Biomedical Informatics Commons^™

Modality-Agnostic, Patient-Specific Digital Twins Modeling Temporally Varying Digestive Motion, Jorge Tapias Gomez, Nishant Nadkarni, Lando S Bosma, Jue Jiang, Ergys D Subashi, William P Segars, James M Balter, Mert R Sabuncu, Neelam Tyagi, Harini Veeraraghavan

Faculty, Staff and Student Publications

No abstract provided.

Neuronal Subtype Governs Amyloid Structure, Cellular Response, And Cognitive Outcome In Genetically Targeted App Mouse Models, Gabriella A Perez, Zoe Lai, George A Edwards Iii, Jacob M Dundee, Shannon N Leahy, Chuangye Qi, Yanyan Qi, Ye-Jin Park, Tzu-Chiao Lu, M Danish Uddin, Rong Zhao, Hui Zheng, Hongjie Li, Joanna L Jankowsky

Faculty, Staff and Students Publications

Pathological heterogeneity is increasingly appreciated in Alzheimer’s disease, yet we do not know how distinct aggregate conformations arise or influence cognitive outcomes. In an amyloid mouse model, we found that different brain regions formed structurally distinct Aβ deposits, prompting us to test whether neuronal subtypes shape aggregate conformation. To address this, we created transgenic mice expressing the same APP construct in either glutamatergic or GABAergic neurons. APP expression in GABAergic neurons resulted in diffuse plaques with high Aβ42/Aβ40 ratios and minimal gliosis, while glutamatergic expression produced neuritic plaques with activated glia. Despite similar Aβ levels, only mice with neuritic plaques …

A Prognostic Matrix Gene Expression Signature Defines Functional Glioblastoma Phenotypes And Niches, Monika Vishnoi, Zeynep Dereli, Zheng Yin, Elisabeth K Kong, Meric Kinali, Kisan Thapa, Ozgun Babur, Kyuson Yun, Nourhan Abdelfattah, Xubin Li, Behnaz Bozorgui, Mary C Farach-Carson, Robert C Rostomily, Anil Korkut

Faculty, Staff and Student Publications

Interactions among tumor, immune, and vascular niches play major roles in glioblastoma (GBM) malignancy and treatment responses. The composition and heterogeneity of extracellular core matrix proteins (CMPs) that mediate such interactions are not well understood. Here, we present an analysis of the clinical relevance of CMP expression in GBM at bulk, single-cell, and spatial anatomical resolution. We show that CMP enrichment is associated with worse patient survival, specific driver oncogenic alterations, mesenchymal state, pro-tumor immune infiltration, and immune checkpoint expression. Matrisome expression is enriched in vascular and leading edge/infiltrative niches that are known to harbor glioma stem cells. Finally, we …

Precision Targeting Of Sting: Challenges, Innovations, And Clinical Outlook For Cancer Therapy, Jiaqi Shi, Yingying Zhang, Na Zhao, Ekihiro Seki, Li Ma, Gordana Kocic, Xiaobo Li, Janoš Terzić, Tongsen Zheng

Faculty, Staff and Student Publications

The stimulator of interferon genes (STING) pathway plays a crucial role in immune responses and has emerged as a compelling target in cancer therapy. Despite promising preclinical studies, clinical trials of STING agonists have largely failed to deliver durable efficacy, with no agents progressing to phase III trials. This review examines the biological, pharmacological, and clinical barriers limiting STING pathway activation in cancer treatment. We discuss the inherent limitations of STING agonists as well as host-related resistance driven by tumor heterogeneity, immune suppression, and chronic STING activation. Mechanisms of acquired resistance, such as immune checkpoint upregulation and suppression of effector …

