Biomedical Informatics Commons^™

Agent-Based Modeling Of Cellular Dynamics In Adoptive Cell Therapies, Yujia Wang

Dissertations and Theses (Open Access)

Adoptive cell therapies (ACT) have shown promising progress in combating cancer, but clinical responses remain heterogeneous. Key determinants, including the functional states of infused cells, tumor–immune interactions, and dosing strategies, are difficult to resolve experimentally in the dynamic and heterogeneous tumor microenvironment, limiting optimization of ACT products and treatment regimens. To address the gap, we developed ABMACT (Agent-Based Model for Adoptive Cell Therapies), a computational framework that reconstruct key cellular functions, interactions, and molecular signatures to recapitulate cell population dynamics associated with differential treatment responses. ABMACT encodes autonomous “virtual cells” using literature-informed rules calibrated with experimental data, enabling simulation of …

Elucidating The Multi-Omics Of Early-Onset Colorectal Cancer, Jumanah Alshenaifi

Dissertations and Theses (Open Access)

The incidence and mortality rates of sporadic early-onset colorectal cancer have increased in recent decades, but there is no clear etiological basis for this trend. EOCRC is commonly defined as colon and rectal cancers diagnosed before the age of 50 years. The rising incidence of EOCRC has made it the second most common cancer and the third leading cause of cancer death in this age group. The rising incidence of EOCRC is also documented internationally in more than 20 countries across different continents. Clinically, EOCRC has a distinct, more aggressive clinical profile than LOCRC. While approximately 15% of EOCRC cases …

Leveraging Observational And Rct Data For Understanding Interventions’ Efficacy: Applications In Progressive And Acute Neurological Diseases, Yaobin Ling

Dissertations and Theses (Open Access)

The advancement of drug repurposing for progressive and acute neurological diseases is hampered by the limitations of randomized clinical trials (RCTs) and observational data. This dissertation presents a comprehensive framework to integrate data-driven insights from multiple sources, including observational studies, RCTs, and synthetic data generation, to overcome these challenges.

The first study focuses on estimating treatment effects on the population level, which investigates the effects of routine and high-dose influenza vaccines on the risk of Alzheimer’s Disease and Related Dementias (ADRD) through a trial emulation framework applied to health claims data, addressing biases inherent in observational studies. The second study …

Standardizing Social Determinants Of Health Factors From Heterogeneous Sources To Improve Data Fairness, Yifang Dang

Dissertations and Theses (Open Access)

Social Determinants of Health (SDoH) significantly influence health outcomes, yet their representation in computational models remains fragmented. This dissertation addresses this gap by constructing an SDoH ontology (SDoHO), leveraging it to improve large language model (LLM) performance, and using LLMs to extract new knowledge and enrich the ontology. The overarching goal is to establish a feedback loop where ontology development enhances LLM-based extraction, and LLM-derived insights refine and expand the ontology. The methodology is structured across three aims: (1) ontology construction, (2) ontology-assisted LLM enhancement, and (3) LLM-driven ontology enrichment, with a focus on Alzheimer’s Disease and Related Dementias (ADRD). …

Computer-Aided Integrated Rehabilitation For Post-Stroke Patients Using Deep Learning Techniques, Kaichen Tang

Dissertations and Theses (Open Access)

Stroke is a leading cause of long-term disability, often requiring intensive rehabilitation and frequent clinical assessments such as the Fugl-Meyer Assessment. However, traditional in-person evaluations are resource-heavy and difficult to scale, limiting access for many patients. Additionally, monitoring vital signs like blood pressure and oxygen saturation typically depends on specialized equipment, leading to fragmented care and incomplete recovery insights. Even when assessments and monitoring are available, patients often struggle to maintain high-quality, intensive exercise routines without supervision, further limiting rehabilitation outcomes.

To address these challenges, this dissertation proposes an AI-driven, smartphone-based framework that integrates automated motor function assessment, non-invasive vital …

Leveraging And Advancing The Foundation Models For Clinical Trajectory Analysis Based On Electronic Health Record Data, Jianping He

Dissertations and Theses (Open Access)

Enhancements in foundation models have provided significant potentials for clinical applications. This dissertation leverages and advances foundation models for a range of clinical tasks using electronic health record (EHR) data, demonstrating their applicability in Clinical Temporal Relation Extraction (CTRE), disease prediction, and patients trajectory analysis.

