Biostatistics Commons^™

Beyond The Lace Index: Benchmarking Machine Learning Architectures And Explaining 30-Day Hospital Readmission Risk With Shap Analysis, Carl E. Hughes Iii

Williams Honors College, Honors Research Projects

Unplanned 30-day hospital readmission remains a fundamental challenge in US healthcare, associated with increased risk to patient recovery and representing an estimated $52.4 billion in annual expenses (Beauvais et al., 2022). While the rigorously validated LACE index serves as the clinical standard for readmission modeling, its linear structure and four explanatory variables lack the complexity to capture the high-dimensional and interactive nature of patient risk. This study utilizes an admission granularity level cohort of the MIMIC-IV database to develop and compare machine learning architectures against the baseline LACE index. Due to the imbalanced prevalence of readmission, the penalized logistic regression, …

Iso-Detr: A Novel Detection Transformer For Industrial Small Object Detection, Faisal Saeed, Anand Paul

School of Public Health Faculty Publications

Effectively detecting and assessing real-time structural and ecological parameters in contemporary manufacturing environments poses significant challenges, particularly in identifying minute objects within product images. The swift evolution of the industrial sector underscores the necessity for intelligent manufacturing environments to uphold stringent product quality standards. However, accelerating production processes at high speeds heightens the risk of defective product outcomes. This research addresses the challenges inherent in small object detection within industrial contexts, proposing an innovative detection transformer model tailored to modern manufacturing environments. The proposed model integrates a feature-enhanced multi-head self-attention block (FEMSA), merging cross-channel communication network and multiple multi-head self-attention …

Benchmarking Dna Foundation Models For Genomic And Genetic Tasks, Haonan Feng, Lang Wu, Bingxin Zhao, Chad Huff, Jianjun Zhang, Jia Wu, Lifeng Lin, Peng Wei, Chong Wu

School of Medicine Faculty Publications

The rapid evolution of DNA foundation models promises to revolutionize genomics, yet comprehensive evaluations are lacking. Here, we present a comprehensive, unbiased benchmark of five models (DNABERT-2, Nucleotide Transformer V2, HyenaDNA, Caduceus-Ph, and GROVER) across diverse genomic and genetic tasks including sequence classification, gene expression prediction, variant effect quantification, and topologically associating domain (TAD) region recognition, using zero-shot embeddings. Our analysis reveals that mean token embedding consistently and significantly improves sequence classification performance, outperforming other pooling strategies. Model performance varies among tasks and datasets; while general purpose DNA foundation models showed competitive performance in pathogenic variant identification, they were less …

Heuristic Weight Initialization For Transfer Learning In Classification Problems, Musulmon Lolaev, Anand Paul, Jeonghong Kim

School of Public Health Faculty Publications

Transfer learning is the predominant method for adapting pre-trained models on another task to new domains while preserving their internal architectures and augmenting them with requisite layers in Deep Neural Network models. Training intricate pre-trained models on a sizable dataset requires significant resources to fine-tune hyperparameters carefully. Most existing initialization methods mainly focus on gradient flow-related problems, such as gradient vanishing or exploding, or other existing approaches that require extra models that do not consider our setting, which is more practical. To address these problems, we suggest employing gradient-free heuristic methods to initialize the weights of the final new-added fully …

Predicting Sleep And Sleep Stage In Children Using Actigraphy And Heartrate Via A Long Short-Term Memory Deep Learning Algorithm: A Performance Evaluation, Robert Weaver Med, Phd, James White, Olivia Finnegan, Hongpeng Yang, Zifei Zhong, Keagan Kiely, Catherine Jones, Yan Tong, Srihari Nelakuditi, Rahul Ghosal, David E. Brown, Russell R. Pate Ph.D., Gregory J. Welk, Massimiliano De Zambotti, Yuan Wang, Sarah Burkart, Elizabeth L. Adams Phd, Bridget Armstrong, Michael Beets Med, Mph, Phd

