Open Access. Powered by Scholars. Published by Universities.®

Digital Commons Network™

Open Access. Powered by Scholars. Published by Universities.®

2026

Discipline
Institution
Keyword
Publication
Publication Type
File Type

Articles 54991 - 55020 of 55765

Full-Text Articles in Entire DC Network

Propensity Score Matching Accounting For Longitudinal Trends Before Baseline With Group-Based Trajectory Modeling, Dustin R. Bastaich Jan 2026

Propensity Score Matching Accounting For Longitudinal Trends Before Baseline With Group-Based Trajectory Modeling, Dustin R. Bastaich

Theses and Dissertations

Propensity score matching is used in observational studies to balance baseline attributes between a treatment of interest and a control group. Propensity score matching typically relies on baseline variables, but longitudinal trends in patient characteristics can also influence treatment decisions and subsequent health outcomes. This dissertation extends standard approaches by explicitly incorporating longitudinal trajectories of key variables into the propensity score estimation process.

Trends in a longitudinal variable prior to baseline were characterized using group-based trajectory modeling. A two-step modeling approach was implemented where trajectory groups of a key variable were first estimated and then included as covariates in the …


Substance Use Behaviors And Treatment Engagement In Individuals With Severe Psychopathology With And Without Comorbid Obesity, Rachel M. Madera-Arnold Jan 2026

Substance Use Behaviors And Treatment Engagement In Individuals With Severe Psychopathology With And Without Comorbid Obesity, Rachel M. Madera-Arnold

Theses and Dissertations

Research has found significantly higher rates of both substance use and obesity among individuals with SMI compared to population samples which in turn can lead to worsening health outcomes. Despite this, there is limited research on the co-occurrence of obesity, substance use, and SMI and how these conditions may interact to affect patient outcomes. In addition, there are many gaps in the research regarding the relationship between substance use and body weight, appetite and/or eating behaviors. This study conducted a secondary analysis of the NSDUH 2021 survey that characterized substance use and disorders among individuals who had severe psychopathology, examined …


Cb1 Allosteric Modulation: Preclinical Insights Into Therapeutic Potential And Misuse Liability, Mohammed A. Mustafa Jan 2026

Cb1 Allosteric Modulation: Preclinical Insights Into Therapeutic Potential And Misuse Liability, Mohammed A. Mustafa

Theses and Dissertations

Cannabinoid type-1 (CB1) allosteric modulators represent a promising approach to modulate CB1 receptor signaling by binding to distinct receptor sites, without producing adverse cannabimimetic and dependence-related effects associated with Δ9-tetrahydrocannabinol (THC) and other CB1 agonists. This dissertation investigates the pharmacological, behavioral, and dependence-related profiles of CB1 allosteric modulators for their therapeutic potential and misuse liability. Presented here, the chiral CB1 positive allosteric modulator (PAM) ZCZ011 was resolved into its R- and S-enantiomers and characterized across in vitro and in vivo assays. Both enantiomers enhance CB1 agonist activity and produce intrinsic effects in vitro. Behaviorally, they produce antinociceptive effects in the …


Munajat: Design As A Dialogue With The Divine, Shawky Abdalla Jan 2026

Munajat: Design As A Dialogue With The Divine, Shawky Abdalla

Theses and Dissertations

Contemporary design discourse remains grounded in functional, seemingly user-centered paradigms, often neglecting what lies beyond the tangible within a human experience. This research challenges such frameworks by positioning design as a dialogue with what exceeds the physical, moving toward the experiential, where meaning precedes and informs form. Drawing on Islamic philosophy, particularly the relationship between zahir and batin (outward form and inward meaning), the study repositions design as a medium for remembrance (dhikr) rather than mere utility.

Through a critique of modernist and postmodernist principles, the research proposes a series of objects that engage with memory, introspection, and transcendence in …


Within The Ruin: A Modern Brewery Rebirth, Karim Asarzadeh Jan 2026

Within The Ruin: A Modern Brewery Rebirth, Karim Asarzadeh

Theses and Dissertations

This thesis project focuses on the revitalization of the historic ruins of the James River Steam Brewery in Richmond, Virginia. The project transforms the forgotten industrial structure into a modern brewery with a second-floor restaurant addition and community gathering spaces while preserving the historic masonry ruins. It showcases a holistic design approach that considers all aspects of the building, including its connection to the urban context and landscape, as well as its architecture, interiors, and furniture. The project demonstrates how a holistic design approach can create stronger spatial connections and more cohesive environments. In particular, it offers a strategy for …


Characterization Of Microrna Expression In Neuron-Enriched Extracellular Vesicles During Early Life, Allison Molen Jan 2026