International Guidelines On The Diagnosis And Treatment Of Nut Carcinoma, Yu Zhang, Qi Zhang, Yue Hao, Jia Luo, Yingshi Piao, Wenxian Wang, Zhengbo Song, Ziming Li, Luka Brcic, Aijun Liu, Jinpu Yu, Yasuhiro Tsutani, Wenzhao Zhong, Wenfeng Fang, Zhijie Wang, Shengxiang Ren, Athanasios G Papavassiliou, Yongchang Zhang, Jingjing Liu, Shirong Zhang, Xiuyu Cai, Ayten Kayi Cangir, Anwen Liu, Wen Li, Filippo Lococo, Ping Zhan, Hongbing Liu, Tangfeng Lv, Liyun Miao, Lingfeng Min, Helmut Popper, Yu Chen, Jingping Yuan, Feng Wang, Zhansheng Jiang, Gen Lin, Long Huang, Xingxiang Pu, Rongbo Lin, Kalevi Kairemo, Weifeng Liu, Chuangzhou Rao, Dongqing Lv, Zongyang Yu, Ashrafian Leanne, Xiaoyan Li, Chuanhao Tang, Hifzur R Siddique, Chengzhi Zhou, Junping Zhang, Junli Xue, Vishal Shelat, Hui Guo, Qian Chu, Rui Meng, Fatemeh Ardeshir, Jingxun Wu, Rui Zhang, Jin Zhou, Robert A Kratzke, Zhengfei Zhu, Yongheng Li, Hong Qiu, Fan Xia, Fiorella Calabrese, Yang Xia, Alessandro Wasum Mariani, Yuanyuan Lu, Xiaofeng Chen, Mark A Klein, Rui Ge, Enyong Dai, Axel H Schönthal, Yu Han, Zhenying Guo, Jian Zhang, Yinghua Ji, Xianbin Liang, Hongmei Zhang, Xuelei Ma, Marco Chiappetta, Xuewen Liu, Francoise Galateau Salle, Yu Yao, Malgorzata Szolkowska, Weiwei Pan, Fei Pang, Fan Wu, Stefan B Watzka, Liping Wang, Youcai Zhu, Li Lin, Aparna Sharma, Jianfei Tu, Xinqing Lin, Jing Cai, Ling Xu, Jisheng Li, Xiaodong Jiao, Kainan Li, Marjorie G Zauderer, Jia Wei, Huijing Feng, Lin Wang, Yingying Du, Wang Yao, Elizabeth Dudnik, Xuefei Shi, Xiaomin Niu, Dongmei Yuan, Yanwen Yao, Jianhui Huang, Yue Feng, Yinbin Zhang, Binbin Song, Wenfeng Li, Jianfei Fu, Marina K Baine, Pingli Sun, Hong Wang, Mingxiang Ye, Dong Wang, Zhaofeng Wang, Jing Wu, Yunyun Yang, Yuan Fang, Zhen Wang, Bin Wan, Donglai Lv, Huafei Chen, Shengjie Yang, Jing Kang, Jiatao Zhang, Chao Zhang, Lin Shi, Yina Wang, Mohamed Emam Sobeih, Bihui Li, Bin Lian, Lili Mao, Zhang Zhang, Ke Wang, Zhongwu Li, Zhefeng Liu, Nong Yang, Lin Wu, Xiaobing Chen, Gu Jin, Miao Li, Guansong Wang, Thomas U Marron, Jiandong Wang, Sanjay Popat, Meiyu Fang, Yong Fang, Daniel Mansilla, Yuan Li, Xiaojia Wang, Jing Chen, Yiping Zhang, Xixu Zhu, Yi Shen, Shenglin Ma, Aaron S Mansfield, Biyun Wang, Lu Si, Anja C Roden, Bjørn H Grønberg, Yong Song, Geoffrey I Shapiro, Christopher A French, Yuanzhi Lu, Qian Wang, Chunwei Xu

Faculty, Staff and Student Publications

Nuclear protein in testis (NUT) carcinoma (NC) represents a rare, clinically aggressive cancer defined by pathognomonic NUT Midline Carcinoma Family Member 1 (NUTM1) gene fusions, with bromodomain and extraterminal domain (BET) protein 4 (BRD4)-NUTM1 being the predominant oncogenic driver. Since its description in 1991, gradual advances have clarified the pathologic mechanisms of NC and its diagnostic methods; however, NC treatment remains a significant challenge. Moreover, diagnostic and treatment approaches for this cancer require further validation and standardization. These guidelines were developed by the Chinese Alliance of Research for NC (ChARN) based on current evidence in …

Vacmap: An Accurate Long-Read Aligner For Unraveling Complex Genomic Rearrangements, Hongyu Ding, Fritz J Sedlazeck, Christos Proukakis, Caoimhe Morley, Marco Toffoli, Anthony Hv Schapira, Zhirui Liao, Lianrong Pu, Shanfeng Zhu