Faculty Publications

Children's ambulatory sleep is commonly measured via actigraphy. However, traditional actigraphy measured sleep (e.g., Sadeh algorithm) struggles to predict wake (i.e., specificity, values typically < 70) and cannot predict sleep stages. Long short-term memory (LSTM) is a machine learning algorithm that may address these deficiencies. This study evaluated the agreement of LSTM sleep estimates from actigraphy and heartrate (HR) data with polysomnography (PSG). Children (N = 238, 5–12 years,52.8% male, 50% Black 31.9% White) participated in an overnight laboratory polysomnography. Participants were referred be-cause of suspected sleep disruptions. Children wore an ActiGraph GT9X accelerometer and two of three consumer wearables(i.e., Apple Watch Series 7, Fitbit Sense, Garmin Vivoactive 4) on their non-dominant wrist during the polysomnogram. LSTM estimated sleep versus wake and sleep stage (wake, not-REM, REM) using raw actigraphy and HR data for each 30-s epoch. Logistic regression and random forest were also estimated as a benchmark for performance with which to compare the LSTM results. A 10-fold cross-validation technique was employed, and confusion matrices were constructed. Sensitivity and specificity were calculated to assess the agreement between research-grade and consumer wearables with the criterion polysomnography. For sleep versus wake classification, LSTM outperformed logistic regression and random forest with accuracy ranging from 94.1to 95.1, sensitivity ranging from 94.9 to 95.9 across different devices, and specificity ranging from 84.5 to 89.6. The addition of HR improved the prediction of sleep stages but not binary sleep versus wake. LSTM is promising for predicting sleep and sleep staging from actigraphy data, and HR may improve sleep stage prediction.

Topodino: Self-Supervised Topological Representation Learning For Neuronal Morphologies, Yasser Binbisher

Master's Theses

Neuronal cell types are categorized by transcriptomic identity, yet their morphological heterogeneity defies this classification. In response, researchers have adopted unsupervised graph representation learning as a tool to reveal morphological variation within single-class transcriptomic types. However, the complex geometry of neuronal morphology—especially long axons and dense dendrites—challenges graph neural networks, which struggle with message propagation across extended structures. To mitigate this, current approaches enforce sub-sampling on neuronal graphs and omit axons entirely, sacrificing critical biological features for computational efficiency. To overcome this trade-off, this thesis introduces TopoDINO, a self-supervised, topology-aware representation learning model designed to preserve the full hierarchical organization …

Machine Learning Methods For Pattern Recognition Analysis Of Genomic And Molecular Data, Kuang Du

Dissertations

While immune therapies achieve remarkable success in treating various cancers, only a subset of patients achieves a durable clinical response, and many exhibit innate or acquired resistance. Precision medicine aims to tailor treatments to individual patients based on specific biological markers, ensuring that each patient receives the therapy most likely to be effective. Predictive biomarkers and gene signatures offer potential for more personalized treatment strategies by identifying patients likely to benefit. Recent studies suggest that gene signatures, comprising sets of genes, hold predictive value for certain clinical variables. Typically derived from biological expert knowledge, these signatures demonstrate substantial predictive potential, …

Measurement Of Breast Artery Calcification Using An Artificial Intelligence Detection Model And Its Association With Major Adverse Cardiovascular Events, Suzanne Rose, Josette Hartnett, Zachary Estep, Daniyal Ameen, Shweta Karki, Edward Schuster, Rebecca Newman, David Hsi

Department of Medicine Faculty Papers

Breast artery calcification (BAC) obtained from standard mammographic images is currently under evaluation to stratify risk of major adverse cardiovascular events in women. Measuring BAC using artificial intelligence (AI) technology, we aimed to determine the relationship between BAC and coronary artery calcification (CAC) severity with Major Adverse Cardiac Events (MACE). This retrospective study included women who underwent chest computed tomography (CT) within one year of mammography. T-test assessed the associations between MACE and variables of interest (BAC versus MACE, CAC versus MACE). Risk differences were calculated to capture the difference in observed risk and reference groups. Chi-square tests and/or Fisher's …

