Development, Validation, And Diagnostic Performance Of A Novel Radiomic Model For Predicting Prostate Cancer Recurrence, Linda M. Huynh

Theses & Dissertations

Multi-parametric magnetic resonance imaging (MP-MRI)-derived radiomics have been shown to capture sub-visual patterns for the quantitative characterization of prostate cancer (PC) phenotypes. The present dissertation seeks to develop, evaluate, and compare the performance of an MRI-derived radiomic model for the prediction of PC recurrence following definitive treatment with radical prostatectomy (RP).

MP-MRI was obtained from 339 patients who had a minimum of 2 years follow-up following RP at three institutions. The prostate was manually delineated as the region of interest and 924 radiomic features were extracted. All features were evaluated for stability via intraclass correlation coefficient (ICC) and image normalization …

Can Mirna Be The Missing Link Between Parkinson’S Disease And Pesticides?, Fatma Gobba

Theses and Dissertations

Parkinson’s disease (PD) is a common neurodegenerative condition that leads to significant morbidity and a decline in the quality of life. It develops as a consequence of the loss of dopaminergic neurons in the substantia nigra pars compacta. Nevertheless, the development of PD is influenced by environmental factors, and the intricate nature of these relationships is further complicated by a multitude of factors, including the genetic backgrounds that are specific to populations and variations in environmental exposures, such as pesticides. Pesticides, consisting of a diverse family of chemicals commonly used in both agricultural and household settings to protect crops against …

Interpretable Mechanistic And Machine Learning Models For Pre-Dicting Cardiac Remodeling From Biochemical And Biomechanical Features, Anamul Haque

All Dissertations

Biochemical and biomechanical signals drive cardiac remodeling, resulting in altered heart physiology and the precursor for several cardiac diseases, the leading cause of death for most racial groups in the USA. Reversing cardiac remodeling requires medication and device-assisted treatment such as Cardiac Resynchronization Therapy (CRT), but current interventions produce highly variable responses from patient to patient. Mechanistic modeling and Machine learning (ML) approaches have the functionality to aid diagnosis and therapy selection using various input features. Moreover, 'Interpretable' machine learning methods have helped make machine learning models fairer and more suited for clinical application. The overarching objective of this doctoral …

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

Dissertations & 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 …

Operationalizing The Datagauge Framework In A Health Information Exchange Utilizing Hepatitis C Data, Edward Yao

Translational Projects (Open Access)

This project aims to implement the DataGauge framework in a health information exchange (HIE) setting as a proof of concept. The modified DataGauge framework, described by Diaz-Garelli et al. (2019), is utilized to test its functionality and applicability with any dataset. The specific objective of the project is to determine the number of hepatitis C-positive tests within the HIE. The implementation involved multiple iterations following the DataGauge framework's steps for data extraction and analysis. Five iterations were conducted, resulting in both successful and failed queries based on the validity of the data standards. The findings revealed that the HIE, in …

Sctiger: A Deep-Learning Method For Inferring Gene Regulatory Networks From Single-Cell Gene Expression Data, Madison Dautle

Theses and Dissertations

Inferring gene regulatory networks (GRNs) from single-cell RNA-sequencing (scRNA-seq) data is an important computational question to reveal fundamental regulatory mechanisms. Although many computational methods have been designed to predict GRNs, none work on condition specific GRNs by directly using paired datasets of case versus control experiments, common in diverse biological research projects. We present a novel deep-learning based method, scTIGER, for GRN detection by using the co-dynamics of gene expression. scTIGER also employs cell type-based pseudotiming, an attention-based convolutional neural network method, and permutation-based significance testing to infer GRNs from gene modules. We first applied scTIGER to scRNA-seq datasets of …

A Quantitative Visualization Tool For The Assessment Of Mammographic Risky Dense Tissue Types, Margaret R. Mccarthy

