Diagnosis Commons^™

Advocateai: A Human-In-The-Loop Artificial Intelligence Platform To Improve Diagnostic Trajectories And Patient Empowerment In Chronic Pelvic Pain, Gayatri Bhanot, Ashley Kochans

InnovateHER Meeting 2026

Chronic pelvic pain (CPP) affects up to 27% of women globally^1, yet diagnosis takes 4 – 12 years on average² — a crisis driven by healthcare fragmentation, systemic gender bias, and a 62% rate of symptom dismissal by healthcare providers³. AdvocateAI is a human-in-the-loop AI platform designed to empower patients to accelerate their own diagnostic journey. By synthesizing fragmented medical records and patient-reported symptoms, the tool creates structured clinical summaries and personalized advocacy scripts. Here, we present our findings from discovery, including a landscape analysis of available CPP treatments, a prototype co-designed by patients, and custom …

Comparing The Use Of Measured And Smoothed Data In Forecasting Visual Field Tests Using Deep Learning, Ashkan Abbasi, Sowjanya Gowrisankaran, Wei-Chun Lin, Xubo Song, Bhavna Josephine Antony, Gadi Wollstein, Joel Schuman, Hiroshi Ishikawa

Wills Eye Hospital Papers

OBJECTIVE: To evaluate the impact of training and testing deep learning (DL) models for visual field (VF) forecasting using input-target pairs in which the target is either the measured VF test result, or its smoothed counterpart constructed via linear regression.

DESIGN: A retrospective data analysis study evaluating DL models for VF forecasting under multiple training and testing configurations.

SUBJECTS AND CONTROLS: A total of 1400 subjects (healthy and glaucoma patients) with 19 437 reliable Humphrey VF (24-2 Swedish Interactive Threshold Algorithm) tests collected from longitudinal cohorts at the University of Pittsburgh and New York University.

METHODS: Three DL-based pointwise VF …

A History Of Native Medical Auxiliaries, Tanzania:1920s To The 1960s, Irene Gabriel Ndosi, Ashura Jackson Ngoya

Journal of Humanities and Social Sciences

This paper examines the role and evolution of Native Medical Auxiliaries (NMAs) in Kilimanjaro, Tanzania, during British colonial rule between the 1920s and 1960s. It argues that NMAs were not merely subordinates within the colonial medical system but active agents who negotiated and blended Western medical practices with indigenous healing knowledge. Drawing on archival records and oral histories, the paper finds that NMAs filled critical gaps in healthcare delivery, particularly in rural areas, while simultaneously preserving local therapeutic traditions. By applying Local Agency Theory, the paper highlights the NMAs’ strategic engagement with colonial structures and their contribution to shaping hybrid …

Stroke Mimics And Stroke Chameleons: Leveraging The False Positive/False Negative Diagnostic Schema In Resident Teaching, James Espinosa, Alan Lucerna

Rowan-Virtua Research Day

Background

Stroke mimics and stroke chameleons contribute significantly to diagnostic uncertainty in Emergency Medicine. Traditional teaching often relies on enumerating examples, yet residents struggle to internalize these distinctions.

Objective

To present a conceptual teaching framework that maps stroke mimics to false positives and stroke chameleons to false negatives, leveraging pre-existing diagnostic schemas.

Methods

Using representative cases—including hypoglycemic hemiparesis and spinal epidural lipomatosis presenting as stroke mimic—we developed an explanation for residents involving framing mimics as false positives and chameleons as false negatives.

Results

Framing mimics as false positives and chameleons as false negatives activates existing learner schemas related to sensitivity …

Point-Of-Care Intestinal Ultrasound Is Associated With Reduced Colonoscopy Utilization And Improved Clinical Decision-Making In Ibd, Lakumi Dias, Ashlyn Mcclelland, Amy Glasofer, Charalampos Papachristou, Yecheskel Schneider, Sanket Patel

Rowan-Virtua Research Day

Background:

Point-of-care intestinal ultrasound (IUS) enables real-time assessment of bowel inflammation, and it is underutilized in the United States. IUS provides visualization of bowel wall thickness, vascularity, and complications without radiation or bowel preparation. Prior studies demonstrate that IUS changes management and reduces reliance on invasive testing. This study hypothesizes that IUS will impact downstream clinical decision-making in a U.S. outpatient IBD cohort by decreasing invasive procedures and supporting appropriate treatment decisions.