Random Forest For High-Dimensional Data, George Ekow Quaye

Open Access Theses & Dissertations

The exponential growth of data has led to a rapid increase in high-dimensional datasets across various domains, presenting significant challenges in data analysis, particularly in predictive modeling tasks. Traditional Random Forest (RF), while robust, often struggles with datasets filled with numerous noisy or non-informative features, compromising both performance and accuracy. This study introduces an advanced algorithm, High-Dimensional Random Forests (HDRF), designed to address these challenges by integrating robust multivariate feature selection techniques directly into the decision tree construction process. Unlike standard RF, HDRF incorporates ridge regression-based variable screening at each decision split, enhancing its ability to identify and utilize the …

Advancing Objective Mobile Device Use Measurement Inchildren Ages 6–11 Through Built-In Device Sensors: A Proof-Of-Concept Study, Olivia L. Finnegan, Robert Glenn Weaver Med, Phd, Hongpeng Yang, James W. White, Srihari Nelakuditi, Zifei Zhong, Rahul Ghosal Ph.D., Yan Tong, Aliye B. Cepni, Elizabeth L. Adams, Sarah Burkart Mph, Ph.D., Michael W. Beets Med, Mph, Phd, Bridget Armstrong Ph.D.

Faculty Publications

Mobile devices (e.g., tablets and smartphones) have been rapidly integrated into the lives of children and have impacted howchildren engage with digital media. The portability of these devices allows for sporadic, on-demand interaction, reducing theaccuracy of self-report estimates of mobile device use. Passive sensing applications objectively monitor time spent on a givendevice but are unable to identify who is using the device, a significant limitation in child screen time research. Behavioralbiometric authentication, using embedded mobile device sensors to continuously authenticate users, could be applied toaddress this limitation. This study examined the preliminary accuracy of machine learning models trained on iPad …

Time Series Models For Predicting Application Gpu Utilization And Power Draw Based On Trace Data, Dorothy Xiaoshuang Parry

Electrical & Computer Engineering Theses & Dissertations

This work explores collecting performance metrics and leveraging various statistical and machine learning time series predictive models on a memory-intensive application, Inception v3. Trace data collected using nvidia-smi measured GPU utilization and power draw for two runs of Inception3. Experimental results from the statistical and machine learning-based time series predictive algorithms showed that the predictions from statistical-based models were unable to capture the complex changes in the trace data. The Probabilistic TNN model provided the best results for the power draw trace, according to the test evaluation metrics. For the GPU utilization trace, the RNN models produced the most accurate …

Reducing Food Scarcity: The Benefits Of Urban Farming, S.A. Claudell, Emilio Mejia

Journal of Nonprofit Innovation

Urban farming can enhance the lives of communities and help reduce food scarcity. This paper presents a conceptual prototype of an efficient urban farming community that can be scaled for a single apartment building or an entire community across all global geoeconomics regions, including densely populated cities and rural, developing towns and communities. When deployed in coordination with smart crop choices, local farm support, and efficient transportation then the result isn’t just sustainability, but also increasing fresh produce accessibility, optimizing nutritional value, eliminating the use of ‘forever chemicals’, reducing transportation costs, and fostering global environmental benefits.

Imagine Doris, who is …

Deep Learning For Microbiome-Based Integrative Modeling And Microbial Biomarkers Identification, Sen Yang

Statistical Science Theses and Dissertations

The human microbiome, comprising trillions of microorganisms, plays a pivotal role in modulating host physiology via molecular and metabolite exchanges. One of the major challenges in this field lies in the effective integration of microbiome and metabolomics data, an achievement that holds the promise of substantially enhancing the precision of disease prediction. However, many datasets prioritize microbiome data while neglecting paired metabolome information. Additionally, the prevalent analytical tools face challenges in effectively merging these intricate datasets, leading to possible misinterpretations and reduced prediction accuracies.