Characterization Of Microrna Expression In Neuron-Enriched Extracellular Vesicles During Early Life, Allison Molen

Theses and Dissertations

Extracellular vesicles (EVs) are membrane-bound sacs released by cells that carry molecular cargo reflective of their cell of origin. EVs enriched using L1 cell adhesion molecule (L1CAM) as a marker of putative neuronal origin can cross the blood–brain barrier and provide a minimally invasive window into brain-related processes. Exosomal microRNA (miRNA) regulate gene expression and have been implicated in psychiatric disorders, including major depressive disorder (MDD). However, measuring and analyzing miRNA from L1CAM-positive EVs presents substantial analytical challenges due to low abundance and sparse detection across samples.

Plasma samples from participants recruited through the Mid-Atlantic Twin Registry (MATR) were used …


Spell Of Forty Small Failings, Erin B. Ehren Jan 2026

Spell Of Forty Small Failings, Erin B. Ehren

Theses and Dissertations

Spell of Forty Small Failings is a collection of images and writings that draws from an unruly range of literary forms, academic disciplines, and religious cannons in order to address the Divine—all that which exists on account of the phenomena of what it is to see and be seen: to hear and be heard: to touch and be touched: to know and be known, and through that knowing proceed beyond mediation. I wrote this thesis for me in the hopes that all along I was writing for you.


24-H Circadian Rest-Activity Rhythms And Physical Frailty In Older Adults: A Biopsychosocial Perspective On Sex Differences And Social Capital, Jisu Kim Jan 2026

24-H Circadian Rest-Activity Rhythms And Physical Frailty In Older Adults: A Biopsychosocial Perspective On Sex Differences And Social Capital, Jisu Kim

Theses and Dissertations

Physical frailty is a prevalent geriatric syndrome characterized by age-related decline across multiple physiological systems. Physical frailty is associated with an elevated risk of adverse health outcomes, including chronic disease progression and all-cause mortality, representing a significant and growing public health concern. Disrupted circadian rest-activity rhythms (RARs) are increasingly recognized as clinically meaningful markers of physical frailty in older adults. However, the extent to which biological sex and social determinants of health (SDoH), particularly social capital, contribute to or modify the associations between RARs and physical frailty remains underexplored.

Therefore, this dissertation summarizes the existing literature on age-related changes in …


Centering Individual Well-Being In Learning Environments: Academic Stress, Psychological Safety, And Digital Discourse, Rachel Niemira Namboodri Jan 2026

Centering Individual Well-Being In Learning Environments: Academic Stress, Psychological Safety, And Digital Discourse, Rachel Niemira Namboodri

Theses and Dissertations

Statement of Problem

How do we guide students through school while supporting their emotional and psychological health? This question lies at the heart of contemporary educational psychology research, as growing evidence demonstrates that students’ academic achievement and psychological well-being are deeply intertwined with their experiences in learning environments (Baumeister & Leary, 1995; Edmondson & Lei, 2014; Gopalan & Brady, 2020; Song et al., 2024; Spencer, 1995; Walton & Cohen, 2011). Decades of scholarship affirm that students’ academic achievement and psychological well-being are deeply intertwined with how they experience schools, classrooms, peers, teachers, and institutional structures (Baumeister & Leary, 1995; Edmondson …


Characterization Of Growth, Motility And C-Di-Gmp In Selenomonas Sputigena Atcc 35185, Margaret E J Stiker Jan 2026

Characterization Of Growth, Motility And C-Di-Gmp In Selenomonas Sputigena Atcc 35185, Margaret E J Stiker

Theses and Dissertations

Selenomonas sputigena is an obligate anaerobic, Gram-negative pathobiont that transitions from a low-abundance commensal bacteria to a structural component in dysbiotic oral biofilms associated with early childhood caries and periodontitis. Analysis of S. sputigena ATCC 35185 cultures optimized in TYGVS media revealed robust growth, characteristic crescent morphology with flagellar tuft motility, and strong monospecies biofilm formation comparable to Streptococcus mutans via crystal violet assays.