Methods:

A retrospective cohort study was performed. Logistic regression and chi-square tests assessed associations between IUS use, colonoscopy referral, hospital utilization, and treatment modification. A derived “surveillance-due” variable …

The Case For Intraprocedural Ultrasound Guidance In Lumbar Puncture--From Landmarking To Navigation In Lumbar Puncture. A Conceptual Review And Research Agenda, James Espinosa, Frank Wheeler, Robin Lahr, Sergey Medlenov, Alan Lucerna, Henry Schuitema

Rowan-Virtua Research Day

Ultrasound guidance for lumbar puncture (LP) is well established for pre-procedural landmark identification, particularly in patients with difficult anatomy. However, most current approaches discontinue ultrasound prior to needle insertion, returning the operator to a blind technique. Current emergency medicine ultrasound guided intravenous line insertion demonstrate feasibility of real-time needle visualization.  However,  the development and adoption of real-time guidance in the setting of lumbar puncture remains limited. Prior simulation work demonstrated that ergonomics, operator experience, and workflow integration significantly influence performance in ultrasound-assisted LP (Horn, Espinosa et al., 2016).  Here we make the case that LP is not a static targeting …

Evaluating The 4mm Endometrial Thickness Threshold: Racial Disparities In Ultrasound Sensitivity And Diagnostic Delay, Ngozi Ikpeama, Sophia Vogiatzidakis, Xuezhi Jiang, Elizabeth Hertz, Vitoria Chaves, Peter Schnatz

Rowan-Virtua Research Day

Title: Evaluating the 4mm Endometrial Thickness Threshold: Racial Disparities in Ultrasound Sensitivity and Diagnostic Delay

Background: Current ACOG guidelines utilize a 4mm endometrial thickness (ET) threshold via transvaginal ultrasound (TVUS) to exclude malignancy in postmenopausal women. However, recent evidence suggests these standardized thresholds may not be equally effective across all racial cohorts. This systematic review evaluates the diagnostic performance of the 4mm threshold specifically in Black patients.

Methods: A systematic search of peer-reviewed literature was conducted to identify studies comparing TVUS sensitivity and clinical outcomes between racial groups. Data were extracted focusing on the diagnostic sensitivity of the 4mm threshold, …

Isolated Giant Aneurysm Of The Acute Marginal Branch Of Right Coronaryartery Presenting As Nstemi: Successful Direct Surgical Repair Preserving The Native Flow, Sai Kumari Ms., Anbarasu Mohanraj Dr, Saranya Damodaran Ms

Journal Of Indian Physician Associates

Abstract

Background: A “giant” coronary artery aneurysm is variably defined in the literature—commonly as a dilatation of a coronary vessel exceeding four times the diameter of the adjacent normal segment, or exceeding a fixed threshold such as > 8 mm or > 20 mm in diameter^1.

Case presentation: We report the case of a 61-year-old woman with type II diabetes mellitus and systemic hypertension, who presented with breathlessness and chest pain radiating to the back. She had recently suffered a non-ST elevation myocardial infarction (NSTEMI) and was found on coronary angiography to have a large aneurysm of the acute marginal branch …

Determinants Of Hypertension Awareness And Control In Kenya: A Secondary Analysis Of National Survey Data, Alexander K. Davis

Honors Theses

In low- and middle-income countries (LMICs), cardiovascular diseases (CVDs) are prevalent and pose a major concern as the current healthcare systems are oriented primarily towards communicable diseases. The largest contributor to CVDs, hypertension, is a significant issue in Kenya, a model LMIC. Based on previous studies in this lab, high rates of hypertension are present in the region of Kasigau, Kenya. Kasigau is a small region within Taita-Taveta County, Kenya. Traditional risk factors are not necessarily predictive of hypertension in all regions of Kenya. This study aims to address the lack of tested risk factors for hypertension in Kenya and …

Characterization Of Circulating Extracellular Proteome In Plasma Samples Of Triple-Negative Breast Cancer Patients, Brionna Wilson

Honors Theses

Extracellular vesicles (EVs) are membrane-bound vesicles secreted by cells in the body that play an important role in intercellular signaling, immune modulation, and transfer of biomolecules between cells. EV s reflect the physiological state of their cells of origin, so they are being explored as potential noninvasive biomarkers for cancer detection and monitoring. Triple-negative breast cancer (TNBC), an aggressive subtype lacking targeted therapies, is difficult to detect early and currently has no reliable prognostic biomarkers. This study aimed to quantify EV concentrations in the blood serum of TNBC patients (n=40) compared with cancer-free healthy controls (n=35) as well as determine …

Validation Of A Real-Time Pcr Laboratory Developed Test For The Detection Of Pneumocystis Jirovecii In Bronchoalveolar Lavage Samples, Caitlyn Moon