Aim 1 is to efficiently adapt large language models (LLMs) for CTRE in both full data and few-shot settings. This study leveraged four LLMs: GatorTron-Base, GatorTron-Large, LLaMA3.1, and MeLLaMA. The proposed fine-tuning strategies include: (a) standard fine-tuning; (b) hard-prompting; (c) soft-prompting; (d) Low-Rank Adaptation (LoRA). We found that nearly all proposed fine-tuning strategies outperformed existing …

Precision Drug Dosing And Disease Risk Prediction: Advanced Deep Learning Artificial Intelligence Approaches For Precision Medicine Using Structured Electronic Health Records Data, Bingyu Mao

Dissertations and Theses (Open Access)

Advancements in precision medicine increasingly rely on data-driven approaches to improve clinical decision-making. This work presents three interconnected studies that leverage deep learning, reinforcement learning, and comparative modeling to address key challenges in precision drug dosing and disease risk prediction. Together, these contributions offer novel computational frameworks that enhance model performance, improve dosing strategies, and guide model selection for clinical predictive tasks.

To improve individualized vancomycin therapeutic drug monitoring (TDM), the first study introduces PKRNN-2CM, a novel deep learning framework that integrates a two-compartment pharmacokinetic (PK) model with recurrent neural networks (RNNs). While one-compartment models are commonly used in clinical …

Computational Methods For Enhancing The Quality And Interoperability Of Biomedical Terminologies, Xubing Hao

Dissertations and Theses (Open Access)

Biomedical ontologies or terminologies not only serve as a part of the metadata standards for describing data in the FAIR Data Principles (Findable, Accessible, Interoperable, Reusable), but also play a vital role in downstream applications such as cohort identification from electronic health records (EHR). However, there are two critical barriers that may lead to ambiguity, complexity, and inaccuracies in such ontology-based downstream applications. The first barrier is the quality of the ontology. Despite efforts by ontology curators to ensure ontology accuracy and comprehensiveness, errors and inconsistencies are unavoidable. The second barrier is the semantic heterogeneity since human experts may use …

Advancing Genetic Association Discovery In Brain Mri Using Unsupervised And Self-Supervised Deep Learning: Exploring Learning Dynamics, Region-Specific Features, And Spatially Resolved Representations, Sheikh Muhammad Saiful Islam

Dissertations and Theses (Open Access)

Deep learning has unlocked significant potential for advancing the discovery of genetic associations in imaging genetics, particularly in brain imaging using T1-weighted Magnetic Resonance Imaging (MRI). Traditional methods for this task often relied on hand-crafted or semi-automated feature extraction, followed by genetic association studies utilizing these features. While effective, these approaches are limited by their lack of data-driven exploration and the generation of features with limited informativeness.

Unsupervised deep learning, in particular, has emerged as a powerful alternative, addressing some of these limitations by enabling automated and data-driven feature discovery. Recent research in this domain has primarily focused on adapting …

Harnessing Knowledge And Data For Clinical Information Extraction In The Era Of Large Language Models, Yan Hu

Dissertations and Theses (Open Access)

The rapid digitization of healthcare records has led to the widespread adoption of Electronic Health Records (EHRs), which contain rich, unstructured clinical notes. These notes hold valuable information for patient care and clinical research, but their complexity and unstructured nature pose significant challenges for effective utilization. Clinical Information Extraction (IE) aims to bridge this gap by transforming unstructured text into structured data, enabling automated analysis. Traditional Natural Language Processing (NLP) techniques, such as Named Entity Recognition (NER), have been widely used for clinical IE, but recent advancements in Large Language Models (LLMs) like GPT-3.5, GPT-4, and LLaMA have opened new …

Accelerating Drug Repurposing And Target Discovery Using Deep Learning, Kohong Lin

Dissertations and Theses (Open Access)

Drug discovery is a long-lasting and expensive process. Computational approaches, particularly deep learning techniques, offer the potential to accelerate this process by integrating diverse perspectives from drug discovery theories and capturing intricate patterns within large, multimodal datasets. This dissertation explores deep learning methodologies to accelerate drug repurposing and genetic target discovery. The first aim focuses on integrating multimodal data, including chemical structures, disease genetics, and systems biology, into comprehensive disease knowledge graphs, followed by applying graph neural networks (GNNs) to prioritize repurposable drug candidates. The second aim is to develop a heterogeneous GNN-based approach capable of modelling distinct semantic relationships …

Comprehensive Analysis Of Adverse Events Following Covid-19 Vaccination: Insights From Diverse Data Sources, Yiming Li

Dissertations and Theses (Open Access)

