent chronic diseases in children and one of the most challenging ailments to diagnose in infants and preschoolers in the United States. Predictive models can be instrumental in improving early diagnosis, personalized treatment strategies, and disease progression. By utilizing nationalized data, this study focuses on building and comparing high-performing analytical predictive models based on the relevant risk factors and identifying the most influential predictors.

Methods: We analyzed cross-sectional BRFSS Asthma Call-Back Survey data (2011-2020; N = 9,813) and randomly split participants into training and testing sets. An XGBoost model (hyperparameters tuned via grid …

Ensemble Learning For Predicting Periapical Lesions From Dental Radiographs, Fang-Yuan Liao, Ming-Jyun Jian, Abdullah Sarini, Yulianto Jesica, Yen-Kun Lin, Hsun-Yu Huang

Journal of Dental Sciences

Background/purpose: Diagnosing periapical cysts and granulomas using periapical radiographs is challenging due to subtle radiographic differences. This study aimed to develop a machine learning–based diagnostic framework to improve lesion classification through ensemble learning and dentin standardization.

Materials and methods: Five models—Support Vector Classifier (SVC), Nu-SVC, K-Nearest Neighbors (KNN) and Decision Tree—were trained on 144 pre-treatment periapical radiographs (70 cysts and 74 granulomas). Dentin standardization normalized grayscale values to ensure feature consistency. A weighted soft voting strategy was employed to integrate predictions, with model weights derived from individual diagnostic performance. Model performance was evaluated via five-fold cross-validation. Statistical significance among models …

The Impact Of Congenital Heart Disease On The Timing Of Alzheimer's Disease In Down Syndrome, Julianne G Clina, Beau Ances, Et Al.

2020-Current year OA Pubs

INTRODUCTION: The incidence of Alzheimer's disease (AD) in Down syndrome (DS) exceeds 90%. Approximately 50% of people with DS have congenital heart disease (CHD). Having CHD increases risk for early-onset AD in populations without DS, but it is unclear if CHD influences AD in DS.

METHODS: Data from the Alzheimer Biomarker Consortium-Down Syndrome (ABC-DS) were used. Participants with CHD (

RESULTS: People with CHD scored lower for visuospatial ability (

DISCUSSION: Presence of CHD may influence AD progression in DS.

HIGHLIGHTS: In adults with Down syndrome (DS), those with congenital heart disease (CHD) had higher amyloid beta and reached the …

Ocular Surface Disease Following Lasik And Cataract Surgery: A Review Of Their Interrelated Complications, Matthew D. Spangler, Nila Kirupaharan, John D. Sheppard

Department of Ophthalmology Faculty Publications

Background: Ocular surface disease is a multifactorial condition that is very commonly caused by dry eye disease (DED). Ophthalmic procedures intended to improve visual outcomes, laser-assisted in situ keratomileusis (LASIK) and cataract surgery, can paradoxically cause or exacerbate underlying ocular surface disease. This results in worsening vision and quality of life.

Areas covered: This review examines the pathophysiological mechanisms contributing to ocular surface disease development following LASIK and cataract surgery. Both procedures are associated with the transection of corneal nerves, leading to decreased tear production, surface instability, altered neurotrophin production, and impairment of the blink reflex. Furthermore, these incisional procedures …

Preoperative Patient Sentiment Is Associated With Postoperative Outcomes In Adult Spinal Deformity Surgery, Ross J. Gore, David Mazur-Hart, Mohan K. Sunkara, Aaqib Ali, Qizar Ali, Christopher J. Lynch, Christopher Ames

Center for Secure and Intelligent Critical Systems (CSICS) Publications

Study Design: Prospective observational pilot study of adult spinal deformity surgery patients.

Objective: To determine whether preoperative patient sentiment, quantified using a 21-class valence scale extending the CARP paradigm implemented through an offline Large Language Model, predicts postoperative outcomes.