Electronic Theses and Dissertations

Breast cancer is the second most occurring cancer type and is ranked fifth in terms of mortality. X-ray mammography is the most common methodology of breast imaging and can show radiographic signs of cancer, such as masses and calcifcations. From these mammograms, radiologists can also assess breast density, which is a known cancer risk factor. However, since not all dense tissue is cancer-prone, we hypothesize that dense tissue can be segregated into healthy vs. risky subtypes. We propose that risky dense tissue is associated with tissue microenvironment disorganization, which can be quantified via a computational characterization of the whole breast …

Genome-Scale Methylation Analysis In Blood And Tumor Identifies Immune Profile, Age Acceleration, And Dna Methylation Alterations Associated With Bladder Cancer Outcomes, Ji-Qing Chen

Dartmouth College Ph.D Dissertations

Bladder cancer patients receive frequent screening due to the high tumor recurrence rate (more than 60%). Nowadays, the conventional monitoring method relies on cystoscopy which is highly invasive and increases patient morbidity and burden to the health care system with frequent follow-up. As a result, it is urgent to explore novel markers related to the outcomes of bladder cancer. Immune profiles have been associated with cancer outcomes and may have the potential to be biomarkers for outcomes management. However, little work has been conducted to investigate the associations of immune cell profiles with bladder cancer outcomes. Here, I utilized the …

Towards Generalizable Machine Learning Models For Computer-Aided Diagnosis In Medicine, Yiyang Wang

College of Computing and Digital Media Dissertations

Hidden stratification represents a phenomenon in which a training dataset contains unlabeled (hidden) subsets of cases that may affect machine learning model performance. Machine learning models that ignore the hidden stratification phenomenon--despite promising overall performance measured as accuracy and sensitivity--often fail at predicting the low prevalence cases, but those cases remain important. In the medical domain, patients with diseases are often less common than healthy patients, and a misdiagnosis of a patient with a disease can have significant clinical impacts. Therefore, to build a robust and trustworthy CAD system and a reliable treatment effect prediction model, we cannot only pursue …

Feature Selection From Clinical Surveys Using Semantic Textual Similarity, Benjamin Warner

McKelvey School of Engineering Theses & Dissertations

Survey data collected from human subjects can contain a high number of features while having a comparatively low quantity of examples. Machine learning models that attempt to predict outcomes from survey data under these conditions can overfit and result in poor generalizability. One remedy to this issue is feature selection, which attempts to select an optimal subset of features to learn upon. A relatively unexplored source of information in the feature selection process is the usage of textual names of features, which may be semantically indicative of which features are relevant to a target outcome. The relationships between feature names …

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

Dissertations & 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 …

Mapping Next Generation Sequence Data With Bwa (Burrows-Wheel Aligner) On Galaxy Software, Rabeh Z. Omar

Honors College Theses

Advancement of next-generation sequencing technologies introduces a vast amount of data which has become a challenge for researchers to organize and sequence data sets. BWA (Burrows-Wheeler Aligner) is one of the widely used software for aligning and mapping sequencing data against a reference genome. In my thesis, I present a comprehensive guide for analyzing genome sequences using BWA. I discuss the various steps involved in the process, including gathering the data, preparing the reference genome, aligning the sequences, and processing the data to visualize the results.

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

Dissertations & 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: …

Implementing Clinical Decision Support Aimed At Reducing Co-Prescribing Of Opioids And Benzodiazepines At Adventist Healthcare Maryland, Monica Coley

Translational Projects (Open Access)

Clinical Decision Support (CDS) leverages computerized toolsets to provide condition specific guidance that aids providers in clinical decision making processes (AHRQ, 2019; AMIA, n.d.; ONC, 2018). Research has shown that applying CDS, interruptive within the electronic health record (EHR) prescribing workflow, can assist providers with avoiding unsafe medication prescribing, such as 1) multiple opioids and 2) opioid-benzodiazepine combinations (Malte et al., 2018; Smith et al., 2019, Price-Haywood et al., 2020; Nelson et al., 2022). In an effort to decrease the co-prescribing rate for 1) multiple opioids and 2) opioid-benzodiazepine combinations, Adventist HealthCare Maryland (AHC) launched a performance improvement project in …