This dissertation investigates adverse events (AEs) associated with COVID-19 vaccinations through a multi-faceted approach involving structured and unstructured data. The study is organized into three specific aims, each contributing to a comprehensive understanding of vaccine safety. Aim 1 focuses on the temporal and spatial analysis of AEs reported in the Vaccine Adverse Event Reporting System (VAERS). We performed a detailed temporal analysis to detect patterns over time, revealing a significant increase in reported AEs shortly after the vaccine rollout. Spatial analysis highlighted regional variations in AE reporting, with higher frequencies observed in middle and north regions of the United States …

Cardiovascular Biomarkers Using Deep Learning And Retinal Imaging For The Assessment Of Systemic Disease, Ivan Coronado

Dissertations and Theses (Open Access)

Fundus photography is a radiation-free, non-invasive imaging modality widely employed to assess both ocular and systemic diseases in population-level applications. Traditional methods for extracting cardiovascular biomarkers rely on quantifying vascular features in these images to identify indicators of disease. However, these approaches often depend on manual clinical expertise, which can be costly and time-consuming, making them impractical for large-scale datasets. Deep learning offers a compelling alternative to traditional techniques by enabling the automated processing of extensive datasets with high accuracy. Despite its advantages, deep learning models often function as "black boxes," making it challenging to interpret the features they prioritize …

Single Cell And Spatial Analysis Characterize Metabolic Dpep1+ Fibroblasts In Pdac, Yuanyuan Zhu

Dissertations and Theses (Open Access)

Pancreatic ductal adenocarcinoma (PDAC) is highly malignant and exhibits aggressive progression patterns, resists conventional treatments, and poses significant challenges to patient survival, necessitating urgent research and development of novel therapeutic approaches. Understanding cancer-associated fibroblasts (CAF) metabolism reprogramming in PDAC tumor microenvironment (TME) may uncover novel therapeutic targets. Here, we used single cell and spatial transcriptomics to comprehensively characterize the TME content of human PDAC. We characterized CAFs metabotypes and a novel CAF population expressing DPEP1, COMP, CST1, which involved in glutathione metabolism, termed "gluCAFs” and was associated with poor clinical outcomes and advanced PDAC stages. We also validate the existence …

Multi-Omic Single-Cell Integration For Understanding T Cell Responses In Acute Myeloid Leukemia, Poonam Desai

Dissertations and Theses (Open Access)

In recent years, translational initiatives have gained significant traction within the medical community. Clinical parameters alone have been insufficient to fully understand the intricate mechanisms governing patient responses to disease and therapy. Additionally, single-cell technologies have rapidly advanced to a point where generation of large patient-based datasets is financially and logistically feasible. The integration of clinical information with multi-omic single-cell technologies enables the formation of data-driven hypotheses pertaining to the mechanisms of disease progression and therapeutic resistance. Acute Myeloid Leukemia (AML) is a rapidly-progressing cancer of the bone marrow with poor prognoses and dismal outcomes. Of the adult patients that …

Designing Recommendation Systems For Identification And Reduction Of Unnecessary Blood Tests, Tongtong Huang

Dissertations and Theses (Open Access)

Blood testing is an indispensable tool to check the patient's health status. However, the overutilization of lab tests in healthcare settings is a prevalent issue that can lead to redundant information, increased patient risk, and financial strain on healthcare resources. This dissertation presents novel approaches to optimizing lab test utilization by applying deep learning models. The primary objective is to develop and validate methods that accurately predict and reduce unnecessary blood tests.

The study introduces a “selective” mechanism that quantifies the predictability of future lab tests, allowing for the selective reduction of unnecessary tests in the context of specific clinical …

Improving Distributed Health Information Technology Integration Through Enriched Context In Sociotechnical System Components, Jeritt Thayer

Dissertations and Theses (Open Access)

The design and architecture of health information technology (HIT) are in the process of a transformative shift. Monolithic code bases, which are several systems intertwined into a single program, are being split into multiple distributed programs that communicate across information networks. Thus far, only sparse knowledge exists about the challenges of distributed HIT, and the interaction of these architectures with other factors of the sociotechnical system, such as clinical content, is not well understood. Existing sociotechnical models describe the components within a healthcare system and the connections between components, but the types of relationships between each component are underspecified. Within …

Acute Pain Prediction In Oral Cavity And Oropharyngeal Cancer Patients Receiving Radiation Therapy, Vivian Salama

Dissertations and Theses (Open Access)

Oral-Cavity and oropharyngeal cancers (OC/OPC) are types of head and neck cancers that are increasing in incidence domestically. Radiation therapy (RT) is crucial in OC/OPC management. Pain is a common and challenging symptom for most patients during therapy, as nearly all patients undergoing locoregional RT in OC/OPC require analgesia for acute iatrogenic pain. Moreover, about 45% of long-term survivors report chronic pain, with more than 10% exhibiting severe chronic pain. Pain control is challenging due to the multifactorial clinical, molecular, and cellular etiology of cancer/therapy pain, as well as variation in pain assessment and the non-uniform management of pain between …