Summary of Background Data: Predicting adult spinal deformity surgery outcomes remains challenging with traditional clinical and radiographic parameters alone. Although patient psychological factors and expectations significantly influence postoperative satisfaction and quality of life, systematic approaches to capture these factors are underdeveloped. Offline Large Language Models offer scalable, privacy-preserving psychological risk stratification.

Materials and Methods: We prospectively enrolled 18 patients undergoing adult …

Preoperative Patient Sentiment Is Associated With Postoperative Outcomes In Adult Spinal Deformity Surgery, Ross J. Gore, David Mazur-Hart, Mohan K. Sunkara, Aaqib Ali, Qizar Ali, Christopher J. Lynch

Center for Secure and Intelligent Critical Systems (CSICS) Publications

Study Design:

Prospective observational pilot study of adult spinal deformity surgery patients.

Objective:

To determine whether preoperative patient sentiment, quantified using a 21-class valence scale extending the CARP paradigm implemented through an offline Large Language Model, predicts postoperative outcomes.

Summary of Background Data:

Predicting adult spinal deformity surgery outcomes remains challenging with traditional clinical and radiographic parameters alone. Although patient psychological factors and expectations significantly influence postoperative satisfaction and quality of life, systematic approaches to capture these factors are underdeveloped. Offline Large Language Models offer scalable, privacy-preserving psychological risk stratification.

Materials and Methods:

We prospectively enrolled 18 patients undergoing adult …

Pathways, Outputs And Impact Of Nih-Supported Bioinformatics And Genomics Graduate Trainees In Africa, Daudi Jjingo, Andrew Walakira, Suhaila Hashim, Cisse Cheickna, Ronald Galiwango, Caleb Kibet, Florence N. Kivunike, Gerald Mboowa, Fredrick Elishama Kakembo, Babajide Ayodele, Jean Baka Domelevo Entfellner, Santie De Villiers, Karen Wambui, Segun Fatumo, Tinashe Chikowore, John Mukisa, Alfred Ssekagiri, Nicholas Bbosa, Julius Mulindwa, Samuel Kyobe, Mike Nsubuga, Grace Kebirungi, Eric Katagirya, Savannah Mwesigwa, Ibra Lujumba, Rogers Kamulegeya, Samuel Kirimunda, Stephen Kanyerezi, Shahiid Kiyaga, Ivan Sserwadda, Davis Kiberu, Daniel Masiga

All Peer-Reviewed Publications

Global biomedical and health research is increasingly relying on genomic and computational approaches, largely driven by the increasing volumes of nucleic acid sequencing. Concurrently, epidemiological studies and clinical records are generating enormous amounts of data amenable to disease modeling, machine learning, and artificial intelligence techniques. Bioinformatics and data science expertise is therefore essential for improved population health. Accordingly, in 2012, the US National Institutes of Health (NIH) in partnership with the Wellcome Trust, and with support from the African Society for Human Genetics, initiated the H3Africa (Human Heredity and Health in Africa) consortium. One of its key goals was to …

Analysis Theories On Artificial Intelligence, Chatgpt, Data Science, And Metaverse: The Case Of Digital Medicine, Yin Yang, Xingyun Liu, Jorge Luis Cuyubamba Dominguez, Yuan Fang, Wen Xie, Bairong Shen, Keng Siau

Research Collection School Of Computing and Information Systems

Healthcare organizations are increasingly adopting digital technologies, with Artificial Intelligence (AI), Data Science, and the metaverse driving significant advancements in smart healthcare. Al facilitates personalized medicine and efficient drug development, while Data Science enables predictive analytics and big data management, enhancing patient outcomes and healthcare quality. The metaverse introduces immersive training and telemedicine platforms, revolutionizing patient engagement and healthcare research. This study conducts' a scoping review of 6,171 articles, analyzing the transformational impact of AI, ChatGPT, Data Science, and the metaverse on healthcare. It highlights the benefits and risks of these technologies, identifies research gaps in their application within the …

