A5021115223- Machine Learning in Healthcare
- Biomedical Text Mining and Ontologies
- Computational Drug Discovery Methods
- Artificial Intelligence in Healthcare and Education
- Acute Ischemic Stroke Management
- Traumatic Brain Injury and Neurovascular Disturbances
- Electronic Health Records Systems
- Advanced Chemical Sensor Technologies
- Genomics and Rare Diseases
- Cholinesterase and Neurodegenerative Diseases
- BRCA gene mutations in cancer
- Genetic Associations and Epidemiology
- Traumatic Brain Injury Research
- Health, Environment, Cognitive Aging
- Bioinformatics and Genomic Networks
- Chemotherapy-induced cardiotoxicity and mitigation
- Synthesis of Tetrazole Derivatives
- Computational and Text Analysis Methods
- Intracranial Aneurysms: Treatment and Complications
- Topic Modeling
- Meta-analysis and systematic reviews
- Chronic Disease Management Strategies
- Advanced Causal Inference Techniques
- GDF15 and Related Biomarkers
- Long-Term Effects of COVID-19
Vanderbilt University Medical Center
2023-2025
Vanderbilt University
2020-2024
University of Virginia
2021
University of Virginia Health System
2019
1 Military Clinical Hospital with Outpatient Clinic
2014
Drug repurposing represents an attractive alternative to the costly and time-consuming process of new drug development, particularly for serious, widespread conditions with limited effective treatments, such as Alzheimer's disease (AD). Emerging generative artificial intelligence (GAI) technologies like ChatGPT offer promise expediting review summary scientific knowledge. To examine feasibility using GAI identifying candidates, we iteratively tasked proposing twenty most promising drugs in...
Abstract Objectives Phenotyping is a core task in observational health research utilizing electronic records (EHRs). Developing an accurate algorithm demands substantial input from domain experts, involving extensive literature review and evidence synthesis. This burdensome process limits scalability delays knowledge discovery. We investigate the potential for leveraging large language models (LLMs) to enhance efficiency of EHR phenotyping by generating high-quality drafts. Materials Methods...
Abstract Objective Diagnosis codes documented in electronic health records (EHR) are often relied upon to clinically phenotype patients for biomedical research. However, these diagnoses can be incomplete and inaccurate, leading false negatives when searching with phenotypes of interest. This study aims determine whether PheMAP, a comprehensive knowledgebase integrating multiple clinical terminologies beyond diagnosis capture phenotypes, effectively identify lacking relevant EHR codes....
The urgent need for safe and effective therapies Alzheimer's disease (AD) has spurred a growing interest in repurposing existing drugs to treat or prevent AD. In this study, we combined multi-omics clinical data investigate possible opportunities We performed transcriptome-wide association studies (TWAS) construct gene expression signatures of AD from publicly available GWAS summary statistics, using both transcriptome prediction models 49 tissues the Genotype-Tissue Expression (GTEx)...
Topic modeling utilizes unsupervised machine learning to detect underlying themes within texts and has been deployed routinely analyze social media for insights into healthcare issues. However, the inherent messiness of hinders full realization this technique’s potential. As such, we hypothesized that restricting medical concepts in specific related semantic types applying topic these could be a feasible approach overcome challenge traditional texts. Therefore, developed semantic-type-based...
Abstract Objective Pediatric patients have different diseases and outcomes than adults; however, existing phecodes do not capture the distinctive pediatric spectrum of disease. We aim to develop specialized (Peds-Phecodes) enable efficient, large-scale phenotypic analyses patients. Materials Methods adopted a hybrid data- knowledge-driven approach leveraging electronic health records (EHRs) genetic data from Vanderbilt University Medical Center modify most recent version better phenotypes....
Statins reduce low-density lipoprotein cholesterol (LDL-C) and are efficacious in the prevention of atherosclerotic cardiovascular disease (ASCVD). Dose-response to statins varies among patients can be modeled using three distinct pharmacological properties: (1) E
Abstract Drug repurposing represents an attractive alternative to the costly and time-consuming process of new drug development, particularly for serious, widespread conditions with limited effective treatments, such as Alzheimer’s disease (AD). Emerging generative artificial intelligence (GAI) technologies like ChatGPT offer promise expediting review summary scientific knowledge. To examine feasibility using GAI identifying candidates, we iteratively tasked proposing twenty most promising...
Background:Avascular necrosis of the lunate bone (Kienböck's disease), is a condition in which bone, loses its blood supply, leading to bone.There probably no single cause Kienbock's disease.Its origin may involve multiple factors, such as supply (arteries), drainage (veins), and skeletal variations.Trauma, either isolated or repeated, possibly be factor some cases.This case presented with multifactorial etiology. Case Report:In case, patient negative ulnar variant had injured her right...
ABSTRACT Objectives Phenotyping is a core task in observational health research utilizing electronic records (EHRs). Developing an accurate algorithm demands substantial input from domain experts, involving extensive literature review and evidence synthesis. This burdensome process limits scalability delays knowledge discovery. We investigate the potential for leveraging large language models (LLMs) to enhance efficiency of EHR phenotyping by generating high-quality drafts. Materials Methods...
<title>Abstract</title> Current studies regarding the secondary use of electronic health records (EHR) predominantly rely on domain expertise and existing medical knowledge. Though significant efforts have been devoted to investigating application machine learning algorithms in EHR, efficient powerful representation patients is needed unleash potential discovering new patterns underlying EHR. Here, we present an unsupervised method for embedding high-dimensional EHR data at patient level,...
Identifying symptoms highly specific to COVID-19 would improve the clinical and public health response infectious outbreaks. Here, we describe a high-throughput approach - Concept-Wide Association Study (ConceptWAS) that systematically scans disease's manifestations from notes. We used this method identify early in course of pandemic. Using Vanderbilt University Medical Center (VUMC) EHR, parsed notes through natural language processing pipeline extract concepts. examined difference concepts...
Abstract Drug repurposing represents an attractive alternative to the costly and time-consuming process of new drug development, particularly for serious, widespread conditions with limited effective treatments, such as Alzheimer’s disease (AD). Emerging generative artificial intelligence (GAI) technologies like ChatGPT offer promise expediting review summary scientific knowledge. To examine feasibility using GAI identifying candidates, we iteratively tasked proposing twenty most promising...
Pediatric patients have different diseases and outcomes than adults; however, existing phecodes do not capture the distinctive pediatric spectrum of disease. We aim to develop specialized (Peds-Phecodes) enable efficient, large-scale phenotypic analyses patients.