Radiation-Induced Lymphopenia: Understanding, Predictive Modelling And Developing Photon And Proton-Based Mitigation Strategies, Yan Chu

Dissertations and Theses (Open Access)

It is well recognized that the effectiveness of radiotherapy (RT) requires an intact adaptive immune system, while lymphocytes are highly radiosensitive and are prevalent in the “dose bath” of radiation surrounding the tumor volume. Furthermore, it has been shown that, for nearly all disease sites, radiation-induced lymphopenia (RIL) is associated with poor outcomes. Recently, we observed compelling evidence of significant differences in the lymphocyte-sparing effects of proton therapy (PT) vs. photon (or x-ray) therapy (XRT) attributable to the differences in magnitudes of the dose baths of the two modalities. In addition, previous work has further demonstrated that both patient-specific and …

An Informatics Framework For Representing, Detecting, And Measuring Citations Of Biomedical Datasets, Xu Zuo

Dissertations and Theses (Open Access)

Biomedical research is inherently data-intensive, emphasizing the necessity of making data findable, accessible, interoperable, and reusable (FAIR) to expedite scientific breakthroughs. Despite the importance, data creators often do not receive sufficient recognition and lack the motivation to publish datasets in accordance with FAIR principles, primarily due to inadequate incentives. Citations serve as a means to attribute credit for dataset creation, track dataset usage, and assess the impact of data. Implementing standardized data citations could significantly enhance the discoverability of data and foster the maintenance of high-quality datasets. Initiatives like DataCite and the FAIRsharing community have been instrumental in addressing this …

Decoding Disease Mechanisms: Unraveling Large-Scale Biological Data For Novel Therapeutic Target Discovery, Yuntao Yang

Dissertations and Theses (Open Access)

This dissertation leverages large biological datasets and data-driven research to enhance our understanding of complex human diseases, deploying a unified narrative across three interconnected bioinformatics studies. Each study targets a different biological level, including genes, proteins, cells, and tissues, to uncover disease mechanisms and speed up the discovery of potential therapeutic targets.

The first study addresses gene-level analysis in the context of bladder cancer. It integrates gene expression data from lab models with clinical survival data to identify new therapeutic targets. This research pinpoints the IL6/JAK/STAT3 signaling pathway as a promising target for treating SMARCB1-deficient bladder cancer, demonstrating how combining …

Single Cell Proteogenomics Analysis Of Aml Samples Treated With Decitabine And Venetoclax Reveals Divergent Treatment Escape Mechanisms, Yi June Kim

Dissertations and Theses (Open Access)

Venetoclax is a small molecule inhibitor targeting BCL-2. Since its approval, the combination therapy of hypomethylating agents and Venetoclax (HMA+Ven) has become a standard of care for acute myeloid leukemia (AML) patients unfit for intensive chemotherapy. Nonetheless, clinical challenges persist as patients either do not respond or eventually relapse, and the underlying mechanisms of these outcomes are not yet fully understood. Prior studies have identified genetic factors (TP53 and RTK/RAS pathway mutations) and phenotypic factors (monocytic differentiation) to be associated with resistance. In this light, we hypothesized that integrative assessment of genetic and phenotypic factors could further elucidate the unknown …

Advancing Precision Medicine: Unveiling Disease Trajectories, Decoding Biomarkers, And Tailoring Individual Treatments, Yanfei Wang

Dissertations and Theses (Open Access)

Chronic diseases are not only prevalent but also exert a considerable strain on the healthcare system, individuals, and communities. Nearly half of all Americans suffer from at least one chronic disease, which is still growing. The development of machine learning has brought new directions to chronic disease analysis. Many data scientists have devoted themselves to understanding how a disease progresses over time, which can lead to better patient management, identification of disease stages, and targeted interventions. However, due to the slow progression of chronic disease, symptoms are barely noticed until the disease is advanced, challenging early detection. Meanwhile, chronic diseases …

Toward Nonparametric Propensity Score Estimation With Guaranteed Covariate Balance, Yan Li

Dissertations and Theses (Open Access)

Establishing clear causality between exposures and outcomes is often complicated by confounders in observational studies, which leads to imbalance in covariate distributions between treatments and biased treatment effect inference. The propensity score (PS) has been widely used to adjust this covariate imbalance in observational data. However, the propensity score analysis methods rely on a correctly specified parametric PS model. When the model is misspecified, the covariate imbalance may occur, which leads to biased estimation of the treatment effect. Therefore, it is necessary to study how to improve the model misspecification in propensity score analysis.