ELISA quantification demonstrated significantly elevated c-di-GMP levels in sessile biofilm fractions relative to motile planktonic cells (p=0.0009), establishing the secondary messenger’s correlation with the motile-sessile lifestyle switch. Recombinant expression and purification yielded PilZ-domain effector proteins, Selsp_1666 …


Maintaining Legitimacy While Managing Competition: Do Transplant Survival Ratings Affect Kidney Transplant Waitlisting?, Andrew Placona Jan 2026

Maintaining Legitimacy While Managing Competition: Do Transplant Survival Ratings Affect Kidney Transplant Waitlisting?, Andrew Placona

Theses and Dissertations

Statement of problem and objectives: Waitlisting is an essential step towards kidney transplantation among people with end-stage kidney disease (ESRD). There are no universal standards for waitlisting ESRD patients and how waitlists are managed in kidney transplant programs is opaque and under-studied. This study investigated whether the quality ratings of kidney transplant programs based on their one-year survival rates were associated with waitlist outcomes, including the number of waitlist additions, waitlist removals, the risk profiles of patients added or removed from a kidney transplant program’s waitlist, and whether market competition among kidney transplant programs attenuated these relationships.

Procedure followed: …


The Mundo I Imagine, Angeliky Castrellon Jan 2026

The Mundo I Imagine, Angeliky Castrellon

Theses and Dissertations

My work investigates the human experience of belonging and how the force of displacement alters the perception of one's present and enables dissociation. After leaving my home and starting a new life overseas, coming back never felt the same; I couldn’t find peace and comfort anywhere. This made me create an imaginary world called “Mundo.” Shelters for the souls of the displaced, looking for comfort. As I became a graduate student in the Craft/Materials Studies department, my perspective widened, and my work itself answered a question for me: I want to be comfortable everywhere; how can my home be everywhere …


What’S Sleep Got To Do With It? A Mixed Methods Exploration Of The Feasibility, Acceptability, And Initial Outcomes Of Group Cbt For Insomnia In Parkinson’S Disease, Claire M. Williams Jan 2026

What’S Sleep Got To Do With It? A Mixed Methods Exploration Of The Feasibility, Acceptability, And Initial Outcomes Of Group Cbt For Insomnia In Parkinson’S Disease, Claire M. Williams

Theses and Dissertations

Parkinson’s disease is a progressive neurodegenerative disease that is commonly associated with sleep disturbances, affecting up to 80 percent of individuals with Parkinson’s. Effective and accessible treatments for sleep problems in Parkinson’s disease remain limited. Cognitive Behavioral Therapy for Insomnia (CBTi) is a well-established, non-pharmacological treatment for insomnia but has been minimally studied in Parkinson’s populations. This study evaluated the feasibility, acceptability, and preliminary outcomes of a group-based CBTi intervention adapted for individuals with Parkinson’s disease. Participants engaged in a six-week group intervention that incorporated Parkinson’s-specific adaptations. Preliminary findings indicated that the adapted group CBTi intervention was generally feasible and …


Early Math Readiness And Later Achievement: A Longitudinal Study, Bailey Bontrager Jan 2026

Early Math Readiness And Later Achievement: A Longitudinal Study, Bailey Bontrager

Theses and Dissertations

The current body of literature provides much evidence that mathematics skills at the start of kindergarten are predictive of later mathematics achievement, and that students enrolled in early childhood education (ECE) programs are better prepared for mathematics at the start of kindergarten. However, the potential for children to develop mathematical skills prior to entering kindergarten relies on access to ECE programs and resources in families’ surrounding communities. Recent use of geospatial data collection techniques and measures of community resource availability have enabled researchers to examine specific localities for the ways in which community organizations and institutions support residents in particular …


Comparison Of Artificial Intelligence Vs Human Observer For Periapical Radiolucency Detection, Adam J. Pink Jan 2026

Comparison Of Artificial Intelligence Vs Human Observer For Periapical Radiolucency Detection, Adam J. Pink

Theses and Dissertations

Objective: The aim of this study was to assess the performance of an Artificial Intelligence (AI) program (OverJet AI) with that of experienced endodontic residents, endodontists, a radiologist, and dental students in detecting periapical radiolucencies using radiographic images.

Methods: One hundred and fifty periapical radiographic images were analyzed using the OverJet AI software to determine the presence/absence of a periapical radiolucency as well as the size (small 1-3mm, medium 4-6mm, and large 6+mm). The unaltered images were also evaluated by two endodontic residents, two practicing endodontists, an oral radiologist and two 4th year dental students.

