Medicine and Health Sciences Commons^™

Acceptability, Usability, And Clinical Integration Of A Clinic-Based Digital Game For Hpv Education: Qualitative Perspectives From Adolescents, Parents, And Healthcare Providers, Elizabeth Reifsnider, Satya Subedi, Nouran Ghonaim, Megan Whaley, Angela Chia-Chen Chen

Ellmer School of Nursing Faculty Publications

Background/Objectives: HPV vaccination is safe, effective, and recommended at ages 11–12, yet uptake remains suboptimal. Serious video games may offer an innovative strategy to deliver brief, engaging education during clinic visits. This qualitative paper, embedded within a mixed-methods study, examined adolescents’, parents’, and healthcare providers’ (HCPs’) perceptions of the acceptability, usability, and perceived clinical applicability of HPV Detective, a tablet-based digital game designed to provide HPV-related education to parent–child dyads during pediatric clinic wait times. Methods: Eight adolescent–parent dyads (N = 16) and three HCPs from university-affiliated pediatric clinics participated in 30–60-min semi-structured Zoom interviews. Interviews were audio-recorded, transcribed, and …

Organized Sports-Based Interventions And Motor Outcomes In Children Diagnosed With Autism Spectrum Disorder: A Systematic Review, Kailash Ram, Maeren Hill, Caitlyn Stewart, Kaitlin P. Hardy Md, Sonia Khurana

Rehabilitation Sciences Faculty Publications

Aim

To evaluate the effectiveness of organized sports-based interventions on motor outcomes in children with autism spectrum disorder (ASD).

Method

Four databases were searched from inception to November 2025 for randomized controlled trials (RCTs) and non-randomized controlled trials (NRCTs) reporting motor outcomes of organized sports-based interventions in children with ASD. Risk of bias was evaluated using ROB-2 (Cochrane Risk of Bias Tool, Version Two) for RCTs and ROBINS-I (Risk Of Bias In Non-randomized Studies - of Interventions) for NRCTs.

Results

Eleven studies (six RCTs, five NRCTs) were included and categorized as martial arts (n = 5), aquatic training (n = …

Glucagon-Like Peptide-1-Based Therapies And The Intersection Of Metabolic And Skin Disease, Ana Ormaza-Vera, Clinton W. Enos

Department Dermatology Faculty Publications

[Introduction] To the Editor: The development of the glucagon-like peptide-1 (GLP-1) receptor agonists (GLP-1RAs) and the dual glucose-dependent insulinotropic polypeptide/GLP-1RAs is revolutionizing the management of metabolic disease. Perhaps most impressive is that their clinical significance extends far beyond their approved indications and touches seemingly every organ system, even the skin.

Photobiomodulation Mitigates The Inhibitory Effects Of Pirfenidone On Cancer-Associated Fibroblasts And Their Pro-Tumorigenic Properties: A Cause For Concern, Nima Rastegar-Pouyani, Alireza Nasirpour, Fatemeh Javani Jouni, Hossein Vazini, Ahmad Moshaii

Electrical & Computer Engineering Faculty Publications

Cancer-associated fibroblasts (CAFs) within the tumor microenvironment highly contribute to cancer progression and poor prognosis. Recent findings introduce pirfenidone, a medication for pulmonary fibrosis, as a promising repurposed candidate for inhibiting CAFs. Moreover, photobiomodulation (PBM), or low-level laser therapy, has surfaced as a potential modality against cancer; however, its impact on CAFs is not thoroughly comprehended. The present study scrutinized the effects of PBM, pirfenidone, and PBM+pirfenidone on CAFs, and their consequent impact on cancer cells using the CAF-conditioned media. After treating CAFs with PBM at wavelengths 660 and 980 nm with/without PFD and then culturing cancer cells in the …

The Association Between Maternal-Fetal Medicine Physician Density And Pregnancy Outcomes, Tetsuya Kawakita, Rula Atwani, Misa Hayasaka, Lindsay Robbins, George Saade

Department of Obstetrics & Gynecology Faculty Publications

Objective

We sought to examine the association between maternal-fetal medicine (MFM) physician density and adverse pregnancy outcomes at the state level.