Interpretable Multimodal Zero Shot Ecg Diagnosis Via Structured Clinical Knowledge Alignment, Jialu Tang, Hung Manh Pham, Ignace De Lathauwer, Henk S. Schipper, Yuan Lu, Dong Ma, Aaqib Saeed

Research Collection School Of Computing and Information Systems

Electrocardiogram (ECG) interpretation is essential for cardiovascular disease diagnosis, but current automated systems often struggle with transparency and generalization to unseen conditions. To address this, we introduce ZETA, a zero-shot multimodal framework designed for interpretable ECG diagnosis aligned with clinical workflows. ZETA uniquely compares ECG signals against structured positive and negative clinical observations, which are curated through an LLM-assisted, expertvalidated process, thereby mimicking differential diagnosis. Our approach leverages a pre-trained multimodal model to align ECG and text embeddings without disease-specific fine-tuning. Empirical evaluations demonstrate ZETA’s competitive zero-shot classification performance and, importantly, provide qualitative and quantitative evidence of enhanced interpretability, grounding …

Sage: Spatially Aware Gene Selection And Dual-View Embedding Fusion For Domain Identification In Spatial Transcriptomics, Yi He, Yunpei Xu, Liqing Ding, Hong-Dong Li, Yaohang Li, Shaokai Wang

Computer Science Faculty Publications

Despite enabling high-resolution mapping of gene expression within tissues, spatial transcriptomics (ST) still faces challenges in accurately segmenting spatial domains due to complex tissue architecture and limitations of current methods. Most approaches rely on local spatial priors, lack gene-level interpretability, and fall short in capturing structure-discriminative genes or long-range functional relationships, limiting their ability to resolve biologically meaningful architectures. We present Spatially Aware Gene selection and dual-view Embedding fusion (SAGE), a unified and reproducible framework for domain identification in spatial transcriptomics that combines topic-driven gene selection with dual-view embedding fusion to address these gaps. SAGE integrates non-negative matrix factorization (NMF)-based …

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. …

Near Real-Time Adaptive Isotropic And Anisotropic Image-To-Mesh Conversion For Cerebral Aneurysm Simulations, Kevin Garner, Chander Sadasivan, Nikos Chrisochoides

Computer Science Faculty Publications

This paper presents two performance optimization techniques for a mesh adaptation method that is designed to help streamline the discretization of complex vascular geometries within the numerical modeling process. This method is integrated into a pipeline with an image-to-mesh conversion tool to generate adaptive anisotropic meshes from segmented medical images. The pipeline is shown to satisfy quality, fidelity, smoothness, and robustness requirements while providing near real-time performance for medical image-to-mesh conversion. Tested with two brain aneurysm cases and utilizing up to 96 CPU cores within a single, multicore node on Purdue University’s Anvil supercomputer, the parallel adaptive anisotropic meshing method …

Adaptive Self-Attention For Enhanced Segmentation Of Adult Gliomas In Multi-Modal Mri, Evan P. Savaria, Jiangwen Sun

Computer Science Faculty Publications

Every year there are an estimated 80,000–90,000 new glioma cases, highlighting the need for reliable imaging-based decision support. Although deep learning has improved tumor sub-region segmentation, many state-of-the-art models fail to fully capture complementary information across T1, T1Gd, T2, and FLAIR MRI modalities and often operate as “black boxes,” limiting physician trust when precise delineation is critical for surgical planning, radiation targeting, and treatment monitoring. To address these limitations, we propose AIMS, an Adaptive Integrated Multi-Modal Segmentation framework that maintains modality-specific feature streams and employs adaptive self-attention within a hierarchical CNN-Transformer architecture to prioritize and fuse multi-modal MRI features. We …

A Comparative Analysis Of Explainable Ai (Xai) Techniques For Transparent And Reliable Image Classification, Sovon Chakraborty, Shakib Mahmud Dipto, Kevin R. Pilkiewicz, Michael L. Mayo, Pratip Rana