To address these challenges, the first part of this research introduces the Microbiome-based Supervised Contrastive Learning …

Statistical And Machine Learning Approaches To Describe Factors Affecting Preweaning Mortality Of Piglets, Md Towfiqur Rahman, Tami M. Brown-Brandl, Gary A. Rohrer, Sudhendu R. Sharma, Vamsi Manthena, Yeyin Shi

Department of Agricultural and Biological Systems Engineering: Faculty Publications

High preweaning mortality (PWM) rates for piglets are a significant concern for the worldwide pork industries, causing economic loss and well-being issues. This study focused on identifying the factors affecting PWM, overlays, and predicting PWM using historical production data with statistical and machine learning models. Data were collected from 1,982 litters from the United States Meat Animal Research Center, Nebraska, over the years 2016 to 2021. Sows were housed in a farrowing building with three rooms, each with 20 farrowing crates, and taken care of by well-trained animal caretakers. A generalized linear model was used to analyze the various sow, …

Optimizing Tumor Xenograft Experiments Using Bayesian Linear And Nonlinear Mixed Modelling And Reinforcement Learning, Mary Lena Bleile

Statistical Science Theses and Dissertations

Tumor xenograft experiments are a popular tool of cancer biology research. In a typical such experiment, one implants a set of animals with an aliquot of the human tumor of interest, applies various treatments of interest, and observes the subsequent response. Efficient analysis of the data from these experiments is therefore of utmost importance. This dissertation proposes three methods for optimizing cancer treatment and data analysis in the tumor xenograft context. The first of these is applicable to tumor xenograft experiments in general, and the second two seek to optimize the combination of radiotherapy with immunotherapy in the tumor xenograft …

The Effects Of Demographics And Risk Factors On The Morphological Characteristics Of Human Femoropopliteal Arteries, Sayed Ahmadreza Razian, Majid Jadidi, Alexey Kamenskiy

UNO Student Research and Creative Activity Fair

Background: Disease of the lower extremity arteries (Peripheral Arterial Disease, PAD) is associated with high morbidity and mortality. During disease development, the arteries adapt by changing their diameter, wall thickness, and residual deformations, but the effects of demographics and risk factors on this process are not clear.

Methods: Superficial femoral arteries from 736 subjects (505 male, 231 female, 12 to 99 years old, average age 51±17.8 years) and the associated demographic and risk factor variables were used to construct machine learning (ML) regression models that predicted morphological characteristics (diameter, wall thickness, and longitudinal opening angle resulting from the …

Deep Learning-Based Technique For The Perception Of The Cervical Cancer, Aya Haraz, Hossam El-Din Moustafa, Abeer Twakol Khaleel, Ahmed H. Eltanboly

Mansoura Engineering Journal

In third-world countries, cervical cancer is the most prevalent and leading cause of death. It is affected by a variety of factors, including smoking, poor nutritional status, immunological inadequacy, and prolonged use of contraception. The Pap smear test, which is intended to prevent cervical cancer, finds preneoplastic changes in cervical epithelial cells. This study framework classified cervical cancer cells from Pap smears into five specified cell types using machine learning-based classification algorithms. The SIPaKMeD database is used in this investigation. This public dataset, which was manually cropped from 966 cluster cell images taken from Pap smear slides, has 4045 isolated …

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 …

Mathematical Models Yield Insights Into Cnns: Applications In Natural Image Restoration And Population Genetics, Ryan Cecil

Electronic Theses and Dissertations

Due to a rise in computational power, machine learning (ML) methods have become the state-of-the-art in a variety of fields. Known to be black-box approaches, however, these methods are oftentimes not well understood. In this work, we utilize our understanding of model-based approaches to derive insights into Convolutional Neural Networks (CNNs). In the field of Natural Image Restoration, we focus on the image denoising problem. Recent work have demonstrated the potential of mathematically motivated CNN architectures that learn both `geometric' and nonlinear higher order features and corresponding regularizers. We extend this work by showing that not only can geometric features …

Data-Driven Statin Initiation Evaluation And Optimization For Prediabetes Population, Muhenned A. Abdulsahib