Study Design

This was a cross-sectional analysis of publicly available, state-level data from 2018 to 2021, including Natality, Multiple Cause-of-Death, and Fetal Death databases. The number of active MFM physicians per year was obtained for each state from the American Medical Association Masterfile. The primary exposure was the density of MFM per state, categorized into three groups: (1) low density (< 30 MFM physicians per 100,000 live births), (2) moderate density (30-59 MFM physicians per 100,000 live births), and (3) high density (≥60 MFM physicians per 100,000 live births). Our primary outcome was maternal mortality during pregnancy and up to 42 days postdelivery. Our secondary outcomes were pregnancy-related mortality up to 365 days postdelivery and stillbirth. We calculated adjusted incident rate ratios (aIRR) and average marginal effect (AME) with 95% confidence intervals (95% CI) using multivariable negative binomial mixed effects regression models.

Results

Overall, there were 14,792,743 live births, 3,440 maternal mortalities, 4,980 pregnancy-related mortalities, and 90,848 stillbirths included. The …

Association Between Neighborhood Social Determinants Of Health And Stillbirth, Tetsuya Kawakita, Misa Hayasaka, Ann M. Harper, John Brush, George Saade

Department of Obstetrics & Gynecology Faculty Publications

OBJECTIVE:

To examine the association between neighborhood-level social determinants of health and stillbirth.

METHODS:

We performed a retrospective cohort study of deliveries that occurred at a gestational age of at least 20 weeks within a five-hospital system (2012-2022). Electronic health record data mapped to the Observational Medical Outcomes Partnership Common Data Model were geocoded using addresses at the time of delivery and linked to neighborhood health indices, which included the Area Deprivation Index (ADI), Maternal Vulnerability Index (MVI), and Social Vulnerability Index (SVI) at the Census tract level. Stillbirths were adjudicated by medical record review. Modified Poisson regression generated relative …

Mediating Effect Of Social Determinants Of Health Between Race And Phthalate Biomarkers In Pregnancy, Tetsuya Kawakita, Misa Hayasaka, Carole Barake, Trinity Soto, Jillian Fleming, Amir Lueth, Stevens Danielle, Alfred Abuhamad, Ann Pryzybylska, Elena Sinkovskaya, Kelly K. Ferguson, George Saade

Department of Obstetrics & Gynecology Faculty Publications

Introduction

Prenatal phthalate exposure is linked to adverse reproductive and developmental outcomes and is consistently higher among non‐Hispanic Black compared to non‐Hispanic White pregnant individuals, yet the factors responsible for these disparities are poorly characterized. We sought to quantify Black–White differences in repeated urinary concentrations of phthalate biomarkers during pregnancy and to estimate the extent to which neighborhood‐level social determinants of health (SDoH) mediate these disparities.

Methods

This secondary analysis used data from the Human Placenta Project Study, a prospective observational cohort study conducted at two academic institutions between 2016 and 2018. Eligible participants had singleton pregnancies, were recruited before …

Differential Impact Of Admission Type And Clinical Complexity On Diabetes Hospitalization Costs Among African American And Hispanic Patients In Southeastern Virginia, Ismail El Moudden, Asra Amidi, Reem Sharaf-Alddin, Michael C. Bittner, Qi Zhang

Department of Obstetrics & Gynecology Faculty Publications

Background

Diabetes mellitus (DM) imposes substantial healthcare costs with documented disparities among African Americans and Hispanic patients. To inform care delivery and resource allocation, this study identified hospitalization cost predictors among African American and Hispanic patients with diabetes in Southeastern Virginia.

