A5086956951- Artificial Intelligence in Healthcare and Education
- RNA modifications and cancer
- Healthcare Technology and Patient Monitoring
- Cancer Genomics and Diagnostics
- COVID-19 diagnosis using AI
- Lung Cancer Treatments and Mutations
- Lymphatic System and Diseases
- Emergency and Acute Care Studies
- Blood Pressure and Hypertension Studies
- Hematopoietic Stem Cell Transplantation
- Trauma and Emergency Care Studies
- Cardiac, Anesthesia and Surgical Outcomes
- Genomics and Phylogenetic Studies
- Ethics in Clinical Research
- Hospital Admissions and Outcomes
- Meta-analysis and systematic reviews
- Viral-associated cancers and disorders
- Cutaneous Melanoma Detection and Management
- Colorectal Cancer Treatments and Studies
- Patient Safety and Medication Errors
- Military and Defense Studies
- Sepsis Diagnosis and Treatment
- Medication Adherence and Compliance
- Mobile Health and mHealth Applications
- Dental Research and COVID-19
Vanderbilt University Medical Center
2019-2024
Vanderbilt University
2018-2023
Vanderbilt-Ingram Cancer Center
2022
American Association For Cancer Research
2021
University of New Orleans
2012-2013
Epstein-Barr virus (EBV) is associated with roughly 10% of gastric carcinomas worldwide (EBVaGC). Although previous investigations provide a strong link between EBV and carcinomas, these studies were performed using selected gene probes. Using cohort carcinoma RNA-seq data sets from The Cancer Genome Atlas (TCGA), we quantitative global assessment expression in assessed cellular pathway alterations. transcripts detected 17% samples but varied significantly coverage depth. In four the highest...
Artificial intelligence (AI) and machine learning (ML) technology design development continues to be rapid, despite major limitations in its current form as a practice discipline address all sociohumanitarian issues complexities. From these emerges an imperative strengthen AI ML literacy underserved communities build more diverse workforce engaged health research. has the potential account for assess variety of factors that contribute disease improve prevention, diagnosis, therapy. Here, we...
<sec> <title>UNSTRUCTURED</title> The role and use of race within health-related artificial intelligence machine learning (AI/ML) models has sparked increasing attention controversy. Despite the complexity breadth related issues, a robust holistic framework to guide stakeholders in their examination resolution remains lacking. This perspective provides broad-based, systematic, cross-cutting landscape analysis race-related challenges, structured around AI/ML lifecycle framed through “points...
Proton pump inhibitors (PPIs) are often used in pediatrics to treat common gastrointestinal disorders, and there growing concerns for infectious adverse events. Because CYP2C19 inactivates PPIs, genetic variants that increase function may decrease PPI exposure infections. We tested the hypothesis metabolizer phenotypes associated with infection event rates children exposed PPIs.
Abstract Objectives Artificial intelligence (AI) proceeds through an iterative and evaluative process of development, use, refinement which may be characterized as a lifecycle. Within this context, stakeholders can vary in their interests perceptions the ethical issues associated with rapidly evolving technology ways that fail to identify avert adverse outcomes. Identifying throughout AI lifecycle systematic manner facilitate better-informed deliberation. Materials Methods We analyzed...
ABSTRACT Many cell lines commonly used for biological studies have been found to harbor exogenous agents such as the human tumor viruses Epstein-Barr virus (EBV) and papillomavirus. Nevertheless, broad-based, unbiased approaches globally assess presence of ectopic organisms within model systems not previously available. We reasoned that high-throughput sequencing should provide unparalleled insights into microbiomes tissue culture systems. Here we our RNA-seq analysis pipeline, PARSES...
Early warning systems lack robust evidence that they improve patients' outcomes, possibly because of their limitation predicting binary rather than time-to-event outcomes.To compare the prediction accuracy 2 statistical modeling strategies (logistic regression and Cox proportional hazards regression) machine learning (random forest random survival forest) for in-hospital cardiopulmonary arrest.Retrospective cohort study with model development from deidentified electronic health records at an...
Background Emergency department (ED) visits for hypertension are rising, but the importance of elevated blood pressure (BP) measured during ED visit is controversial. We evaluated relationship between BP and mean over subsequent year. Methods Results performed a retrospective cohort study from January 1, 2010 to December 31, 2013 8105 adult patients who made 1 an academic medical center with ≥2 BPs in The primary exposure was lowest systolic BP. outcome ≥140 mm Hg year following index visit....
