A5031304391- Diabetes Management and Education
- Health Systems, Economic Evaluations, Quality of Life
- Medication Adherence and Compliance
- Electronic Health Records Systems
- Biomedical Text Mining and Ontologies
- Semantic Web and Ontologies
- Machine Learning in Healthcare
- Data Quality and Management
- Chronic Disease Management Strategies
- Artificial Intelligence in Healthcare
- Scientific Computing and Data Management
- Pharmaceutical Practices and Patient Outcomes
- Diabetes Treatment and Management
- Statistical Methods in Clinical Trials
- Attention Deficit Hyperactivity Disorder
- Healthcare Policy and Management
- Schizophrenia research and treatment
- Cerebrovascular and Carotid Artery Diseases
- Biomedical and Engineering Education
- Blood Pressure and Hypertension Studies
- Topic Modeling
- Cardiovascular Health and Risk Factors
- Distributed and Parallel Computing Systems
- Adolescent and Pediatric Healthcare
- Neural Networks and Applications
Duke University
2013-2020
Duke University Hospital
2015
Duke Medical Center
2015
Duke University Health System
2013
Widespread sharing of data from electronic health records and patient-reported outcomes can strengthen the national capacity for conducting cost-effective clinical trials allow research to be embedded within routine care delivery. While pragmatic (PCTs) have been performed decades, they now draw on rich sources operational that are continuously fed back inform practice. The Health Care Systems Collaboratory program, initiated by NIH Common Fund in 2012, engages healthcare systems as partners...
This study compares the yield and characteristics of diabetes cohorts identified using heterogeneous phenotype definitions.Inclusion criteria from seven definitions were translated into query algorithms applied to a population (n=173 503) adult patients Duke University Health System. The numbers meeting for each definition component (diagnosis, diabetes-associated medications, laboratory results) compared.Three based heavily on ICD-9-CM codes 9-11% patient population. A broad Durham Diabetes...
Objective: We assessed the sensitivity and specificity of 8 electronic health record (EHR)-based phenotypes for diabetes mellitus against gold-standard American Diabetes Association (ADA) diagnostic criteria via chart review by clinical experts. Materials Methods: identified EHR-based phenotype definitions that were developed various purposes a variety users, including academic medical centers, Medicare, New York City Health Department, pharmacy benefit managers. applied these to sample 173...
The goal of this survey is to discuss the impact growing availability electronic health record (EHR) data on evolving field Clinical Research Informatics (CRI), which union biomedical research and informatics.Major challenges for use EHR-derived include lack standard methods ensuring that quality, completeness, provenance are sufficient assess appropriateness its research. Areas need continued emphasis integrating from heterogeneous sources, guidelines (including explicit phenotype...
Comorbid diabetes and substance use diagnoses (SUD) represent a hazardous combination, both in terms of healthcare cost morbidity. To date, there is limited information about the association SUD related mental disorders with type 2 mellitus (T2DM).We examined associations between T2DM multiple psychiatric diagnosis categories, focus on comorbidities among adults T2DM. We analyzed electronic health record (EHR) data 170,853 unique aged ≥18 years from EHR warehouse large academic system....
Peripheral artery disease (PAD) is underrecognized, undertreated, and understudied: each of these endeavors requires efficient accurate identification patients with PAD. Currently, PAD patient relies on diagnosis/procedure codes or lists diagnosed treated by specific providers in locations ways. The goal this research was to leverage natural language processing more accurately identify an electronic health record system compared a structured data-based approach.The clinical notes from cohort...
The Affordable Care Act encourages healthcare systems to integrate behavioral and medical healthcare, as well employ electronic health records (EHRs) for information exchange quality improvement. Pragmatic research paradigms that EHRs in are needed produce clinical evidence real-world settings informing learning systems. Adults with comorbid diabetes substance use disorders (SUDs) tend costly inpatient treatments; however, there is a lack of empirical data on implementing reduce risk adults...
Abstract Children with autism spectrum disorder (ASD) or attention deficit hyperactivity (ADHD) have 2–3 times increased healthcare utilization and annual costs once diagnosed, but little is known about their patterns early in life. Quantifying health system could uncover condition-specific trajectories to facilitate earlier detection intervention. Patients born 10/1/2006–10/1/2016 ≥ 2 well-child visits within the Duke University Health System before age 1 were grouped as ASD, ADHD, ASD + No...
Purpose: Poor adherence to prescribed medicines is associated with increased rates of poor outcomes, including hospitalization, serious adverse events, and death, also healthcare costs. However, current approaches evaluation medication using real-world electronic health records (EHRs) or claims data may miss critical opportunities for capture fall short in modeling representing the full complexity environment. We sought explore a framework understanding improving population-based...
Background: Children with ADHD have 2 to 3 times increased health care utilization and annual costs once diagnosed, but little is known about patterns early in life, prior diagnosis. Quantifying services use among children later diagnosed could help us understand the life impact of disorder uncover associated higher risk. Methods: Electronic record (EHR) data from Duke University Health System (DUHS) was analyzed for patients born October 1, 2006–October 2016. Those at least two well-child...