Exploring The Use Of Bidirectional Text Messaging Reminders To Increase Colorectal Cancer Screening Rates In Patients Prescribed Cologuard®, James Harris

Translational Projects (Open Access)

Meaningfully engaging with patients through technology is becoming increasingly important in healthcare. Mailed letters, phone calls, and even one-way text messaging or some combination of these have all been utilized to communicate with patients regarding preventative healthcare screening measures, with varying degrees of success. While many studies have examined the use of bidirectional text messaging (BTM) to engage patients regarding mammograms, cervical cancer screening, and other issues, very little literature exists on BTM concerning colorectal cancer (CRC).

Therefore, this project sought to examine the impact of BTM between two primary care clinics and their respective patients who were prescribed and …

Virtual Patient/Family Communication In The Acute Care Setting, Kathleen Defigueiredo

Translational Projects (Open Access)

Patient and family-centered care strategies see patients and families as valuable healthcare team members. Such strategies thus treat these groups as essential clinical partners in providing safe, high-quality care. Participation, collaboration, and shared decision-making are central to this framework. Historically, hospitals have relied on physical presence at the bedside as a prerequisite to engaging families in the shared decision-making process. Visitor restrictions of the COVID-19 pandemic removed the primary strategy for family participation: physical presence. Healthcare organizations rapidly deployed mobile devices to help minimize the exposure of healthcare providers and provide video visits for family members. This deployment was often …

Implementation Of Telemedicine To Reduce No-Show Rates, Peter Kizza

Translational Projects (Open Access)

Missed appointments, or no-shows, are defined as “patients who neither kept nor canceled scheduled appointments” (Dayal, 2019, p.27). Missed appointments cost the United States healthcare system more than $150 billion annually. They disrupt the continuity of healthcare services, add to patients' dissatisfaction due to delays in getting new appointments, and hinder the detection and treatment of disease. The rates of missed appointments vary between countries and healthcare systems. Studies conducted previously in primary care settings found that the rate of missed appointments ranged from 5%–55% in different series in the United States. One study suggested that missed appointments are likely …

Moral Injury To Inform Analysis Of Post-Traumatic Stress Disorder, Amanda Julia Manea

Senior Theses

Post-traumatic stress disorder (PTSD) is a mental health condition that almost one out of ten veterans struggle with. Although the National Center for PTSD has made extensive progress in characterizing and developing new treatments for PTSD, most veterans still experience symptoms of PTSD following treatment. Novel avenues of investigation, such as developing algorithms to review electronic health record (EHR) data and better understanding moral injury, are being pursued to address the gap that still exists when it comes to treating veterans. Moral injury is the individual evaluation of exposure to a potentially morally injurious event (PMIE) and can lead to …

Machine Learning Methods For Computational Phenotyping Using Patient Healthcare Data With Noisy Labels, Praveen Kumar

Computer Science ETDs

Positive and Unlabeled (PU) learning problems abound in many real-world applications. In healthcare informatics, diagnosed patients are considered labeled positive for a specific disease, but being undiagnosed does not mean they can be labeled negative. PU learning can improve classification performance, and estimate the positive fraction, α, among unlabeled samples. However, algorithms based on the Selected Completely At Random (SCAR) assumption are inadequate when the SCAR assumption fails (e.g., severe cases overrepresented), and when class imbalance is substantial. This dissertation presents and evaluates new algorithms to overcome these limitations. The proposed methods outperform the state-of-art for α-estimation, enhance classification performance, …

Machine Learning Framework For Real-World Electronic Health Records Regarding Missingness, Interpretability, And Fairness, Jing Lucas Liu

Theses and Dissertations--Computer Science

Machine learning (ML) and deep learning (DL) techniques have shown promising results in healthcare applications using Electronic Health Records (EHRs) data. However, their adoption in real-world healthcare settings is hindered by three major challenges. Firstly, real-world EHR data typically contains numerous missing values. Secondly, traditional ML/DL models are typically considered black-boxes, whereas interpretability is required for real-world healthcare applications. Finally, differences in data distributions may lead to unfairness and performance disparities, particularly in subpopulations.