Medical students may observe and subsequently perpetuate redundancy in clinical documentation, but the degree of student notes whether there is an association with scholastic performance are unknown.This study sought to quantify redundancy, defined generally as proportion similar text between two strings, medical evaluate relationship note objective indicators performance.Notes generated by rotating through their medicine clerkship during a single academic year at our institution were...
Background Emergency department (ED) visits can be opportunities to address uncontrolled hypertension. We sought compare short-term blood pressure measures between the Vanderbilt Room Bundle (VERB) intervention and usual care plus education. Methods Results conducted a randomized trial of 206 adult patients with hypertension elevated systolic (SBP) presenting 2 urban emergency departments in Tennessee, USA. The VERB included educational materials, brief motivational interview, pillbox,...
Current methods of communication between the point injury and receiving medical facilities rely on verbal communication, supported by brief notes memory field medic. This can be made more complete reliable with technologies that automatically document actions medics. However, designing state-of-the-art technology for military personnel civilian first responders is challenging due to barriers researchers face in accessing environment understanding situated cognitive models employed field.To...
Understanding a patient's state is critical to providing optimal care. However, information loss occurs during patient hand-offs (e.g., emergency services (EMS) transferring care receiving hospital), which hinders quality. Augmenting the flow from an EMS vehicle hospital may reduce and improve outcomes. Such augmentation requires noninvasive system that can automatically recognize clinical procedures being performed send near real-time hospital. An automatic procedure detection uses wearable...
Abstract Background Estimating the extent of affected skin is an important unmet clinical need both for research and practical management in many diseases. In particular, cutaneous burden chronic graft‐vs‐host disease ( cGVHD ) a primary outcome trials. Despite advances artificial intelligence 3D photography, progress toward reliable automated techniques hindered by limited expert time to delineate patient images. Crowdsourcing may have potential provide requisite expert‐level data....
Abstract Objective This study examines the validity of optical mark recognition, a novel user interface, and crowdsourced data validation to rapidly digitize extract from paper COVID-19 assessment forms at large medical center. Methods An recognition/optical character recognition (OMR/OCR) system was developed identify fields that were selected on 2,814 forms, each with 141 which used assess potential infections. A interface (UI) displayed mirrored showing scanned OMR results superimposed...
Ideal treatment of trauma, especially that which is sustained during military combat, requires rapid management to optimize patient outcomes. Medical transport teams `scoop-and-run' trauma centers deliver the within `golden hour', has been shown reduce likelihood death. During transport, emergency medical technicians (EMTs) perform numerous procedures from tracheal intubation CPR, sometimes documenting procedure on a piece tape their leg, or not at all. Understandably, EMT's focus precludes...
Information about a patient's state is critical for hospitals to provide timely care and treatment. Prior work on improving the information flow from emergency medical services (EMS) demonstrated potential of using automated algorithms detect clinical procedures. However, prior has not made effective use video sources that might be available during patient care. In this paper we explore convolutional neural networks (CNNs) raw data determine how well alone can automatically identify We apply...
<sec> <title>BACKGROUND</title> Artificial intelligence (AI) and machine learning (ML) technology design development continues to be rapid, despite major limitations in its current form as a practice discipline address all sociohumanitarian issues complexities. From these emerges an imperative strengthen AI ML literacy underserved communities build more diverse workforce engaged health research. </sec> <title>OBJECTIVE</title> has the potential account for assess variety of factors that...
Background Chronic graft-versus-host disease (cGVHD) is a significant cause of long-term morbidity and mortality in patients after allogeneic hematopoietic cell transplantation. Skin the most commonly affected organ, visual assessment cGVHD can have low reliability. Crowdsourcing data from nonexpert participants has been used for numerous medical applications, including image labeling segmentation tasks. Objective This study aimed to assess ability crowds raters—individuals without any prior...
<sec> <title>BACKGROUND</title> Chronic graft-versus-host disease (cGVHD) is a significant cause of long-term morbidity and mortality in patients after allogeneic hematopoietic cell transplantation. Skin the most commonly affected organ, visual assessment cGVHD can have low reliability. Crowdsourcing data from nonexpert participants has been used for numerous medical applications, including image labeling segmentation tasks. </sec> <title>OBJECTIVE</title> This study aimed to assess ability...