A5021524144- Radiomics and Machine Learning in Medical Imaging
- Colorectal Cancer Screening and Detection
- Inflammatory Bowel Disease
- Liver Disease Diagnosis and Treatment
- Artificial Intelligence in Healthcare and Education
- Gallbladder and Bile Duct Disorders
- Liver Diseases and Immunity
- Liver Disease and Transplantation
- Machine Learning in Healthcare
- Pediatric Hepatobiliary Diseases and Treatments
- Gastrointestinal Bleeding Diagnosis and Treatment
- Diet, Metabolism, and Disease
- Gastrointestinal disorders and treatments
- Diagnosis and treatment of tuberculosis
- Gastroesophageal reflux and treatments
- Dental Research and COVID-19
- Nutrition and Health in Aging
- Advanced Chemical Sensor Technologies
- Clinical Nutrition and Gastroenterology
- Gut microbiota and health
- Topic Modeling
- Hepatitis C virus research
- Health Systems, Economic Evaluations, Quality of Life
- Vagus Nerve Stimulation Research
- Stoma care and complications
Virginia Hospital Center
2023-2025
Hunter Holmes McGuire VA Medical Center
2021
Virginia Commonwealth University
2012-2021
Inova Fairfax Hospital
2018-2020
University Health System
2020
Introduction: Gastroenterologists are prone to endoscopy-related musculoskeletal injuries (ERI). Current interventions lack real-time monitoring and feedback. ErgoGenius©, a novel artificial intelligence computer-vision tool, addresses this gap by providing continuous posture assessment feedback without wearable motion trackers. The aim of study was determine the feasibility ErgoGenius, its accuracy compared human appraisers, ability detect abnormal posture. Methods: conducted at two large...
Studies showed that nicotine has a positive influence on symptoms of ulcerative colitis. In the present study, we explored effect treatment using different routes administration in dextran sodium sulfate (DSS) colitis mouse model. We also investigated effects cotinine, major metabolite nicotine, C57BL6 adult male mice were given DSS solution freely drinking water for seven consecutive days, and tap was thereafter. Disease severity, length colon, colon tissue histology, inflammatory markers,...
Dyslipidemia is one of the common risk factors for NAFLD and associated with cardiovascular (CV) mortality, which most cause death in NAFLD. Lipid-lowering agents (LLAs) are used to reduce CV events general population. Our aim was assess whether use LLAs patients can mortality. We third National Health Nutrition Examination Survey mortality linked files. Mortality determined from Death Index records through 2011. diagnosed by ultrasound after exclusion other causes liver disease. After...
INTRODUCTION: Bowel movement (BM) frequency is used to titrate lactulose for hepatic encephalopathy (HE). However, stool consistency using the Bristol scale (BSS, 0–7) often ignored. METHODS: The study included pre-BSS and post-BSS cohorts. BSS was incorporated into decision-making after training in outpatients with cirrhosis. Two 3 BMs/d 3–4 were considered normal, whereas rest high or low; concordance between metrics evaluated. Medication changes 6-month admissions compared this group...
Abstract Introduction While general-purpose large language models(LLMs) were able to pass USMLE-style examinations, their ability perform in a specialized context, like gastroenterology, is unclear. In this study, we assessed the performance of three widely available LLMs: PaLM-2, GPT-3.5, and GPT-4 on most recent ACG self-assessment(2022), utilizing both basic prompt-engineered technique. Methods We interacted with chat interfaces GPT-4. first applied prompt approach, providing each exam...
Primary biliary cholangitis (PBC) is an autoimmune liver disease that can lead to cirrhosis and failure. Our aim was assess the recent trends in mortality rates health care utilization of patients with PBC seen inpatient setting United States. We used National (Nationwide) Inpatient Sample data (2005‐2014). The study population included adults PBC, using International Classification Diseases, Ninth Revision codes. Trends PBC‐related discharges, total charges, length stay (LoS), in‐hospital...
In the United States in 2014 approximately 1.7 million adults were hospitalized with sepsis, resulting about 270,000 deaths. Malnutrition patients contributes to increased morbidity, mortality, and costs, especially critically ill population.Our goal was investigate prevalence of malnutrition sepsis impact it has on clinical financial outcomes our most patients.We implemented nutritional screening by a registered dietitian 1000 admitted specialized care units. We calculated malnutrition,...
Abstract BACKGROUND IBD constitutes a diverse and progressive spectrum of chronic illnesses, presenting formidable management challenges for both patients healthcare providers. Due to the inherent unpredictability disease progression, proactive monitoring strategies are crucial optimal management. The linchpin in is patient engagement, which necessary continuous activity. GI practices using SonarMD, technology-driven care coordination company specializing IBD, have consistently maintained an...
Background and Aims: This study evaluates the medical reasoning performance of large language models (LLMs) vision (VLMs) in gastroenterology. Methods: We used 300 gastroenterology board exam-style multiple-choice questions, 138 which contain images to systematically assess impact model configurations parameters prompt engineering strategies utilizing GPT-3.5. Next, we assessed proprietary open-source LLMs (versions), including GPT (3.5, 4, 4o, 4omini), Claude (3, 3.5), Gemini (1.0),...
Introduction: The gut microbiome (GM) exhibits multifunctional redundancy due to different bacteria sharing a capacity for similar metabolic function. Despite an extreme diversity in taxonomy, function is much less diverse. Fecal metabolomics, the quantification of GM metabolites, has demonstrated profiles health and disease. Patterns volatile organic compounds (VOCs) produced by metabolome have ability separate patients with Inflammatory Bowel Disease from healthy controls. Unfortunately,...
Introduction: The application of artificial intelligence (AI) in healthcare has seen rapid progression, with large language models (LLMs) emerging as essential tools due to their proficiency assimilating unstructured clinical data and generating meaningful inferences. LLMs have demonstrated potential executing routine tasks. We aim assess the aptitude widely accessible perform a specific function: providing recommendations for polyp surveillance colonoscopy consistent society guidelines....