My Ph.D. dissertation consists of three …

Multiparametric Magnetic Resonance Imaging Artificial Intelligence Pipeline For Oropharyngeal Cancer Radiotherapy Treatment Guidance, Kareem Wahid

Dissertations and Theses (Open Access)

Oropharyngeal cancer (OPC) is a widespread disease and one of the few domestic cancers that is rising in incidence. Radiographic images are crucial for assessment of OPC and aid in radiotherapy (RT) treatment. However, RT planning with conventional imaging approaches requires operator-dependent tumor segmentation, which is the primary source of treatment error. Further, OPC expresses differential tumor/node mid-RT response (rapid response) rates, resulting in significant differences between planned and delivered RT dose. Finally, clinical outcomes for OPC patients can also be variable, which warrants the investigation of prognostic models. Multiparametric MRI (mpMRI) techniques that incorporate simultaneous anatomical and functional information …

Leveraging Digital Technologies For Management Of Peripartum Depression To Mitigate Health Disparities, Alexandra Zingg

Dissertations and Theses (Open Access)

Health disparities are adverse, preventable differences in health outcomes that affect disadvantaged populations. Examples of health disparities can be seen in the condition of peripartum depression (PPD), a mood disorder affecting approximately 10-15% of peripartum women. For example, Hispanic and African-American women are less likely to start or continue PPD treatment. Digital health technologies have emerged as practical solutions for PPD care and self-management. However, existing digital solutions lack an incorporation of behavior theory and distinctive information needs based on women’s personal, social, and clinical profiles. Bridging this gap, I adapt Digilego, an integrative digital health development framework consisting of: …

Social Network Analysis Of Online Support Communities For Adolescent And Young Adult Cancer Survivors, Carlos Perez Aldana

Dissertations and Theses (Open Access)

There are an estimated 633,000 adolescent and young adult (AYA) cancer survivors in the U.S. and nearly 89,500 AYAs are diagnosed with cancer every year. Cancer creates developmental and life stage disruptions, which result in multiple survivorship challenges, particularly among AYAs. Despite the advances made in cancer oncology and survivorship care, AYA cancer survivors continue to face diverse and unique psychosocial needs. Research suggests that online support communities have the potential to positively impact psychosocial care by providing AYA cancer survivors with access to social support which can help them successfully transition from treatment back to normal life as well …

Identifying Risk Factors For Anchoring Bias During Emergency Department Transitions Of Care, Roni Matin

Dissertations and Theses (Open Access)

Transitions of care have been associated with breakdowns in communication and medical errors. In emergency departments (ED) these handoffs are typically known as sign outs. Sign outs provide continuity of care for ED patients whose diagnosis and care fall across shift changes. They are short interactions where pertinent information and responsibility for the patient is transferred to the physician assuming care for them. However, these exchanges may also be an opportunity for cognitive biases to be transferred or introduced, leading to erroneous decision making. Anchoring bias is known to have a significant impact on clinical decision making. Yet, little is …

Computer-Aided Diagnosis For Melanoma Using Ontology And Deep Learning Approaches, Xinyuan Zhang

Dissertations and Theses (Open Access)

The emergence of deep-learning algorithms provides great potential to enhance the prediction performance of computer-aided supporting diagnosis systems. Recent research efforts indicated that well-trained algorithms could achieve the accuracy level of experienced senior clinicians in the Dermatology field. However, the lack of interpretability and transparency hinders the algorithms’ utility in real-life. Physicians and patients require a certain level of interpretability for them to accept and trust the results. Another limitation of AI algorithms is the lack of consideration of other information related to the disease diagnosis, for example some typical dermoscopic features and diagnostic guidelines. Clinical guidelines for skin disease …

Enhance Representation Learning Of Clinical Narrative With Neural Networks For Clinical Predictive Modeling, Yuqi Si

Dissertations and Theses (Open Access)

Medicine is undergoing a technological revolution. Understanding human health from clinical data has major challenges from technical and practical perspectives, thus prompting methods that understand large, complex, and noisy data. These methods are particularly necessary for natural language data from clinical narratives/notes, which contain some of the richest information on a patient. Meanwhile, deep neural networks have achieved superior performance in a wide variety of natural language processing (NLP) tasks because of their capacity to encode meaningful but abstract representations and learn the entire task end-to-end. In this thesis, I investigate representation learning of clinical narratives with deep neural networks …