Honors Scholar Theses

Pneumocystis jirovecii is an opportunistic, host-obligate fungal pathogen responsible for causing P. jirovecii pneumonia (PJP) in humans. PJP is treated with trimethoprim-sulfamethoxazole (TMP-SMX), a strong broad-spectrum antibiotic that carries risk of renal and hepatotoxicity. Therefore, rapid diagnosis or exclusion of PJP is crucial to ensure PJP-positive patients receive effective treatment and PJP-negative patients avoid unnecessary antibiotics. Unlike most microorganisms, P. jirovecii cannot be cultured, presenting complications for the typical methods of diagnosing fungal pathogens. Historically, the gold standard for diagnosis was direct microscopic examination with stains such as methenamine silver and calcofluor white, but this diagnostic technique requires highly skilled …

Sepsis As An Immune Continuum: Cytokine Storm To Lymphopenia And Pics, Chelsey King

Senior Honors Theses

Sepsis is a leading cause of morbidity and mortality worldwide, driven by a dynamic immune continuum that progresses from early hyperinflammation to profound immunosuppression. This review examines the three overlapping phases of sepsis: the inflammation-mediated cytokine storm driven by dysregulated PRR activation, NF-κB signaling, and NETosis; apoptosis-driven lymphopenia involving caspase-mediated lymphocyte death, dendritic cell dysfunction, and metabolic exhaustion; and prolonged immunoparalysis culminating in persistent inflammation, immunosuppression, and catabolism syndrome (PICS). Key mechanisms linking these phases, including the co-existence of hyper- and hypo-inflammatory states, are synthesized alongside relevant clinical biomarkers such as IL-6, HLA-DR, and single-cell immune profiles. This review highlights …

Dementia Detection In Low-Resource Languages: Evaluating Translation-Assisted Transfer Learning For Multilingual Clinical Assessment, Kylar A. Deloach

Honors Theses

Alzheimer's disease (AD) is a growing global health concern, with millions of people affected worldwide and cases expected to rise significantly in the coming decades. Early detection is critical for patient treatment and care, and recent advances in natural language processing (NLP) have shown promise in identifying linguistic markers associated with AD. However, most existing work has focused on English, leaving speakers of other languages with limited access to such tools. This study investigates how effective AD detection models trained on English data are at transferring to Greek, a low-resource language with limited dementia-related speech data available. We propose a …

Organic Synthesis Of A Hydrazine Functionalized Ammonium Compound For Improved Capture Of Aldehyde Metabolites From Exhaled Breath, Po'iu N. Burgo

Undergraduate Theses

Breath analysis has emerged as a non-invasive and inexpensive way to screen for respiratory diseases. This technique involves measuring concentrations of specific metabolites found in exhaled breath that serve as a biomarkers for disease. A subclass of volatile organic compounds called α,β-Unsaturated aldehydes, products of the lipid peroxidation mechanism, are underrepresented as biomarkers of lung cancer. These have been found to have relatively increased concentrations in the exhaled breath of lung cancer patients compared to a healthy patient. One of the reasons that these metabolites have been underreported is that the techniques used to measure and characterized exhaled metabolites do …

Robust Non-Invasive Cardiac Index Prediction Via Feature Integration And Data-Augmented Neural Networks, Chih-Hao Chang, Mei-Ling Chan, Yu-Hung Fang, Po-Lin Huang, Tsung-Yi Chen, Tsun-Kuang Chi, I Elizabeth Cha, Tzong-Rong Ger, Kuo-Chen Li, Shih-Lun Chen, Liang-Hung Wang, Jia-Ching Wang, Patricia Angela R. Abu

Department of Information Systems & Computer Science Faculty Publications

Concurrent with the rising consumption of ultra-processed, high-calorie diets and the decline in physical activity, obesity and related cardiovascular conditions among young adults have continued to increase, becoming an important global public health concern. This study integrates non-invasive Internet of Things (IoT) sensing devices, including the TERUMO ES-P2000 blood pressure monitor (Terumo Corp., Tokyo, Japan) and the PhysioFlow PF07 Enduro cardiac hemodynamic analyzer (Manatec Biomedical, Poissy, France), with an artificial neural network (ANN) for cardiac index (CI) prediction. Through appropriate data preprocessing and model training strategies, the generalization ability and stability of the proposed CI prediction model were significantly enhanced. …

Ms-Gator: Multi-Scale Graph Attention With Topological Reasoning For Segmentation And Classification Of Prostate Cancer Based On Gleason Scores Using Histopathology Images, Sujata Patil, Mahadeva Swamy, Kavitha Sooda, Rajanikanth Vadigepalli, Khalid Nazim Abdul Sattar, Md Rafeeq