Computer Science Faculty Publications

Evaluating the trustworthiness of black-box machine learning models remains a significant methodological challenge. Their lack of transparency and interpretability limits applicability, because stakeholders often seek transparency before trusting the results of black-box machine learning models. Explainable AI (XAI) methods provide for human-understandable justifications and informed decision-making of these black-box architectures. Therefore, it is imperative to select the proper XAI model tailored to specific tasks. In this research, we focus on examining four XAI techniques: PEEK, LRP, GRAD-CAM, and LIME to understand how they perform against each other for image classification tasks. We evaluate the performance, robustness, generalizability, noise stability, and …

Attf-Gnn: An Attention-Based Multi-Omics Graph Neural Network With Modality Learning For Disease Subtyping, Sovon Chakraborty, Eleni Adam, Terry Stilwell, Harold Riethman, Desh Ranjan, Pratip Rana

Computer Science Faculty Publications

We propose AttF-GNN, an attention-based graph fusion strategy for diseases classification and subtyping. In multiomics analysis, not all types of molecular data are equally relevant for disease subtyping and considering all modalities equally may obscure discriminative signals and limit the effectiveness of predictive models by overlooking modality-specific contributions. Therefore, we design an attention-based multimodal GraphSAGE framework that can automatically emphasize the modalities providing the most relevant information for classification. At first, we have constructed three graphs using mRNA, RNA-seq and DNA methylation modalities, and train each omics with individual GraphSAGE encoders. Next, a unified intersection graph is formed using an …

Attention-Based Multi-Omics Fusion For Drug Synergy Prediction, Kusal Debnath, Pratip Rana, Preetam Ghosh

Computer Science Faculty Publications

Drug combination therapy in disease management gained popularity in the last few decades. Computational modeling of such combinations is an active area of research in the drug discovery domain. While earlier approaches solely emphasized on the structural features of participating drugs for designing synergistic models, they lack other crucial factors directly linked with drug administration - omics expressions. As differential omics expression is a downstream consequence of the administered drug combinations, utilizing such expressions while designing synergistic models promises robust and dynamic modeling. In this work, we propose SynergyLM that fuses multi-omics features with drug embeddings to build an omics-aware …

Understanding Motivations And Health Outcomes Of College-Aged Triathletes During Covid-19: A Mixed-Methods Study, Patrick Wilson, Eddie Hill, Justin Haegele, Xihe Zhu

Human Movement Studies & Special Education Faculty Publications

A triathlon is a multi-sport event that consists of three simultaneous events: swimming, biking, and running. This sport has experienced significant growth in the past few decades, with colleges and universities now participating. This exploratory mixed-methods study examined the motivations and perceived health benefits of college triathletes during the COVID-19 pandemic, using the Means-Ends of Recreation Scale and the Perceived Health Outcomes of Recreation Scale (N = 29), as well as semi-structured interviews (N = 4). Results indicate no difference in motives or health outcomes between male and female survey respondents. The thematic analysis of open-ended interview questions highlighted lived …

Integrating Self-Determination Theory And Continuous Glucose Monitoring: Promoting Youth Development Among Campers With Type 1 Diabetes, Eddie Hill, Bethany Arrington, Taylor Harvey, Alexis Barmoh, Rowan Williams, Laura Hill

Human Movement Studies & Special Education Faculty Publications

The purpose of this cohort study was to evaluate participants’ general self-management and experiences of autonomy while attending diabetes camp using quantitative and qualitative data collection. Through a partnership, an outdoor diabetes camp was designed to assist youth with type 1 diabetes (T1D) in their management. The REACH Teen program conducted a week-long summer camp for youth with T1D. The study was designed through Outcome-Focused Programming grounded in Self-Determination Theory (SDT) to meet campers’ needs of autonomy, competence, and relatedness. Campers participated in outdoor activities and diabetes education designed to increase healthy behaviors. Twenty-three campers completed a 24-item pre- and …