Faculty, Staff and Students Publications

Sequence alignment is essential for genomic research and clinical diagnostics, yet detecting complex rearrangements such as inversions, duplications, and gene conversions remains challenging due to allele complexity and limitations of current methods. We introduce VACmap, a non-linear mapping approach to enhance the detection and representation of all genetic variations. VACmap improves duplication detection from 20% to 90% in the Challenging Medically-Relevant Genes (CMRG) benchmark and improves characterization of complex inversions in repetitive regions and gene conversion events. It improves resolving clinically significant loci, including the LPA gene (with repetitive KIV-2 units linked to coronary heart disease), GBA1 and STRC genes …

Celltra: Aligning Cell Names With Gene Expression Via A Pathway-Informed Transformer, Zhao Li, Zaiyi Zheng, Rongbin Li, Wenbo Chen, Yuntao Yang, Meer A Ali, Jundong Li, W Jim Zheng

Faculty, Staff and Student Publications

Motivation: Single-cell RNA sequencing (scRNA-Seq) technology enables detailed exploration of gene expression at the individual cell level, crucial for annotating cell types and understanding cellular diversity. Traditional methods for cell type annotation often rely on marker genes and manual labeling, posing challenges due to low data quality and incomplete reference datasets.

Results: We developed CeLLTra, a novel contrastive learning framework that leverages a Transformer-based model integrating biological pathway information to group genes into super tokens, effectively capturing comprehensive gene expression from scRNA-Seq data. By combining this pathway-informed Transformer with a pretrained domain-specific language model, CeLLTra accurately aligns cell-type annotations with …

Machine Learning Models Predict Long Covid Outcomes Based On Baseline Clinical And Immunologic Factors, Naresh Doni Jayavelu, Hady Samaha, Sonia Tandon Wimalasena, Annmarie Hoch, Jeremy P Gygi, Gisela Gabernet, Al Ozonoff, Shanshan Liu, Carly E Milliren, Ofer Levy, Lindsey R Baden, Esther Melamed, Lauren I R Ehrlich, Grace A Mccomsey, Rafick P Sekaly, Charles B Cairns, Elias K Haddad, Joanna Schaenman, Albert C Shaw, David A Hafler, Ruth R Montgomery, David B Corry, Farrah Kheradmand, Mark A Atkinson, Scott C Brakenridge, Nelson I Agudelo Higuit, Jordan P Metcalf, Catherine L Hough, William B Messer, Bali Pulendran, Kari C Nadeau, Mark M Davis, Linda N Gen, Ana Fernandez Sesma, Viviana Simon, Florian Krammer, Monica Kraft, Chris Bime, Carolyn S Calfee, David J Erle, Charles R Langelier, Leying Guan, Holden T Maecker, Bjoern Peters, Steven H Kleinstein, Elaine F Reed, Alison D Augustine, Joann Diray-Arce, Patrice M Becker, Nadine Rouphael, Matthew C Altman

Faculty, Staff and Students Publications

Background: The post-acute sequelae of SARS-CoV-2 (PASC), also known as long COVID, remain a significant health issue that is incompletely understood. Predicting which acutely infected individuals will develop long COVID is challenging due to the absence of established biomarkers, clear disease mechanisms, or well-defined sub-phenotypes. Machine learning (ML) models may address this gap by leveraging clinical data to enhance diagnostic precision.

Methods: Clinical data, including antibody titers and viral load measurements collected at the time of hospital admission, are used to predict the likelihood of acute COVID-19 progressing to long COVID. Machine learning models are trained and evaluated for predictive …

Circadian-Shaped Immune Variability Predicts Infection Outcome, Jonathan Lalsiamthara, Mariko Locke, Alejandro Aballay

Faculty, Staff and Student Publications

Disease risk and severity are influenced by genetics, epigenetics, and environmental factors. However, immune responses vary even among genetically similar or related individuals, shaped by inherited and noninherited factors. Using Caenorhabditis elegans, we found that pathogen susceptibility can be predicted by preinfection biomarkers. Individuals with high-basal expression of irg-5, an infection response gene regulated by the p38 mitogen-activated protein kinase-1 (PMK-1) pathway, were more susceptible to Pseudomonas aeruginosa infection. A genome-wide screen identified the myeloid ecotropic viral integration site-1 (MEIS) homeobox protein UNC-62 as a regulator of irg-5 expression, acting through PMK-1 and GATA binding erythroid-like transcription factor …