Methods

We analyzed 6,011 hospital discharges from the Virginia Health Information database (2016-2020) for adults aged 18-85 with diabetes. Discharges were classified by Medicare Severity Diagnosis-Related Groups: DM with complications/comorbidities (DCC, n = 3,328), DM with major complications/comorbidities (DMCC, n = 1,518), and DM without major complications/comorbidities (DWO, n = 1,165). Because cost distributions were right-skewed (skewness 3.5-8.24), we …

Contribution Of Comorbidities And Pregnancy Complications To Severe Maternal Morbidity In The United States, Tetsuya Kawakita, Sora A. Jones, Natsume Furukawa, George Saade

Department of Obstetrics & Gynecology Faculty Publications

Objective: To quantify the extent to which rising rates of severe maternal morbidity (SMM) in the United States from 2016 to 2022 are attributable to increasing prevalence of maternal risk factors, including advanced maternal age, obesity, pregestational diabetes mellitus, gestational diabetes, chronic hypertension, and hypertensive disorders of pregnancy (HDP).

Methods: We conducted a retrospective cohort study using the Nationwide Readmissions Database from 2016 to 2022, representing more than 25 million weighted delivery hospitalizations. The primary outcome of SMM was identified with the Centers for Disease Control and Prevention's 21-condition algorithm; a secondary outcome excluded transfusion to improve specificity. Temporal trends …

Cervicovaginal Lavage Fluid Iron And Manganese Levels In Women With And Without Vaginitis, Barbara Kozma, David Ratonyi, Bence Kozma, Peter Takacs, Attila G. Sipos

Department of Obstetrics & Gynecology Faculty Publications

Transition metals such as iron and manganese are critical for cellular metabolism, redox balance, and immune function, and they also influence host–pathogen interactions. Vaginitis is characterized by mucosal inflammation that may alter local trace-element homeostasis. We hypothesize that inflammatory conditions such as vaginitis may be associated with altered cervicovaginal iron and manganese levels. We performed a prospective, single-center cohort study at the University of Debrecen (Hungary) between April 2023 and April 2024, enrolling 80 women ≥ 18 years with vulvovaginal complaints. Participants were assessed at baseline and at weeks 4, 8, and 12 with clinical evaluation and cervicovaginal lavage (CVL) …

Estetrol (E4) For The Treatment Of Moderate To Severe Vasomotor Symptoms In Postmenopausal Women - Efficacy And Safety Results From The Phase 3 E4comfort I Multicenter, Placebo-Controlled Study, Tommaso Simoncini, Céline Bouchard, Marie Cloes, Mélanie Taziaux, Santiago Palacios, Sebastião Freitas De Medeiros, Valeriu Vrabii, David F. Archer, Nick Panay

Department of Obstetrics & Gynecology Faculty Publications

Objective

To evaluate the efficacy and safety of estetrol in reducing moderate to severe vasomotor symptoms in postmenopausal women.

Methods

Multicenter, randomized, parallel group (1:1:1), placebo-controlled, double-blind, phase 3 study in hysterectomized and non-hysterectomized participants aged 40-65 years. A total of 640 participants with seven or more moderate to severe hot flashes daily or 50 weekly received estetrol 15 mg, estetrol 20 mg, or placebo for 12 weeks. Co-primary endpoints were the change in frequency and severity of moderate to severe vasomotor symptoms from baseline to weeks 4 and 12. Comparisons versus placebo were made using a mixed-effects model for …

The Association Between The Degree Of Social Vulnerability And Maternal Anemia And Other Adverse Perinatal Outcomes, Rubymel J. Knupp, Christina T. Blanchard, Ariann Nassel, Ashley Shea, Lindsay S. Robbins, Jeff M. Szychowski, Ashley N. Battarbee, Akila Subramaniam

Department of Obstetrics & Gynecology Faculty Publications

Objective

Maternal anemia in pregnancy is associated with many adverse maternal, fetal, and neonatal outcomes. The role of social determinants of health (SDOH) in the development of maternal anemia and other adverse outcomes is continually evolving. One such newer tool, the Social Vulnerability Index (SVI), measures an individual's community-level SDOH, with higher SVI denoting higher vulnerability. Our objective was to evaluate the association between SVI, maternal anemia, and other adverse perinatal outcomes.