This dissertation proposes methods to address missing data, interpretability, and fairness issues. The first work proposes an ensemble prediction framework for EHR data with large missing …

High Body Mass Index Changes Peri-Tumor Adipose Tissue Which In Turn Promotes Triple Negative Breast Cancer, Cora Elizabeth Miracle

Theses, Dissertations and Capstones

Cancer is one of the leading causes of death worldwide, responsible for over half a million deaths each year. There are multiple risk factors associated with the development of cancer. Some of these risks include genetics, smoking, and most recently, obesity (Lewandowska et al., 2019) (De Pergola & Silvestris, 2013). Research has shown that obesity is linked to the promotion of fourteen different cancers, including aggressive triple negative breast cancer (TNBC). Patients that are obese are more likely to develop cancer (Park et al., 2014). In addition, if the patient is obese at the time of a cancer diagnosis, they …

Gut Microbial Metabolite Indole: A Stimulator Of Enteroendocrine Cell Differentiation Via Activation Of Aryl Hydrocarbon Receptor, James Hart

Theses, Dissertations and Capstones

Enteroendocrine cells (EECs) regulate energy balance and glucose homeostasis by releasing hormones in response to food intake. Dysregulated EEC differentiation is observed in obesity, while gut microbiota metabolites influence this process. Here, we investigated the role of indole, a biologically active gut microbial metabolite, in EEC differentiation through aryl hydrocarbon receptor (AhR) activation. Human intestinal organoids derived from jejunal mucosal biopsies were exposed to indole. Indole treatment significantly increased mRNA levels of chromogranin A, an EEC marker. The effect was reversed by an AhR antagonist, indicating AhR involvement. Indole also upregulated AhR target gene mRNA levels. These findings highlight the …

Knowledge Discovery On The Integrative Analysis Of Electrical And Mechanical Dyssynchrony To Improve Cardiac Resynchronization Therapy, Zhuo He

Dissertations, Master's Theses and Master's Reports

Cardiac resynchronization therapy (CRT) is a standard method of treating heart failure by coordinating the function of the left and right ventricles. However, up to 40% of CRT recipients do not experience clinical symptoms or cardiac function improvements. The main reasons for CRT non-response include: (1) suboptimal patient selection based on electrical dyssynchrony measured by electrocardiogram (ECG) in current guidelines; (2) mechanical dyssynchrony has been shown to be effective but has not been fully explored; and (3) inappropriate placement of the CRT left ventricular (LV) lead in a significant number of patients.

In terms of mechanical dyssynchrony, we utilize an …

Meta-Analytic Connectivity Modelling Of Healthy Swallowing, Chris R. Tilton

Honors Theses and Capstones

A quantitative, voxel-wise meta-analysis was performed to investigate the brain regions involved in healthy human swallowing. Studies included in the meta-analysis (1) examined water swallowing, saliva swallowing, or both, (2) included healthy, normal subjects, and (3) reported stereotaxic brain activation coordinates in standard space. Following these criteria, a systematic literature review identified 8 studies that met the criteria. An activation likelihood estimation (ALE) meta-analysis and meta-analytic connectivity modelling (MACM) analysis were performed with BrainMap software. Ten clusters with high activation likelihood were found in the bilateral precentral gyri, right insula, left declive, right medial frontal gyrus, right dorsal nucleus of …

Bioinformatic Analysis Of Proteomic And Genomic Data From Nsclc Tumors On Prognostic And Predictive Factors Of Immunotherapy Treatment, Mark Wuenschel