Cholesterol Efflux Protein, Abca1, Supports Anticancer Functions Of Myeloid Immune Cells, Shruti V Bendre, Yu Wang, Basel Hajyousif, Rajendra K C, Shounak G Bhogale, Dhanya Pradeep, Natalia Krawczynska, Claire P Schane, Erin Weisser, Avni Singh, Simon Han, Hannah Kim, Lara Kockaya, Anasuya Das Gupta, Adam T Nelczyk, Hashni Epa Vidana Gamage, Yifan Fei, Desirée Rodríguez-Casiano, Xingyu Guo, Haoyun Li, Ryan J Deaton, Fei Mo, Maria Sverdlov, Peter H Gann, Saurabh Sinha, Sahil Sahni, Kun Wang, Kevin Van Bortle, Emad Tajkorshid, Wendy A Woodward, Wonhwa Cho, Erik R Nelson

Faculty, Staff and Student Publications

Breast and other solid tumors respond poorly to immune therapy. Myeloid cells (MCs) such as macrophages contribute to resistance. Established clinical evidence links cholesterol to cancer outcomes, with MC function being regulated by cholesterol metabolism. We screened MC-expressed regulators of cholesterol homeostasis linked to survival and identified the cholesterol efflux protein ABCA1. ABCA1 activity increases anticancer functions of macrophages: enhancing tumor infiltration, decreasing angiogenic potential, reducing efferocytosis, and improving support of CD8+ T cell activity. Mechanistically, different AKT isoforms are involved, through both PI3K-dependent and PI3K-independent mechanisms. Highlighting the clinical relevance of our findings are correlations between ABCA1 in macrophages …

Nf2 Loss Malignantly Transforms Human Pancreatic Acinar Cells And Enhances Cell Fitness Under Environmental Stress, Yi Xu, Michael H Nipper, Angel A Dominguez, Chenhui He, Francis E Sharkey, Sajid Khan, Han Xu, Daohong Zhou, Lei Zheng, Yu Luan, Jun Liu, Pei Wang

Faculty, Staff and Student Publications

Pancreatic ductal adenocarcinoma (PDAC) occurs as a complex, multifaceted event driven by the interplay of tumor-permissive genetic mutations, the nature of the cellular origin, and microenvironmental stress. In this study, using primary human pancreatic acinar 3D organoids, we performed a CRISPR-KO screen targeting 199 potential tumor suppressors curated from clinical PDAC samples. Our data revealed significant enrichment of a list of candidate genes, with neurofibromatosis type 2 associated gene (NF2) emerging as the top target. Functional validation confirmed that loss of NF2 promoted the transition of PDAC to an invasive state, potentially through extracellular matrix modulation. NF2 inactivation …

Racial, Ethnic, And Socioeconomic Survival Disparities In Early-Onset Metastatic Colorectal Cancer, Jennifer S Wang, Benny Johnson, Caitlin C Murphy

Faculty, Staff and Student Publications

Importance: Rates of metastatic colorectal cancer (mCRC) are rising among young adults. Disparities by race and ethnicity and neighborhood-level socioeconomic status (SES) among this population are understudied.

Objective: To examine the association of race and ethnicity and neighborhood-level SES with mortality among a community-based sample of young adults with mCRC.

Design, setting, and participants: This cohort study used a large electronic health record-derived database of young adults with cancer treated at 280 community-based US clinics between 2013 and 2021. Eligible patients were young adults aged 18 to 49 years diagnosed with de novo or recurrent mCRC. Patients were followed up …

Public Support For Alcohol-Control Policies And Political Ideology In The Us, Joël Fokom Domgue, Robert Yu, Ernest Hawk, Sanjay Shete

Faculty, Staff and Student Publications

This cross-sectional study examines the role of US adults’ political affiliation, perception about alcohol use and cancer, and sociodemographic and behavioral factors in banning outdoor alcohol advertising and adding cancer warnings on alcohol containers.