Methods

Retrospective cohort study of pregnant individuals delivering singletons at a gestational age ≥23 weeks at a single center from 2014 to 2018. Patients with sickle cell disease, …

Evaluating The Mediating Role Of Gestational Phthalate And Replacement Biomarkers In The Associations Between Race/Ethnicity And Birthweight, Amir J. Lueth, Danielle R. Stevens, Sarahna A. Moyd, Elena Sinkovskaya, Ann Przybylska, Antonia M. Calafat, Julianne C. Botelho, George Saade, Alfred Abuhamad, Kelly K. Ferguson

Department of Obstetrics & Gynecology Faculty Publications

Background

Gestational exposure to phthalates is higher among non-Hispanic black (NHB) women than non-Hispanic white (NHW) women and may contribute to racial/ethnic differences in birthweight z-scores.

Objective

We aimed to investigate whether gestational phthalate and replacement biomarkers mediate the association between race/ethnicity and birthweight z-scores.

Methods

We analyzed data from 271 pregnancies in the Human Placenta and Phthalates study, a prospective cohort recruited from 2017 to 2020. Urinary phthalate metabolite concentrations were measured at up to eight time points during pregnancy and averaged to represent gestational exposure. Metabolites were grouped by parent compound. Linear regression models estimated associations in phthalate …

Dupilumab For Patients With Allergic Fungal Rhinosinusitis, Amber U. Luong, Joshua M. Levy, Sarah K. Wise, Joseph K. Han, Mamoru Yoshikawa, Luo Zhang, Rodney Schlosser, Prerna Ranganathan, Paula Dakin, Jennifer Maloney, George D. Yancopoulos, Andrew P. Fontenot, Neelam A. Phadke, Lacey R. Robinson

Department of Otolaryngology (ENT) Faculty Publications

Background

Allergic fungal rhinosinusitis (AFRS) is a severe subtype of chronic rhinosinusitis characterized by fungal hypersensitivity and accentuated type 2 inflammation. Dupilumab-a fully human monoclonal antibody blocking interleukin-4/13, approved for type 2 inflammatory diseases, including chronic rhinosinusitis with nasal polyps-may benefit patients with AFRS.

Objective

We sought to understand the effect of dupilumab in AFRS

Methods

In this phase 3 trial, patients with AFRS aged ≥6 years were randomized to dupilumab or matched placebo for 52 weeks. The primary end point was Lund-Mackay computed tomography (LMK-CT) score, quantifying sinus opacification, at 52 weeks. Secondary end points were multiplicity-controlled and hierarchically …

Assessment Of Major Adverse Cardiovascular Event Across Diverse Racial Groups Of Psoriasis Patients On Biologic Therapy: A Retrospective Cohort Study, Chunghwan Ro, Ana Ormaza Vera, Waleed Adawi, Clinton W. Enos

Department Dermatology Faculty Publications

Psoriasis is associated with an increased risk of major adverse cardiovascular events (MACE), and biologic therapy may reduce this risk by targeting systemic inflammation. However, limited data exist on whether long term MACE risk differs by biologic class or across racial groups. We conducted a retrospective cohort study to assess the risk of primary MACE in psoriasis patients receiving biological therapies, stratified by biological class, compared with biologic-naïve psoriasis patients. Whether MACE risk among biologic-treated patients varied by race was further examined. After 1:1 propensity score matching, 36 330 biologic-treated patients were compared with 36 330 non-biologic-treated patients. Incident MACE …