Photo And Spatial Control Of Rna Structures And Functions: Exploring Positional Effects And Photo-Responsiveness Of Azobenzene Modified Nucleotides, Jinxi Du

Electronic Theses & Dissertations (2024 - present)

RNA molecules perform many important biological functions by forming complex three-dimensional structures stabilized by base pairing, tertiary interactions, and metal ion coordination. Because RNA function depends strongly on its structure, methods that allow reversible control of RNA conformation and activity are important for understanding RNA behavior and for potential therapeutic applications. However, achieving reversible and site-specific control of RNA structure, especially at the single-nucleotide level, remains challenging. In this dissertation, I developed and applied azobenzene-modified nucleotides as a chemical tool to enable optical and spatial control of RNA structure and function.

The first part of this dissertation focuses on establishing …

Hepatitis C Among Persons Who Inject Drugs In New York State: Progress Towards Elimination, Meredith A. Barranco

Electronic Theses & Dissertations (2024 - present)

Background: Hepatitis C virus (HCV) infection is one of the leading causes of liver disease in the United States (US) and worldwide. In the United States today, HCV is transmitted primarily through injection drug use (IDU) and therefore disproportionately impacts persons who inject drugs (PWID), a population with a range of complex social and health needs. HCV is not vaccine-preventable but can be cured in over 90% of cases with an 8–12-week course of daily direct-acting antiviral (DAA) medication. Since approval of curative medications in 2014, various jurisdictions have developed plans to eliminate HCV. In 2021, the New York State …

Test-Retest Reliability And Validity Of The Gas Exchange Threshold, Erik Ryan Snell Mr.

Theses and Dissertations--Kinesiology and Health Promotion

Theoretically, the gas exchange threshold (GET) demarcates the moderate and heavy intensity domains, whereby exercise performed at and below the GET results in a change in oxygen consumption ([ΔVO₂] ≤ 200 mL), and exercise above the GET results in a slow component (ΔVO₂ > 200 mL). This study examined the reliability and validity of the GET. 14 subjects performed two maximal graded exercise tests (GXTs) to determine the GET and its reliability. The minimal difference (MD = 21W) was applied to determine the GET above (GET_+MD) and below (GET_-MD) power outputs for 30 min …

Bringing Pandemic Science To The Classroom: Building Public Health Capacity At A Rural Kentucky High School, Sahar Alameh, Anna G. Hoover, James W. Keck, Scott M. Berry, Sagan Goodpaster, Savannah Tucker, Ashley Goodin

Science, Technology, Engineering, and Mathematics (STEM) Education Faculty Publications

In response to the COVID-19 pandemic, a multidisciplinary team at the University of Kentucky developed an interdisciplinary science, technology, engineering, and mathematics and environmental health unit—the Wastewater Assessment for Coronavirus in Kentucky: Implementing Enhanced Surveillance Technology (WACKIEST) Unit—for high school students in summer 2022. This case study outlines the WACKIEST Unit, which focused on wastewater surveillance and COVID-19, the obstacles faced during development and recruitment, and implementation of the WACKIEST Unit in conjunction with a rural wastewater surveillance initiative. The unit was implemented in spring 2023 at a rural high school in Kentucky, spanning 12 days and engaging 190 students. …

Holographic Sensors For The Detection Of Volatile Organic Compounds, Graceson Antony

Doctoral

Volatile organic compound (VOC) monitoring at parts-per-million (ppm) concentration levels is essential for occupational safety, indoor air quality, and regulatory compliance. Although holographic gas sensors have been widely investigated, most operate in reflection mode as qualitative visual indicators, with limited quantitative evaluation of sensing mechanisms and scarce systematic demonstrations of repeatable multi-cycle validation for VOCs at ppm concentrations. A physics-based optimisation framework for transmission-mode holographic gas sensors which can bridge this gap has remained largely undeveloped.