Peroxisomal Integrity In Demyelination-Associated Microglia Enables Cellular Debris Clearance And Myelin Renewal In Mice, Joseph A Barnes-Vélez, Xiaohong Zhang, Yaren L Peña Señeriz, Kiersten A Scott, Yinglu Guan, Jian Hu

Faculty, Staff and Student Publications

Demyelination associated microglia (DMAM) orchestrate the regenerative response to demyelination by clearing myelin debris and promoting oligodendrocyte maturation. Peroxisomal metabolism has emerged as a candidate regulator of DMAMs, though the cell-intrinsic contribution in microglia remains undefined. Here we elucidate the role of peroxisome integrity in DMAMs, using cuprizone-mediated demyelination coupled with conditional KO of peroxisome biogenesis factor 5 (PEX5) in microglia. Absent demyelination, PEX5 conditional KO (PEX5cKO) had minimal impact on homeostatic microglia. However, during cuprizone-induced demyelination, the emergence of DMAMs unmasked a critical requirement for peroxisome integrity. At peak demyelination, PEX5cKO DMAMs exhibited increased lipid droplet burden and reduced …

Metabolic Syndrome Beyond Diagnostic Criteria: Population-Scale Integrative Metabolomics Characterization, Marwa Talal

Theses and Dissertations

Background: Metabolic syndrome (MetS) is a complex cluster of interrelated metabolic abnormalities associated with elevated cardiometabolic risk. While diagnosis is based on well-established five clinical criteria, these may overlook early or atypical metabolic alterations. Large-scale metabolomic profiling offers an opportunity to identify biochemical signatures of MetS beyond diagnostic bias and to evaluate their relative importance across different presentations of the syndrome.

Methods: Data from 117,147 UK Biobank participants were analyzed in a cross-sectional design. High-throughput NMR quantified 75 circulating metabolites, for. Univariate analyses, MetS subtype stratification, and elastic net models with SHAP interpretation were applied to assess feature …

Previsit Ai: A Retrieval-Augmented Generation For Patient Readiness In Clinical Encounters, Rolande Umuhoza

All Graduate Theses, Dissertations, and Other Capstone Projects

With healthcare systems under growing pressure from rising patient volumes and shrinking consultation windows, improving how patients communicate with physicians has become essential to delivering quality care. Yet patients routinely arrive at appointments unable to clearly describe their symptoms, recall their medical history, or articulate concerns, contributing to miscommunication, diagnostic inefficiency, and pre-visit anxiety. This study introduces PreVisit AI, a conversational system designed to address this gap through structured, knowledge-based patient preparation. The system is built on a Retrieval-Augmented Generation (RAG) architecture combining HuggingFace sentence embeddings (all-MiniLM-L6-v2), a Chroma vector store, and Google’s Gemini language model over a curated seven-document …

Bpa: Effects Of The "Plastic Era", Bianca G. Pietrangeli

Student Work

Infographic review of sources of BPA and its impacts on human health with a focus on osteoporosis.

Evaluating The Impact Of Proactive Rounding On Early Recognition And Rapid Response, Alicia Mcintosh

Doctor of Nursing Practice Final Project Abstract

Purpose: This quality improvement project evaluated the impact of a Rapid Response Team (RRT)-led proactive rounding model on the early recognition of clinical deterioration and selected patient outcomes.

Background: Delays in recognizing clinical deterioration contribute to preventable adverse events, highlighting the need for proactive strategies to support early identification and timely intervention. To address this need, the project was implemented on a 36-bed intermediate care unit at a community medical center in Southeast United States.

Methodology: Guided by the Plan-Do-Study-Act framework, the project used a six-week pre-post intervention in which an Advanced Practice Provider (APP) conducted proactive rounds on patients …

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

Computer Science and Engineering Dissertations

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

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

Accelerating Ai Innovation In Healthcare: Real-World Clinical Research Applications On The Mayo Clinic Platform, Yue Yu, Xinyue Hu, Sivaraman Rajaganapathy, Jingna Feng, Ahmed Abdelhameed, Xiaodi Li, Jianfu Li, Xiaoke Liu, Liu Yang, Nilüfer Ertekin-Taner, Phil Fiero, Soulmaz Boroumand, Richard Larsen, Maneesh Goyal, Clark C Otley, Nansu Zong, Vijay H Shah, John D Halamka, Cui Tao

Faculty, Staff and Student Publications

Artificial intelligence (AI) holds promise for healthcare, but real-world implementation remains difficult. The Mayo clinic platform (MCP) addresses this by providing scalable, multi-institutional, de-identified data and analytical tools. Through four research projects, we demonstrate MCP's ability to support efficient cohort identification, AI model development, and real-world evidence generation. MCP enables broader accessibility and standardization compared to institutional EHRs, positioning it as a powerful platform for advancing translational research and precision medicine.