The Interplay Between Loneliness, Cortisol, And Nk Cell Function: The Role Of Cortisol In Nk Cell Dysfunction, Abhinav Saurabh, Yvonne Baumer, Laurel G. Mendelsohn, Elizabeth M. Aquino Peterson, Dana Sadler, Shirley J. Lopez De Leon, Ayushi Dave, Andrew S. Baez, Lola R. Ortiz-Whittingham, Mario A. Pita, Manuel A. Cintron, Hannatu A. Tarfa, Sandy T. Reynolds, Shelby R. Hicks, Sonal Sharda, J. Eleanor Seo, Maria Lopez-Ocasio, Pradeep K. Dagur, Skyler A. Kuhn, Neelam R. Redekar, James F. Troendle, Ayanna L. Wells, Marie Marah, Katherine J. Tolentino, Michael J. Corley, Alika K. Maunakea, Lynnette K. Nieman, Marcus R. Andrews, Tiffany M. Powell-Wiley

Department of Biomedical and Translational Sciences Faculty Publications

Chronic psychosocial stressors contribute to cardiovascular disease (CVD) and related risk factors, particularly in under-resourced communities. Psychosocial stressors activate the hypothalamic-pituitary-adrenal (HPA) axis, leading to sustained cortisol action on immune cells. Natural killer (NK) cells are altered in distribution and function in cardio-metabolic diseases; however, pathways linking cortisol as a marker of chronic stress to NK cell dysfunction remain understudied. We recruited 186 African American women from the Step It Up Community-Engaged, Digital Health Physical Activity Intervention study and collected cortisol, NK cell measures, and psychosocial stress measures using validated questionnaires, including chronic stress and loneliness. Plasma cortisol levels were …

The Effects Of Abused Drugs On Ferroptosis Pathways: Potential Therapeutic Targets For Substance Use Disorders, Tamara Bouchard, Brooke Russell, Liam Liyang Guo, Tina Nguyen, Yan Cheng, Yan Y. Sanders, Ming-Lei Guo

Department of Biomedical and Translational Sciences Faculty Publications

Substance use disorders (SUDs) remain major public health concerns worldwide, particularly in developed countries. SUDs are characterized by persistent neuroinflammation and synaptic dysfunction in the brain. Despite decades of extensive investigation, the detailed mechanisms underlying SUDs remain elusive. Ferroptosis is a highly regulated cell death process deeply affected by iron metabolism, lipid peroxidation, reactive oxygen species (ROS) production, and antioxidant systems. It has been implicated in multiple neurodegenerative diseases, including Alzheimer's disease, Parkinson's disease, multiple sclerosis, and ischemic stroke. Recently, emerging evidence has highlighted the role of ferroptosis in drug-induced pathological changes. Various types of abused substances including alcohol, cocaine, …

Senescent Fibroblasts In Aging And Pulmonary Fibrosis, Sara B. Palega, Aiwei Y. Borengasser, Yan Y. Sanders

Microbiology & Molecular Cell Biology Faculty Publications

Aging is a major risk factor for many chronic lung diseases, including Idiopathic Pulmonary Fibrosis (IPF), a fatal and incurable disease characterized by progressive fibrotic remodeling. Age-associated structural alterations, impaired regenerative capacity, and dysregulated cellular signaling collectively create a pro-fibrotic microenvironment. A central driver of this pathological shift is the accumulation of senescent cells, which undergo irreversible growth arrest and develop a robust pro-inflammatory senescence-associated secretory phenotype (SASP). Emerging evidence identifies senescent lung fibroblasts as critical mediators of IPF pathogenesis. These cells promote excessive extracellular matrix deposition, myofibroblast differentiation, and tissue stiffening, while simultaneously impairing epithelial regeneration. Together, these effects …

Single-Cell Transciptomic Analysis Reveals Age-Related Remodeling Of Brain Endothelial Cells, Hai Duc Nguyen, Summer Siddiqui, Diana G. Bohannon, Robert V. Blair, Hong-Wen Deng, Alexandre Prat, Woong-Ki Kim

