A5057944407- Biomedical Text Mining and Ontologies
- Machine Learning in Healthcare
- Topic Modeling
- Electronic Health Records Systems
- Heart Failure Treatment and Management
- Neurotransmitter Receptor Influence on Behavior
- Natural Language Processing Techniques
- Insect and Pesticide Research
- Suicide and Self-Harm Studies
- Mental Health via Writing
- Artificial Intelligence in Healthcare
- Sepsis Diagnosis and Treatment
- Chronic Disease Management Strategies
- Explainable Artificial Intelligence (XAI)
- Nursing Diagnosis and Documentation
- Mental Health Treatment and Access
- Nursing Education, Practice, and Leadership
- Advanced X-ray and CT Imaging
- Semantic Web and Ontologies
- Plant and fungal interactions
- Radiology practices and education
- Parkinson's Disease Mechanisms and Treatments
- Healthcare Technology and Patient Monitoring
- Delphi Technique in Research
- Psychosomatic Disorders and Their Treatments
Vanderbilt University Medical Center
2012-2025
VA Tennessee Valley Healthcare System
2012-2025
United States Department of Veterans Affairs
2013-2024
Health Services Research & Development
2012-2022
Vanderbilt University
2013-2020
Takeda (United States)
2019
Geriatric Research Education and Clinical Center
2012-2018
University of Colorado Hospital
2018
University of Colorado Denver
2018
VA Eastern Colorado Health Care System
2018
Background: The aim of this study was to build electronic algorithms using a combination structured data and natural language processing (NLP) text notes for potential safety surveillance 9 postoperative complications. Methods: Postoperative complications from 6 medical centers in the Southeastern United States were obtained Veterans Affairs Surgical Quality Improvement Program (VASQIP) registry. Development test datasets constructed stratification by facility date procedure patients with...
ABSTRACT Background Literature on how to translate information extracted from clinical progress notes into numeric scores for 3‐step theory of suicide (3ST) factors is nonexistent. We determined which scoring option would best discriminate between patients who will attempt or die by and with neither suicidal ideation nor attempts, we tested hypotheses related the 3ST. Methods used terminology‐driven natural language processing (NLP) extract Veterans Health Administration (VHA) notes. Counts...
Objective To evaluate the validity of death ascertainment from publicly available internet media sources by benchmarking against state and Federal vital statics data for patients in two large healthcare systems US. Methods We extracted names dates birth including obituaries memorial websites using previously developed natural language processing models. These were probabilistically matched to electronic health records (EHRs) Mass General Brigham (MGB) Vanderbilt University Medical Center...
To determine whether assisted annotation using interactive training can reduce the time required to annotate a clinical document corpus without introducing bias.A tool, RapTAT, was designed assist by iteratively pre-annotating probable phrases of interest within document, presenting annotations reviewer for correction, and then corrected further machine learning-based before subsequent documents. Annotators reviewed 404 notes either manually or RapTAT assistance concepts related quality care...
We developed an accurate, stakeholder-informed, automated, natural language processing (NLP) system to measure the quality of heart failure (HF) inpatient care, and explored potential for adoption this within integrated health care system.To accurately automate a United States Department Veterans Affairs (VA) inpatients with HF.We automated HF Congestive Heart Failure Inpatient Measure 19 (CHI19) that identifies whether given patient has left ventricular ejection fraction (LVEF) <40%, if so,...
Abstract Large observational data networks that leverage routine clinical practice in electronic health records (EHRs) are critical resources for research on coronavirus disease 2019 (COVID-19). Data normalization is a key challenge the secondary use of EHRs COVID-19 across institutions. In this study, we addressed automating diagnostic tests, which elements, but controlled terminology terms were published after implementation. We developed simple effective rule-based tool called TestNorm to...
Background Social risk factors influence rehospitalization rates yet are challenging to incorporate into prediction models. Integration of social using natural language processing (NLP) and machine learning could improve 30-day readmission following an acute myocardial infarction. Methods Results Patients were enrolled derivation validation cohorts. The cohort included inpatient discharges from Vanderbilt University Medical Center between January 1, 2007, December 31, 2016, with a primary...
The state-of-the-art 3-step Theory of Suicide (3ST) describes why people consider suicide and who will act on their suicidal thoughts attempt suicide. central concepts 3ST-psychological pain, hopelessness, connectedness, capacity for suicide-are among the most important drivers behaviour but they are missing from clinical risk prediction models in use at US Veterans Health Administration (VHA). These four not systematically recorded structured fields VHA's electronic healthcare records....
To make recommendations for management of potentially fatal failure the Accufix series atrial J‐wire permanent pacemaker leads, we closely monitored number injuries and fatalities resulting either from spontaneous fracture or attempts to extract lead. In a population 30,357 patients, 2,298 patients are enrolled in prospective follow‐up Multicenter Study, remainder with known clinical status voluntary reporting, 2,992 died following implant. remaining 27,365 6 deaths have been attributed...
This research describes the prevalence and covariates associated with opioid-induced constipation (OIC) in an observational cohort study utilizing a national veteran integrated data from Center for Medicare Medicaid Services (CMS).A of 152,904 veterans encounters between 1 January 2008 30 November 2010, exposure to opioids days or more, no prior year was developed establish existing conditions medications at start opioid determining outcomes through end exposure. OIC identified...
Triadimefon (TDF) is a triazole fungicide that blocks the reuptake of dopamine (DA) and leads to increased locomotor activity levels in mice rats, effects similar those indirect DA agonists such as cocaine. We recently found intermittent TDF administration led robust sensitization, phenomenon reflecting neuronal plasticity, following challenge with same dose after 2-week withdrawal period. The current study sought determine whether antagonists D1-like receptors (SCH 23390; SCH), D2-like...
Assigning outcome labels to large observational data sets in a timely and accurate manner, particularly when outcomes are rare or not directly ascertainable, remains significant challenge within biomedical informatics. We examined whether noisy generated from subject matter experts' heuristics using heterogenous types programming paradigm could provide large, set. chose the clinical condition of opioid-induced respiratory depression for our use case because it is rare, has no administrative...
Assigning outcome labels to large observational data sets in a timely and accurate manner, particularly when outcomes are rare or not directly ascertainable, remains significant challenge within biomedical informatics. We examined whether noisy generated from subject matter experts' heuristics using heterogenous types programming paradigm could provide large, set. chose the clinical condition of opioid-induced respiratory depression for our use case because it is rare, has no administrative...