The Ai-Native Health Science Institution Innovation Theater Vs. Structural Redesign, Jiajie Zhang, Martin J Citardi, Xiaoqian Jiang, Sean Savitz

Faculty, Staff and Student Publications

Academic health institutions face a new constraint: cognitive labor. Many adopt AI through additive initiatives that risk becoming "innovation theater"-visible activity without structural change. We argue this reflects a mismatch between rapid AI advances and slower institutional evolution. AI-native institutions treat AI as infrastructure, requiring governance, shared platforms, and workforce readiness. The challenge is not adoption but redesign; those that fail risk widening gaps and accelerating irrelevance.

Frame: Fast Reference-Based Ancestry Makeup Estimation Tool, Pramesh Shakya, Ardalan Naseri, Degui Zhi, Shaojie Zhang

Faculty, Staff and Student Publications

Motivation: The availability of large-scale genetic data presents a unique opportunity to study the genetic ancestries of individuals, which requires an efficient and scalable method. The existing global ancestry methods are accurate, but they cannot scale to large genetic datasets. Identity-by-descent (IBD) segments are DNA segments shared by individuals such that they are inherited from a common recent ancestor without recombination. These IBD segments, which reflect co-ancestry, provide an efficient alternative for inferring genetic ancestry.

Results: We introduced a reference-based global ancestry inference method called FRAME (Fast Reference-based Ancestry Makeup Estimation). FRAME utilizes partial local ancestry information estimated through IBD …

A Specification-Driven Framework For Self-Supervised Learning In Specialized Vision Domains, Mahmut S. Gokmen

Theses and Dissertations--Computer Science

Self-supervised learning (SSL) has emerged as a principled approach to visual representation learning that derives supervisory signal directly from unlabeled data, enabling foundation models to be trained at scale without manual annotation. Deployments in medical imaging and biometric recognition have demonstrated the potential of this paradigm, yet the assumptions that make SSL effective on natural image benchmarks fail systematically in specialized domains. Generic SSL pipelines encode a tacit assumption that the most informative correspondence is spatial proximity within a single acquisition. In specialized domains this assumption breaks at the level of the data-generating process: the signal that carries domain-specific information …

Adversarial Robustness In Biomedical Time-Series Models, Rohan Tiwari

Bioengineering Theses

This study investigates adversarial vulnerabilities in deep learning models for biomedical time-series classification across two clinically important modalities: electrocardiography (ECG) and electroencephalography (EEG). Using the MIT-BIH Arrhythmia and CHB-MIT seizure datasets, I evaluate time-domain attacks (FGSM, PGD), Fourier-domain constrained attacks, and learned spectral perturbations designed to reveal modality-specific sensitivity patterns. Across both tasks, a consistent trend emerges low-frequency components (0–5 Hz) constitute a dominant axis of adversarial vulnerability, with perturbations in this range producing the steepest degradation in classification performance. In ECG models, protecting the physiologically relevant QRS band (5–20 Hz) significantly improves robustness, whereas EEG models remain highly sensitive …

Robust And Interpretable Medical Image Segmentation Via Retrieval And Mechanistic Analysis, Salma Ahmed

Theses and Dissertations (Comprehensive)

Medical image segmentation is a critical component of clinical decision-making, yet deep learning based segmentation models face persistent challenges. These models typically require large volumes of densely annotated data, exhibit strong sensitivity to domain shifts across scanners and patient populations, and lack explicit anatomical priors. Furthermore, despite continual architectural advances beyond fully convolutional networks, most segmentation models remain opaque, where they lack the granularity required for component-level analysis. As a result, when segmentation models fail, it is difficult to identify which internal representations are responsible, limiting developers’ ability to diagnose errors, improve robustness, or establish trust in clinical settings. Existing …

Hyperglycemia Detection From Sigle - Lead Ecg Using A Hybrid Cnn & Transformer Model, Adam Ayomikun Ogunjembola

Graduate Theses, Dissertations, and Problem Reports (ETD)

Abstract
Hyperglycemia Detection from Single-Lead ECG using a Hybrid CNN & Transformer Model
Adam Ogunjembola

Diabetes Mellitus is known as high blood glucose. This high blood glucose level happens when the body has a problem with producing or using insulin. Insulin is a very important hormone that the pancreas makes to control how much glucose gets into the bloodstream and cells. Diabetes Mellitus has an effect on the body if it is not treated, such as damaging the blood vessels and nerves which can lead to stroke, kidney failure, heart attack and permanent loss of vision. Since people with diabetes …