Theses and Dissertations--Pharmacy

Recent lung cancer research has led to advancements in molecular immunology, resulting in development of small molecule inhibitors, or immune checkpoint inhibitors, that propagate an anti-tumor T cell response. Despite increased overall and progression-free survival with reduced adverse effects compared to traditional chemotherapy, treating advanced stage lung adenocarcinoma patients remains non-curative, and evidence of non-responders or tumor recurrence to immune checkpoint inhibitor therapy is growing. Also, compared to traditional chemotherapy, there is a lower percentage of patients who respond to small molecule inhibitors. In this analysis of proteomic and genomic data from The Cancer Proteome Atlas and Global Data Commons …

Uncovering The Role Of Fat-Infiltrated Axillary Lymph Nodes In Obesity-Related Diseases With Statistical And Machine Learning Analyses, Qingyuan Song

Dartmouth College Ph.D Dissertations

The link between obesity and pathogenesis is a complex and multifaceted area of research that is yet to be fully understood. Ample evidence exists to demonstrate the direct relationship between excessive internal fat and various health conditions such as cancer, and metabolic and cardiovascular diseases. The infiltration of ectopic fat into axillary lymph nodes, observable on breast cancer screening images, has been shown to be correlated with body mass index (BMI) in women undergoing screening. This study aimed to explore the relationship between fat-infiltrated axillary lymph nodes (FIN) and obesity-related diseases, with the goal of evaluating the clinical value of …

An Explainable Deep Learning Prediction Model For Severity Of Alzheimer's Disease From Brain Images, Godwin O. Ekuma

MSU Graduate Theses

Deep Convolutional Neural Networks (CNNs) have become the go-to method for medical imaging classification on various imaging modalities for binary and multiclass problems. Deep CNNs extract spatial features from image data hierarchically, with deeper layers learning more relevant features for the classification application. The effectiveness of deep learning models are hampered by limited data sets, skewed class distributions, and the undesirable "black box" of neural networks, which decreases their understandability and usability in precision medicine applications. This thesis addresses the challenge of building an explainable deep learning model for a clinical application: predicting the severity of Alzheimer's disease (AD). AD …

A Machine Learning Approach For Predicting Patient Mortality With Heart Rate Variability Statistics, Matthew Thiele, Dario Ghersi

Theses/Capstones/Creative Projects

The prediction of patient mortality in the healthcare system provides a metric by which hospitals can better manage patient care and assess the needs of each individual patient. As such, the development of better predictive methods is vital for improving patient outcomes and overall quality of care. Heart rate variability (HRV) is a measure of the heart’s complex beating patterns, giving medical professionals additional insight into patient health. Previous research has demonstrated the potential use of heart rate variability as a metric for patient mortality prediction for various conditions, however more work is necessary to validate HRV as a metric …

Data-Driven Biomarker Panel Discovery In Ovarian Cancer Using Heterogenous Data Fusion On Exosomal And Non-Exosomal Microrna Expression Data, Paritra Mandal

All Dissertations

Ovarian cancer (OC) is an aggressive gynecological cancer and is currently the 5th leading cause of deaths due to cancer in women. High mortality rates are attributable to the vague pathogenesis and asymptomatic nature of the early stages. The development of a liquid biopsy for routine OC screening could help identify the disease at an earlier stage, making treatments more likely to be effective thereby increasing survival rates. Exosomes, small (~100nm) extracellular vesicles present in body fluids, have been shown to contain cancer-progression, onset, and related factors, making them good candidates for use in liquid biopsies. However, to date, only …

The Role Of Generative Adversarial Networks In Bioimage Analysis And Computational Diagnostics., Ahmed Naglah

Electronic Theses and Dissertations

Computational technologies can contribute to the modeling and simulation of the biological environments and activities towards achieving better interpretations, analysis, and understanding. With the emergence of digital pathology, we can observe an increasing demand for more innovative, effective, and efficient computational models. Under the umbrella of artificial intelligence, deep learning mimics the brain’s way in learn complex relationships through data and experiences. In the field of bioimage analysis, models usually comprise discriminative approaches such as classification and segmentation tasks. In this thesis, we study how we can use generative AI models to improve bioimage analysis tasks using Generative Adversarial Networks …