Results: Agreement between the AI …


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 Jan 2026

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 Jan 2026

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 …


Examining Inclusive Computing Education For Blind Students In India, Akshay Kolgar Nayak, Yash Prakash, Md Javedul Ferdous, Sampath Jayarathna, Hae-Na Lee, Vikas Ashok Jan 2026

Examining Inclusive Computing Education For Blind Students In India, Akshay Kolgar Nayak, Yash Prakash, Md Javedul Ferdous, Sampath Jayarathna, Hae-Na Lee, Vikas Ashok

Computer Science Faculty Publications

The growing demand for computer professionals, driven by the expanding Information Technology industry, has led to numerous inclusive computing education efforts. These efforts have even included blind or visually-impaired (BVI) students, who are being increasingly encouraged to pursue education and a career in computing, despite the visually-oriented nature of the discipline. Extant literature has predominantly focused on identifying and addressing the accessibility barriers faced by BVI students to promote more inclusive learning environments. While few studies have also investigated the accessibility of computing education from the perspectives of BVI learners and instructors, these have been primarily situated in the Global …


Voxvista: Enhancing Screen Reading Experience For Online User Comments, Yash Prakash, Akshay Kolgar Nayak, Mohammed Shoaib Alyaan, Sampath Jayarathna, Hae-Na Lee, Vikas Ashok Jan 2026

Voxvista: Enhancing Screen Reading Experience For Online User Comments, Yash Prakash, Akshay Kolgar Nayak, Mohammed Shoaib Alyaan, Sampath Jayarathna, Hae-Na Lee, Vikas Ashok

Computer Science Faculty Publications

Online discussions have become integral to how people exchange ideas, form opinions, and participate in collective deliberation. While sighted users can comfortably engage with online discussions, blind users who are dependent on screen readers are forced to listen to long threads narrated in a single, monotonic voice that lacks prosodic variation, rhythm, or emotion. This robotic auditory experience not only deteriorates the user engagement with the content but also increases cognitive strain, by making it difficult to remain attentive and discern meaning beyond literal words. In an interview study, most blind participants reported that monotonous narration hindered their ability to …


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 Jan 2026

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 …


Exploring Large Language Models For Trustworthy Use: Insights From Research And Development, Sandeep Kalari, Sahithi Padidela, Vikas Ashok, Ravi Mukkamala Jan 2026

Exploring Large Language Models For Trustworthy Use: Insights From Research And Development, Sandeep Kalari, Sahithi Padidela, Vikas Ashok, Ravi Mukkamala

Computer Science Faculty Publications

Large Language Models (LLMs) are increasingly being adopted in a wide variety of domains, including sensitive domains such as healthcare and finance. However, persistent challenges such as unreliable data sources, privacy breaches, and hallucinated output continue to hinder their usage. We have experimented with several strategies to address these challenges. First, we developed BlockQwen, a blockchain-augmented framework that integrates decentralized trust validation, role-specific access control, and verifiable audit trails into the Qwen 2.5 LLM workflow. Second, we developed PrivAware, a multilayered privacy-enforcement framework, using a fine-tuned Flan-T5 model with self-attention masking, to safeguard data while maintaining high utility. Both systems …


Multisystem Predictors Of Dynamic Gait Stability Across Fall Risk In Older Adults, Ashwini Kulkarni, Neda Moghim, Ross Gore, Soumya Banerjee, Christopher K. Rhea, Brittany Samulski Jan 2026

Multisystem Predictors Of Dynamic Gait Stability Across Fall Risk In Older Adults, Ashwini Kulkarni, Neda Moghim, Ross Gore, Soumya Banerjee, Christopher K. Rhea, Brittany Samulski

Rehabilitation Sciences Faculty Publications

Gait stability arises from interactions between physiological, cognitive, and psychological systems, yet these domains are often assessed in isolation. This study examined multisystem predictors of anteroposterior margin of stability during walking (MoSAP) in community-dwelling older adults. Of 340 participants, 143 were retained after data quality screening (105 females; age: 70.8 ± 7.8 years). Participants completed the Physiological Profile Assessment (PPA), cognitive testing using Montreal Cognitive Assessment (MoCA), fear-of-falling evaluations using Modified Falls Efficacy Scale (MFES) and a biomechanical gait assessment during preferred and fast speeds. Participants were stratified into four PPA-based fall-risk groups: low, mild, moderate, and high risk. MoSAP …


Genomic Determinants Of Appetite Regulation And Their Role In Obesity Risk, Timothy J. Renier Jan 2026

Genomic Determinants Of Appetite Regulation And Their Role In Obesity Risk, Timothy J. Renier

Dartmouth College Ph.D Dissertations

Over 40% of US adults and 20% of children live with obesity. It is related to increased risks of diseases including type II diabetes and cancer, is a source of harmful stigma, and impairs child development. Appetitive traits describing patterns of food approach and avoidance behaviors may serve as windows into the underlying pathophysiology of obesity. As both obesity and appetitive traits are heritable, common genetic drivers of obesity may lead to phenotypic obesity through appetitive traits as a disease mechanism. Additionally, GLP-1 receptor agonists (GLP-1RAs) have been shown to exert their profound clinical effects in part by modulating appetite. …


Advancing Cns Tumor Management: Novel Modalities In Surgery, Radiation, And Chemotherapy, Armin David Tavakkoli Jan 2026