Microbiology & Molecular Cell Biology Faculty Publications

Blood–brain barrier (BBB) integrity naturally declines with age. Brain endothelial cells (ECs) and pericytes (PCs) form the BBB, and aging impairs tight junctions, likely via altered PC-to-EC signaling. However, the molecular mechanisms underlying this impairment remain unclear. Using single-cell RNA sequencing, we profiled 68,316 brain ECs expressing 15,564 genes from young and old mice. Unsupervised clustering and annotation revealed five distinct EC subtypes—Capillary EC1, Capillary EC2, Arterial EC, Venous EC1, and Venous EC2—defined by marker genes Mfsd2a, Plvap, Bmx, Nr2f2, and Vcam1, respectively. Aging shifted EC subtype distribution, with reduced Capillary EC1 (45% vs. 57%) and increased Arterial …

Mepolizumab Improves Outcomes In Patients With Crswnp With One Or More Prior Nasal Polyp Surgeries, Joseph K. Han, Joaquim Mullol, Martin Wagenmann, Laura Walrave, Lingjiao Zhang, Ana R. Sousa, Peter Howarth, Claire Hopkins

Department of Otolaryngology (ENT) Faculty Publications

BACKGROUND: Patients with chronic rhinosinusitis with nasal polyps (CRSwNP) often undergo multiple nasal surgeries. The Phase III SYNAPSE study (GSK ID:205687; NCT0308579) demonstrated that mepolizumab reduces the need for repeat surgery. We explored whether outcomes differed based on the number of prior surgeries. METHODOLOGY: This post hoc analysis of SYNAPSE stratified patients by history of 1 or more than 1 prior surgery. Patients were randomised to receive mepolizumab or placebo every 4 weeks, alongside standard of care, for 52 weeks. Outcomes included change from baseline in endoscopic nasal polyp (NP) score, visual analogue scale (VAS) scores for nasal obstruction, loss …

Maxgrnet: A Multi-Axis Vision Transformer With Improved Generalization For Eye Disease Classification Using Explainable Ai With Insertion-Deletion Operations On Fundus Images, Md Mehedi Hasan Santo, Fuyad Hasan Bhoyan, Fuad Ibne Jashim Farhad, Fahmid Al Farid, Sovon Chakraborty, Md Humaion Kabir Mehedi, Jia Uddin, Hezerul Bin Abdul Karim

Computer Science Faculty Publications

Eye diseases, including diabetic retinopathy (DR), glaucoma, and cataracts, represent a major global health concern and can lead to severe visual impairment or blindness if not identified in a timely manner. This study proposes a novel eye disease classification framework based on a multi-axis vision transformer (MaxViT) applied to color fundus images with Explainable Artificial Intelligence (XAI) techniques to enhance model transparency. The proposed architecture integrates transformer-based attention mechanisms with Global Response Normalization (GRN)-based multi-layer perceptron (MLP) layers to capture complex spatial and contextual relationships within fundus images effectively. The model was evaluated on a publicly available eye disease classification …

Privacy-Preserving Federated Learning With Optimized Ensemble Weighting And Knowledge Distillation For Covid-19 Detection From Non-Iid Medical Imaging Data, Richard Annan, Hong Qin, Robert Newman, Madhuri Siddula, Letu Qingge

Computer Science Faculty Publications

Medical imaging enables rapid and accurate diagnosis of COVID-19, with CT scans proving especially effective. However, data privacy concerns limit collaborative model development across hospitals. To address this issue, we introduce a novel federated learning framework. It is referred to as Independent Knowledge Distillation with post-Ensemble Federated Learning (IKDEFL). Differential Privacy (DP) is integrated into the framework to improve privacy guarantees. Three DP mechanisms are evaluated. These include Fixed Gaussian, Gaussian Adaptive, and Tree Adaptive. The evaluation has been conducted on heterogeneous and Non-Independent and Identically Distributed (Non-IID) datasets. These datasets reflect real-world hospital scenarios. Results show that IKDEFL significantly …

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

Computer Science Faculty Publications

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

Isotropic Shrinkage Of Patterned Vacancies Enables Three-Dimensional Nanoprecise Metastructures For Visible Light Applications, Quansan Yang, Gaojie Yang, Takahiro Nambara, Hiroyuki Kusaka, Yuichiro Kunai, Alex C. Matlock, Corban Swain, Brett Pryor, Yannick Salamin, Daniel Oran, Hasindu Kariyawasam, Ramith Hettiarachchi, Dushan Wadduwage, Marin Soljačić, Peter T. C. Soflaei, Edward S. Boyden