This thesis presents the development and optimisation of real-time transmission-mode volume phase transmission holographic grating (VPTHG) sensors for ppm-level VOC detection. A comprehensive theoretical …

Access To Digital Health Technologies: Personalized Framework And Global Perspectives, Sanjiv M Narayan, Mina K Chung, Demilade Adedinsewo, Luisa C C Brant, Leslie L Davis, David Duncker, Jennifer L Hall, Janet K Han, Carolyn S P Lam, Eldrin Lewis, Joseph Loscalzo, Manlio F Márquez, Vasiliki Rahimzadeh, Fatima Rodriguez, Prashanthan Sanders, Emma Svennberg, Kenneth Stein, Mintu Turakhia, Clyde Yancy, Antonis A Armoundas

Center for Medical Ethics and Health Policy Staff Publications

The emergence and rapid adoption of digital health technologies (DHT) present unprecedented opportunities to democratize and reduce disparities in health care by monitoring health and disease at the point of care in all patients. However, limited access to DHT is becoming a major obstacle to realizing these goals. Access to DHT is influenced not only by well-recognized social determinants of health, but also by digital determinants of health, such as digital literacy and the need for broad access to digital infrastructure, as well as commercial and economic factors. Addressing these challenges and designing unbiased systems of care are essential to …

Managing Multi-Drug Resistance: An Evolutionary Game Theory And Optimal Control Approach, Shukhrat Nasrulloev

Theses and Dissertations

Multi-drug resistance is an evolutionary process in which treatment eliminates sensitive cells, allowing resistant clones to dominate. This thesis investigates this process using a framework integrating population dynamics, evolutionary game theory, and optimal control theory. We develop a two-population logistic growth model describing competition between drug-sensitive and drug-resistant cells under treatment, construct dose-dependent payoff matrices and replicator dynamics to characterize evolutionary competition, and derive a critical drug level D_crit = (r_S - rR)/(dS - d_R) at which resistant cells gain a fitness advantage. An optimal control problem is formulated via Pontryagin's Maximum Principle to identify schedules …

Enhancing Hospital Length Of Stay Using Ai Agent Modular Capabilities, Dami Fred

Theses and Dissertations

Hospital Length of Stay (LOS) analysis is essential for managing hospital efficiency and financial performance, yet the analytical depth required remains inaccessible to many organizations due to technical and resource constraints. This thesis introduces the AI Agent Modular Capabilities (AIAM) framework, which decomposes LOS analysis into discrete, codifiable capabilities integrated into a single skill activatable with one prompt. Seven AI Agent Modular Capabilities were developed using a Work Breakdown Structure and tested against a simulated hospital scenario across three successive skill versions. Results demonstrate that the packaged AIAM skill produces comprehensive, consistent, multi-section LOS analyses from a single interaction, outperforming …

Improving Compliance With Safe Sleep Guidelines For Vulnerable Patients In A Community Safety Net Hospital Neonatal Intensive Care Unit, Andrew Beverstock, Samantha Carlton, Hillary Lee, Thomas Lu, Kelsi Morgan, Ashlee Smith-Patel, Kelli Phillips, Joseph Hagan, Pablo Lohmann, Caraciolo Fernandes, Lisa Owens, Daniela Dinu

Faculty, Staff and Students Publications

Objectives: Congenital diaphragmatic hernia (CDH) often coexists with fetal growth restriction (FGR). The observed-to-expected (O/E) total fetal lung volume (TFLV) is used to assess CDH severity, predict outcomes, and direct fetal interventions. Expected TFLV measurements traditionally rely only on gestation age (GA). This simulation assesses how incorporating weight-adjusted GA norms affects O/E TFLV calculations in patients with isolated CDH and FGR.

Methods: A simulated dataset (n=1,005) utilized published mean fetal weight and TFLV references. Computer-generated variables included observed weights (3rd-10th %ile), O/E TFLV (10-65 %), and percent liver herniation (0-42 %). GA estimates were corrected by weight and used to …