Advancing Cns Tumor Management: Novel Modalities In Surgery, Radiation, And Chemotherapy, Armin David Tavakkoli

Dartmouth College Ph.D Dissertations

Most tumors affecting the brain and spine are managed through a combination of surgical resection, radiation, and chemotherapy; however, operative morbidity from invasive surgery, the narrow therapeutic window of conventional radiotherapy, and poor blood-brain barrier penetration of systemic agents are critical barriers that hinder long term tumor control. This thesis presents three complementary strategies to advance brain and spine tumor therapy. First, we investigate laser interstitial thermal therapy (LITT) in the treatment of spinal tumors with metastatic epidural spinal cord compression, replacing “separation surgery” with a minimally invasive, image-guided approach that maximizes tumor ablation while preserving neurologic function. Second, we …


The Serotonin 1b Receptor In Psilocybin’S Therapeutic-Like Mechanisms: From Behavior To Network Reorganization, Sixtine Fleury Jan 2026

The Serotonin 1b Receptor In Psilocybin’S Therapeutic-Like Mechanisms: From Behavior To Network Reorganization, Sixtine Fleury

Dartmouth College Ph.D Dissertations

Mood disorders represent a substantial and growing global health crisis, with ~10 million adults in the US meeting criteria for a major depressive disorder (MDD). Current first-line treatments such as SSRIs require long-term daily administration and fail a significant proportion of patients, driving renewed interest in rapid-acting alternatives. Psilocybin, a serotonergic psychedelic, shows growing clinical evidence of efficacy in treating depressive and anxiety disorders, often producing therapeutic effects persisting weeks to months following a single dose. Yet, the neural mechanisms underlying these enduring effects remain poorly understood and have been largely attributed to the serotonin 2A receptor (5-HT2AR) based on …


Language Models For Enhanced Patient-Provider Communication: Methods, Measures, And Benchmarks, Joseph Gatto Jan 2026

Language Models For Enhanced Patient-Provider Communication: Methods, Measures, And Benchmarks, Joseph Gatto

Dartmouth College Ph.D Dissertations

In recent years, significant efforts have been made to integrate Large Language Models (LLMs) into healthcare. In this study, we explore how to improve patient-provider communication using LLMs --- with explicit focus on asynchronous communication through EHR-integrated web portals. Throughout this thesis, we describe three interconnected studies that allow us to adapt, train, and evaluate LLMs in asynchronous portal communications. The first study focuses on Patient Message Triage, which is the task of determining the medical urgency of patient-authored message content. We introduce a novel benchmark, alongside methods and training strategies producing a state-of-the-art and publicly available triage solution. Our …


The Influence, Dependency, And Targeting Of Fatty Acid Uptake In Er+ Breast Cancer, Abigail E. Goen Jan 2026

The Influence, Dependency, And Targeting Of Fatty Acid Uptake In Er+ Breast Cancer, Abigail E. Goen

Dartmouth College Ph.D Dissertations

Estrogen Receptor-positive/ Human Epidermal Growth Factor 2-negative, breast cancer (ER+/HER2- BC) is the most prevalent subtype of BC, impacting millions of individuals. Although early screening and treatment with endocrine therapy has greatly enhanced survival, this subtype sustains a steady increase of risk for recurrent disease for decades after diagnosis, indicating the persistence of residual cancer cells that are capable of maintaining dormancy for >20 years prior to metastatic outgrowth. Dormant cells reprogram metabolic pathways which can be profoundly influenced by the tumor microenvironment in promoting quiescence or proliferation. Fatty acid oxidation dependency has been noted as a hallmark of drug …


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 Jan 2026

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 …


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 Jan 2026

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 …


Designing Narrative-Based Ai Assistance For Sensemaking In Collaborative Environments: Case Studies In Education And Dementia Care, Dylan Edward Moore Jan 2026

Designing Narrative-Based Ai Assistance For Sensemaking In Collaborative Environments: Case Studies In Education And Dementia Care, Dylan Edward Moore

Dartmouth College Ph.D Dissertations

This thesis addresses a gap in the human-computer interaction literature regarding the design, development, and evaluation of narrative-based AI assistance for collaborative, complex problem solving. I explore this design space through three case studies across the domains of education and dementia care. This work encompasses multi-year industry partnerships and longitudinal fieldwork, user-centered design, dataset curation, model training, and system evaluation.

Specifically, the first case study considers a story-based web platform for teaching AI literacy through peer-generated, personalized narrative scaffolding. Learners on the platform showed significant knowledge gains and other learning-related outcomes. To describe the novel design of this system, I …