A5026367973- Ethics in Clinical Research
- Biomedical Text Mining and Ontologies
- Electronic Health Records Systems
- Machine Learning in Healthcare
- Artificial Intelligence in Healthcare
- Scientific Computing and Data Management
- Sexual Differentiation and Disorders
- Patient-Provider Communication in Healthcare
- Long-Term Effects of COVID-19
- Research Data Management Practices
- Artificial Intelligence in Healthcare and Education
- Genetic and Clinical Aspects of Sex Determination and Chromosomal Abnormalities
- COVID-19 Clinical Research Studies
- Biomedical and Engineering Education
- Hormonal and reproductive studies
- COVID-19 diagnosis using AI
- Opioid Use Disorder Treatment
- Social Media in Health Education
- Emergency and Acute Care Studies
- Cloud Data Security Solutions
- Semantic Web and Ontologies
- Mental Health via Writing
- Clinical practice guidelines implementation
- Telemedicine and Telehealth Implementation
- Biomedical Ethics and Regulation
Medical University of South Carolina
2016-2025
MUSC Hollings Cancer Center
2024
Instituto Federal Farroupilha
2021
Collaborative Research Group
2021
Cohort (United Kingdom)
2021
University of South Carolina
2020
College Station Medical Center
2019
Coloplast (United States)
2019
Seattle Children's Hospital
2018
Institute of Behavioral Sciences
2014
The National COVID Cohort Collaborative (N3C) is a centralized, harmonized, high-granularity electronic health record repository that the largest, most representative COVID-19 cohort to date. This multicenter data set can support robust evidence-based development of predictive and diagnostic tools inform clinical care policy.
We leveraged the largely untapped resource of electronic health record data to address critical clinical and epidemiological questions about Coronavirus Disease 2019 (COVID-19). To do this, we formed an international consortium (4CE) 96 hospitals across five countries (www.covidclinical.net). Contributors utilized Informatics for Integrating Biology Bedside (i2b2) or Observational Medical Outcomes Partnership (OMOP) platforms map a common model. The group focused on temporal changes in key...
Congenital adrenal hyperplasia (CAH) refers to a family of monogenic inherited disorders steroidogenesis most often caused by enzyme 21-hydroxylase deficiency (21-OHD). In the classic forms CAH (simple virilizing and salt wasting), androgen excess causes external genital ambiguity in newborn females progressive postnatal virilization males females. Prenatal treatment with dexamethasone has been successfully used for over decade. This article serves as an update on 532 pregnancies prenatally...
Lack of recruitment qualified research participants continues to be a significant bottleneck in clinical trials, often resulting costly time extensions, underpowered results, and some cases early termination. Some the reasons for suboptimal include laborious consent processes access at remote locations. While new electronic consents technologies (eConsent) help overcome challenges related readability management, they do not adequately address access. To this, we have developed an innovative...
This project assessed performance of natural language processing (NLP) and machine learning (ML) algorithms for classification brain MRI radiology reports into acute ischemic stroke (AIS) non-AIS phenotypes.All from a single academic institution over two year period were randomly divided 2 groups ML: training (70%) testing (30%). Using "quanteda" NLP package, all text data parsed tokens to create the frequency matrix. Ten-fold cross-validation was applied bias correction set. Labeling AIS...
Abstract Objectives We describe our approach in using health information technology to provide a continuum of services during the coronavirus disease 2019 (COVID-19) pandemic. COVID-19 challenges and needs required systems rapidly redesign delivery care. Materials Methods Our system deployed 4 telehealth programs biomedical informatics innovations screen care for patients. Using programmatic electronic record data, we implementation initial utilization. Results Through collaboration across...
Building well-performing machine learning (ML) models in health care has always been exigent because of the data-sharing concerns, yet ML approaches often require larger training samples than is afforded by one institution. This paper explores several federated implementations applying them both a simulated environment and an actual implementation using electronic record data from two academic medical centers on Microsoft Azure Cloud Databricks platform.Using separate cloud tenants, were...
Elevated lipoprotein(a) [Lp(a)] is associated with atherosclerotic cardiovascular disease, yet little known about Lp(a) testing patterns in real-world practice. The objective of this analysis was to determine how used clinical practice comparison low density lipoprotein cholesterol (LDL-C) alone, and whether elevated level subsequent initiation lipid-lowering therapy (LLT) incident (CV) events.This an observational cohort study, based on lab tests administered between Jan 1, 2015 Dec 31,...
Identifying patients with certain clinical criteria based on manual chart review of doctors' notes is a daunting task given the massive amounts text in electronic health records (EHR). This can be automated using classifiers Natural Language Processing (NLP) techniques along pattern recognition machine learning (ML) algorithms. The aim this research to evaluate performance traditional for identifying Systemic Lupus Erythematosus (SLE) comparison newer Bayesian word vector method. We obtained...
Abstract Objective In an effort to improve the efficiency of computer algorithms applied screening for coronavirus disease 2019 (COVID-19) testing, we used natural language processing and artificial intelligence–based methods with unstructured patient data collected through telehealth visits. Materials Methods After segmenting parsing documents, conducted analysis overrepresented words in symptoms. We then developed a word embedding–based convolutional neural network predicting COVID-19 test...
Obtaining informed consent (IC) is vital for ethically and effectively recruiting participants in research projects. However, traditional in-person IC approaches encounter notable obstacles, such as geographic barriers, transportation expenses, literacy challenges, which can lead to delays enrollment increased costs. Telehealth, especially teleconsent, offers a potential way overcome these obstacles by facilitating the process digital setting. Nonetheless, there are concerns about whether...
Tyr-179 and Lys-183 are likely to be functionally important residues in 11 beta-hydroxysteroid dehydrogenase, as these amino acids absolutely conserved all members of the "short chain dehydrogenase" family. We modified by site-directed mutagenesis rat cDNA transfected constructs into CHO cells. A highly but not residue, Asp-110, was also studied. Mutation Phe or Ser completely abolished enzymatic activity (interconversion corticosterone 11-dehydrocorticosterone), did Lys-183-->Arg....
Electronic health records (EHRs) provide great promise for identifying cohorts and enhancing research recruitment. Such approaches are sorely needed, but there few descriptions in the literature of prevailing practices to guide their use. A multidisciplinary workgroup was formed examine current use EHRs recruitment propose future directions. The group surveyed consortium members regarding practices. Over 98% Clinical Translational Science Award Consortium responded survey. Brokered...
Social isolation is an important social determinant that impacts health outcomes and mortality among patients. The National Academy of Medicine recently recommended be documented in electronic records (EHR). However, usually not recorded or obtained as coded data but rather collected from patient self-report clinical narratives. This study explores the feasibility effectiveness natural language processing (NLP) strategy for identifying patients who are socially isolated We used Medical...
Increase in early onset colorectal cancer makes adherence to screening a significant public health concern, with various social determinants playing crucial role its incidence, diagnosis, treatment, and outcomes. Stressful life events, such as divorce, marriage, or sudden loss of job, have unique position among the health. We applied large language model (LLM) history sections clinical notes records database Medical University South Carolina extract recent stressful events assess their...
Fervent attention was paid to what is coined dual-use research (DUR), or that can both benefit and harm humanity, of concern (DURC), a particular subset DUR reasonably anticipated be safety security if misapplied. The aim this paper not reiterate the challenges DURC governance but look at new turn in DURC, namely posed by use artificial intelligence (AI) pharmaceutical development. This important, as AI increasingly being used for development industry. There growing recognition there dearth...