Department of Pathology, Anatomy, and Cell Biology Faculty Papers

Prostate cancer is one of the prevalent and potentially fatal malignancies, affecting men globally. Accurate segmentation and classification of prostate cancer in histopathology images remain challenging due to complex tissue architecture, staining variability, and high inter-observer differences in manual diagnosis. To address these challenges, this research proposes a Multi-Scale Graph Attention with Topological Reasoning (MS-GATOR) for segmentation and classification of prostate cancer based on Gleason Scores (GS). The MS-GATOR incorporates topological reasoning with hierarchical biological structures by constructing a graph-based representation among three spatial scales such as nuclei, glands, and tissues using Delaunay triangulation to capture both geometric and photometric …

Improving Anesthesia Provider Confidence In The Identification, Management, And Treatment Of Postoperative Delirium, Brittany M. Whistle, Charles Dustin Phelps

Scholars Week

Purpose: Postoperative Delirium (POD) is a potentially devastating complication of anesthesia that is poorly understood by clinical staff leading to poor outcomes for surgical patients. This study is meant to determine if a focused knowledge presentation accompanied by visual aids could increase anesthesia providers confidence in identifying, diagnosing, and treating Postoperative Delirium.

Methodology: Utilizing a statistical model to analyze respondents results on a standardized test administered before and after an informational presentation with visual aids on the topic of Postoperative Delirium.

Results: Results indicated a statistically significant difference between pretest and posttest scores, with a p-value of .002, t(11) = …

Therapeutic Potential Of Bacillus Coagulans Unique Is2 Probiotic Supplementation On Early Periodontitis Patients: A Randomized Controlled Trial, Renu Gaur, Aysha Jebin A, Prabhuji M L V

International Arab Journal of Dentistry

Objectives: Bacillus coagulans (B. coagulans) is a probiotic commonly used for broad spectrum of systemic infections, its potential to treat oral infections, particularly periodontitis, is still being studied.The aim of the study was to evaluate the efficacy of probiotic B. coagulans as an adjunct to SRP in periodontitis patients.

Methods: Thirty systemically healthy patients with stage I/ stage II and grade A/ grade B periodontitis were selected and randomly divided into two groups. The control group received SRP along with placebo and the test group received SRP + B. coagulans probiotic chewable tablets. At baseline, one month, and three months …

Effect Of Pre-Training Patients Using A Self-Directed Slideshow Presentation On Visual Field Reliability In First-Time Test Takers, Lillian M. Centlivre B.S., Derek Zahnleuter B.S., Rahul Babu B.S., Chaesik Kim, Kaitlin Ziadeh Md, Hanna Simmons Md, Vivian Rajeswaren Md, Aleskey Parker Williams Do, Jacob Im Md, Aleksey Mishulin Md, Faisal Ridha Al-Timimi Md, Hassan Tokko

Medical Student Research Symposium

Title: Effect of Pre-Training Patients Using a Self-Directed Slideshow Presentation on Visual Field Reliability in First-Time Test Takers

Authors: Lillian Centlivre BS, Derek Zahnleuter BS, Rahul Babu BS, Chaesik Kim BSEE, Kaitlin Ziadeh MD, Hanna Simmons MD, Vivian Rajeswaren MD, Aleksey Parker Williams DO, Jacob Im MD, Aleksey Mishulin MD, Faisal Ridha Al-Timimi MD, Hassan Tokko MD

Background: Visual field (VF) testing is essential for detecting glaucoma, but reliability is limited by patient inexperience and poor fixation. Prior studies report VF test reliability around 59%, primarily attributed to increased fixation loss (FL). Other studies note 75.9% reliability using training videos …

Artificial Intelligence In Radiology: A Comparative Study Of Accuracy And Efficiency Across X-Ray, Ct, And Nuclear Medicine, Courtney J. Mello, Sophia D. Galvan, Britney R. Williams, Tuyen T. Thai, Phuong P. Mor, Saleha Zafar

Research Methods Poster Session 2026

Artificial intelligence (AI) is increasingly used in radiology to improve diagnostic accuracy and workflow efficiency; however, there is limited standardized research comparing its performance across imaging modalities. This study aimed to evaluate the accuracy and efficiency of AI in X-ray, computed tomography (CT), and nuclear medicine. A systematic review was conducted following PRISMA guidelines, analyzing peer-reviewed studies published between 2015 and 2025. Data were extracted on key performance metrics, including sensitivity, specificity, interpretation time, and error rates, to enable cross-modality comparison. Results demonstrated that AI achieved high diagnostic accuracy in X-ray imaging, with average sensitivity and specificity near 91% and …