Graduate Theses and Dissertations

This dissertation develops quantitative models to support medical decision making of statininitiation considering the uncertainty in disease progression for prediabetes patients. A mathematical model is built to help medical decision-makers take action of statin initiation under uncertainty in future prediabetes progressions. The association between cholesterol drug use, such as statin, and elevating glucose level attracted considerable amounts of attention in the literature. Statin effects on glucose vary with respect to different levels of glucose. The first chapter of this dissertation introduces the problem and an overview of the tools that will be used to solve it. In the second chapter …

Sars-Cov-2 Pandemic Analytical Overview With Machine Learning Predictability, Anthony Tanaydin, Jingchen Liang, Daniel W. Engels

SMU Data Science Review

Understanding diagnostic tests and examining important features of novel coronavirus (COVID-19) infection are essential steps for controlling the current pandemic of 2020. In this paper, we study the relationship between clinical diagnosis and analytical features of patient blood panels from the US, Mexico, and Brazil. Our analysis confirms that among adults, the risk of severe illness from COVID-19 increases with pre-existing conditions such as diabetes and immunosuppression. Although more than eight months into pandemic, more data have become available to indicate that more young adults were getting infected. In addition, we expand on the definition of COVID-19 test and discuss …

Maternal Proximity To Mountaintop Removal Mining And Birth Defects In Appalachian Kentucky, 1997-2003, Daniel B. Cooper

Theses and Dissertations--Public Health (M.P.H. & Dr.P.H.)

Background: Extraction of coal through mountaintop removal mining (MTR) alters many dimensions of the landscape, and explosive blasts, exposed rock, and coal washing have the potential to pollute air and water with substances known to increase risk of developmental and birth anomalies. Previous research suggests that infants born to mothers living in MTR coal mining counties have higher prevalence of most types of birth defects.

Objectives: This study seeks to examine further the relationship between MTR activity and birth defects by employing individual level exposure estimation through precise satellite data of MTR activity in the Appalachian region and maternal residence …

Ensemble Protein Inference Evaluation, Kyle Lee Lucke

Graduate Student Theses, Dissertations, & Professional Papers

The Protein inference problem is becoming an increasingly important tool that aids in the characterization of complex proteomes and analysis of complex protein samples. In bottom-up shotgun proteomics experiments the metrics for evaluation (like AUC and calibration error) are based on an often imperfect target-decoy database. These metrics make the inherent assumption that all of the proteins in the target set are present in the sample being analyzed. In general, this is not the case, they are typically a mix of present and absent proteins. To objectively evaluate inference methods, protein standard datasets are used. These datasets are special in …

Machine Learning Applications For Drug Repurposing, Hansaim Lim

Dissertations, Theses, and Capstone Projects

The cost of bringing a drug to market is astounding and the failure rate is intimidating. Drug discovery has been of limited success under the conventional reductionist model of one-drug-one-gene-one-disease paradigm, where a single disease-associated gene is identified and a molecular binder to the specific target is subsequently designed. Under the simplistic paradigm of drug discovery, a drug molecule is assumed to interact only with the intended on-target. However, small molecular drugs often interact with multiple targets, and those off-target interactions are not considered under the conventional paradigm. As a result, drug-induced side effects and adverse reactions are often neglected …

Predicting Disease Progression Using Deep Recurrent Neural Networks And Longitudinal Electronic Health Record Data, Seunghwan Kim

McKelvey School of Engineering Graduate Student Theses & Dissertations

Electronic Health Records (EHR) are widely adopted and used throughout healthcare systems and are able to collect and store longitudinal information data that can be used to describe patient phenotypes. From the underlying data structures used in the EHR, discrete data can be extracted and analyzed to improve patient care and outcomes via tasks such as risk stratification and prospective disease management. Temporality in EHR is innately present given the nature of these data, however, and traditional classification models are limited in this context by the cross- sectional nature of training and prediction processes. Finding temporal patterns in EHR is …

Novel Inference Methods For Generalized Linear Models Using Shrinkage Priors And Data Augmentation., Arinjita Bhattacharyya