Computer Science Faculty Publications

Three-dimensional metastructures with nanoscale feature sizes exhibit unique properties compared with structures with larger feature sizes, but are difficult to fabricate. Here we introduce implosion carving (ImpCarv), a method for photopatterning vacancies of complex geometry throughout materials, followed by isotropic shrinkage (>10-fold). ImpCarv works by photoactivating sensitizers to generate reactive oxygen species that cleave a swollen hydrogel at defined points, followed by controlled shrinkage via dehydration. ImpCarv creates three-dimensional metastructures where the refractive index of each point throughout a material can be specified with nanoscale precision via material presence or absence. By leveraging refractive index programmability for precise phase …

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

Computer Science Faculty Publications

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

An Investigation Of Federated Gnns Under Aggregation, Data Poisoning, And Differential Privacy For Icu Length-Of-Stay Prediction, Shakib Mahmud Dipto, Soumya Banerjee, Sandip Roy, Ahmad F. Al Musawi, Preetam Ghosh, Sachin Shetty, Pratip Rana

Computer Science Faculty Publications

Accurate prediction of ICU Length of Stay (LoS) is essential for clinical decision-making and healthcare resource management. Graph Neural Networks (GNNs), such as GraphSAGE, offer a natural fit by capturing patient data from Electronic Health Records (EHRs) through graph structures. However, the distributed and sensitive nature of this data raises both privacy and legal concerns regarding the aggregation and training of GNN models. This additionally leads to issues with data imbalance and model robustness. In this study, we perform an analysis of the Federated Graph Neural Network (GNN-FL) framework to enable decentralized learning on EHRs derived from the MIMIC-III dataset. …

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

Computer Science Faculty Publications

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

Chromnet: A Multi-Task Learning Framework For Cross-Cell Type Prediction Of 3d Chromatin Interactions Using Epigenetic Signals, Bin Wang, Shaokai Wang, Liqing Ding, Hongdong Li, Yaohang Li, Jianxin Wang

Computer Science Faculty Publications

The 3D organization of chromatin plays a fundamental role in gene regulation, cellular function, and disease mechanisms. However, current experimental techniques, such as Hi-C, remain costly and labor-intensive, limiting their application in large-scale and disease-related studies. To address this challenge, ChromNet is presented, a multi-task learning framework that integrates epigenetic signals across diverse cell types to enable high-precision prediction of chromatin architecture. By incorporating noise perturbation and auxiliary classification tasks, ChromNet improves the identification of topologically associating domains (TADs) and cell-type-specific chromatin structures, demonstrating superior generalization performance. Notably, ChromNet accurately predicts chromatin interactions in acute myeloid leukemia (AML) samples by …

A Comprehensive Overview Of Neurophysiological Correlates Of Cognitive Impairment In Amyotrophic Lateral Sclerosis, Seyyed Bahram Borgheai, Brie E. Achorn, Alyssa H. Zisk, Sarah M. Hosni, Karl E. G. Richter, Frank S. Menniti, Yalda Shahriari

Computer Science Faculty Publications

Amyotrophic lateral sclerosis (ALS) is a progressive neurodegenerative disease that leads to the gradual loss of motor control, typically resulting in paralysis and death within 3 to 5 years of diagnosis. ALS shares neuropathological and genetic associations with fronto-temporal dementia (FTD), a neurodegenerative condition primarily impacting cognitive functions. These two conditions are increasingly viewed as manifestations of a single molecular disease process that affects distinct brain systems, impacting motor neuronal pathways in ALS and fronto-cortical functions in FTD. However, this simple dichotomy belies the complexity of these conditions. In particular, patients with primary motor ALS can also experience significant cognitive …

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

Computer Science Faculty Publications

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