Clinical Outcomes With Perioperative Nivolumab By Nodal Status In Patients With Stage Iii Resectable Nsclc: Phase 3 Checkmate 77t Exploratory Analysis, Mariano Provencio, Mark M Awad, Jonathan D Spicer, Annelies Janssens, Fedor Moiseyenko, Yang Gao, Yasutaka Watanabe, Aurelia Alexandru, Florian Guisier, Nikolaj Frost, Fabio Franke, T Jeroen Nicolaas Hiltermann, Jie He, Fumihiro Tanaka, Shun Lu, Cinthya Coronado Erdmann, Padma Sathyanarayana, Phuong Tran, Vipul Devas, Tina Cascone

Faculty, Staff and Student Publications

Individuals with non-small-cell lung cancer (NSCLC) with metastases to the ipsilateral mediastinum or subcarinal lymph nodes (N2 disease) have poor long-term survival. This exploratory analysis from the randomized phase 3 CheckMate 77T study assessed clinical outcomes by nodal status in individuals with stage III NSCLC who received neoadjuvant nivolumab plus chemotherapy followed by surgery and adjuvant nivolumab (nivolumab) versus neoadjuvant chemotherapy followed by surgery and adjuvant placebo (placebo). Here we show that among patients with N2 disease, nivolumab versus placebo improved event-free survival (1-year rate, 70% versus 45%; hazard ratio, 0.46 (95% confidence interval, 0.30–0.70)) and pathological complete response rate …

Blood Flow Regulates Metabolism In Hematopoietic Development, Pamela L Wenzel

Faculty, Staff and Student Publications

Blood flow modifies oxygen availability and biomechanical forces within the vasculature of the embryo as the hematopoietic system develops. The aorta-gonad-mesonephros (AGM) envelops the largest artery in the body and is a critical site for the emergence of hematopoietic stem cells (HSCs). Herein, I discuss the role of hypoxia-inducible factors (HIFs) and force as determinants of metabolism and fate determination. To address the effects of blood flow on hematopoietic development, I employ mouse embryo models and biomimetic culture. Real-time cell metabolic analyses show that oxygen consumption rates (OCR) and extracellular acidification rates (ECAR) are altered by flow in cultures of …

Recurrence And Co-Occurrence Of Enhancer-Promoter Interactions Across Human Samples, Satvik Gunjala

Honors Undergraduate Theses

Experimental mapping of enhancer-promoter interactions (EPIs) is resource-intensive, and current computational prediction methods struggle with intrinsic genomic complexity and reliance on limited training data. To address this bottleneck and provide insights for improved computational methods, this study systematically analyzed chromatin contact datasets to investigate the recurrence and co-occurrence of enhancer-promoter interactions across human samples. Putative interactions were evaluated across two HiChIP datasets comprising 218 total samples and one Hi-C dataset comprising 266 samples to assess recurrence across samples and assess sequencing depth related to unique EPIs. Additionally, a preliminary item-based collaborative filtering recommender model was developed to assess co-occurrence patterns …

Dietetic Guidance For Nutritional Management Of People With Phenylketonuria Receiving Sepiapterin, Anita Macdonald, Kirsten Ahring, Alexa Bledsoe, Hiroki Fujimoto, Sara Giorda, Christian Kogelmann, Jessica Kopesky, Laura Nagy, Sara O'Neill, Alex Pinto, Soraia Poloni, Paige Roberts, Annemiek M J Van Wegberg, Suzanne Hollander

Faculty, Staff and Student Publications

Background/objectives: Phenylketonuria (PKU) is an autosomal recessive inborn error of metabolism. If untreated, elevated blood phenylalanine (Phe) levels lead to neurological and behavioral impairments. Phe levels can be managed through a lifelong Phe-restricted diet; however, this can be challenging to maintain. Sepiapterin is an adjunct therapy for PKU that has shown efficacy in reducing blood Phe levels in both tetrahydrobiopterin (BH4)-responsive and BH4-non-responsive people with PKU in clinical trials. Practical guidance is needed for dietitians and other healthcare professionals supporting the dietary management of people with PKU who are initiating or receiving sepiapterin.

Methods: A group of international dietitians participated …