Electronic Theses and Dissertations

Generalized linear models have broad applications in biostatistics and sociology. In a regression setup, the main target is to find a relevant set of predictors out of a large collection of covariates. Sparsity is the assumption that only a few of these covariates in a regression setup have a meaningful correlation with an outcome variate of interest. Sparsity is incorporated by regularizing the irrelevant slopes towards zero without changing the relevant predictors and keeping the resulting inferences intact. Frequentist variable selection and sparsity are addressed by popular techniques like Lasso, Elastic Net. Bayesian penalized regression can tackle the curse of …

Hierarchical Clustering Analyses Of Plasma Proteins In Subjects With Cardiovascular Risk Factors Identify Informative Subsets Based On Differential Levels Of Angiogenic And Inflammatory Biomarkers, Zachary Winder, Tiffany L. Sudduth, David W. Fardo, Qiang Cheng, Larry B. Goldstein, Peter T. Nelson, Frederick A. Schmitt, Gregory A. Jicha, Donna M. Wilcock

Sanders-Brown Center on Aging Faculty Publications

Agglomerative hierarchical clustering analysis (HCA) is a commonly used unsupervised machine learning approach for identifying informative natural clusters of observations. HCA is performed by calculating a pairwise dissimilarity matrix and then clustering similar observations until all observations are grouped within a cluster. Verifying the empirical clusters produced by HCA is complex and not well studied in biomedical applications. Here, we demonstrate the comparability of a novel HCA technique with one that was used in previous biomedical applications while applying both techniques to plasma angiogenic (FGF, FLT, PIGF, Tie-2, VEGF, VEGF-D) and inflammatory (MMP1, MMP3, MMP9, IL8, TNFα) protein data to …

Enhancing Timeliness Of Drug Overdose Mortality Surveillance: A Machine Learning Approach, Patrick J. Ward, Peter J. Rock, Svetla Slavova, April M. Young, Terry L. Bunn, Ramakanth Kavuluru

Kentucky Injury Prevention and Research Center Faculty Publications

BACKGROUND: Timely data is key to effective public health responses to epidemics. Drug overdose deaths are identified in surveillance systems through ICD-10 codes present on death certificates. ICD-10 coding takes time, but free-text information is available on death certificates prior to ICD-10 coding. The objective of this study was to develop a machine learning method to classify free-text death certificates as drug overdoses to provide faster drug overdose mortality surveillance.

METHODS: Using 2017–2018 Kentucky death certificate data, free-text fields were tokenized and features were created from these tokens using natural language processing (NLP). Word, bigram, and trigram features were created …

Data Analytics Pipeline For Rna Structure Analysis Via Shape, Quinn Nelson

UNO Student Research and Creative Activity Fair

Coxsackievirus B3 (CVB3) is a cardiovirulent enterovirus from the family Picornaviridae. The RNA genome houses an internal ribosome entry site (IRES) in the 5’ untranslated region (5’UTR) that enables cap-independent translation. Ample evidence suggests that the structure of the 5’UTR is a critical element for virulence. We probe RNA structure in solution using base-specific modifying agents such as dimethyl sulfate as well as backbone targeting agents such as N-methylisatoic anhydride used in Selective 2’-Hydroxyl Acylation Analyzed by Primer Extension (SHAPE). We have developed a pipeline that merges and evaluates base-specific and SHAPE data together with statistical analyses that provides confidence …

Bayesian Analytical Approaches For Metabolomics : A Novel Method For Molecular Structure-Informed Metabolite Interaction Modeling, A Novel Diagnostic Model For Differentiating Myocardial Infarction Type, And Approaches For Compound Identification Given Mass Spectrometry Data., Patrick J. Trainor

Electronic Theses and Dissertations

Metabolomics, the study of small molecules in biological systems, has enjoyed great success in enabling researchers to examine disease-associated metabolic dysregulation and has been utilized for the discovery biomarkers of disease and phenotypic states. In spite of recent technological advances in the analytical platforms utilized in metabolomics and the proliferation of tools for the analysis of metabolomics data, significant challenges in metabolomics data analyses remain. In this dissertation, we present three of these challenges and Bayesian methodological solutions for each. In the first part we develop a new methodology to serve a basis for making higher order inferences in metabolomics, …