A5062759042- Sepsis Diagnosis and Treatment
- Emergency and Acute Care Studies
- Respiratory Support and Mechanisms
- Elder Abuse and Neglect
- Occupational Health and Safety Research
- Intimate Partner and Family Violence
- Patient Safety and Medication Errors
- Nosocomial Infections in ICU
- Sexual Assault and Victimization Studies
- Intensive Care Unit Cognitive Disorders
- Medical Malpractice and Liability Issues
- Artificial Intelligence in Healthcare
- Quality and Safety in Healthcare
- Machine Learning in Healthcare
- COVID-19 diagnosis using AI
- Data Quality and Management
- Pharmacovigilance and Adverse Drug Reactions
- Intracerebral and Subarachnoid Hemorrhage Research
- Hemodynamic Monitoring and Therapy
- Maternal and fetal healthcare
- Traumatic Brain Injury and Neurovascular Disturbances
- Health Systems, Economic Evaluations, Quality of Life
- Vascular anomalies and interventions
- Neonatal and Maternal Infections
- Reproductive Health and Contraception
MedStar Health
2022-2025
Georgetown University
2024
Emory University
2018-2022
<h3>Importance</h3> Discrepancies in oxygen saturation measured by pulse oximetry (Spo<sub>2</sub>), when compared with arterial (Sao<sub>2</sub>) blood gas (ABG), may differentially affect patients according to race and ethnicity. However, the association of these disparities health outcomes is unknown. <h3>Objective</h3> To examine racial ethnic discrepancies between Sao<sub>2</sub>and Spo<sub>2</sub>measures their associations clinical outcomes. <h3>Design, Setting, Participants</h3> This...
We present an interpretable machine learning algorithm called ‘eARDS’ for predicting ARDS in ICU population comprising COVID-19 patients, up to 12-hours before satisfying the Berlin clinical criteria. The analysis was conducted on data collected from Intensive care units (ICU) at Emory Healthcare, Atlanta, GA and University of Tennessee Health Science Center, Memphis, TN Cerner ® Facts Deidentified Database, a multi-site EMR database. participants consisted adults over 18 years age. Clinical...
Introduction Emergency department (ED) encounters offer strategic opportunities for sexually transmitted infection (STI) screening, prevention, and treatment adolescents at risk STIs who may not otherwise have access to routine screening. This study determined optimal ED implementation of the Teen Health Screen (THS), a validated, tablet-based, patient-reported, sexual assessment, evaluated its feasibility under variable workflows high-stress tasks. Methods Workflow analysis included...
Objectives The objective of this study was to explore the use natural language processing (NLP) algorithm categorise contributing factors from patient safety event (PSE). Contributing are elements in healthcare process (eg, communication failures) that instigate an or allow occur. can be used further investigate why events occurred. Methods We 10 years self-reported PSE reports a multihospital system USA. Reports were first selected by date. calculated χ 2 values for each ngram bag-of-words...
Introduction: Intimate partner violence (IPV) is defined as sexual, physical, psychological, or economic that occurs between current former intimate partners. Victims of IPV may seek care for violence-related injuries in healthcare settings, which makes recognition and intervention these facilities critical. In this study our goal was to develop an algorithm using natural language processing (NLP) identify cases within emergency department (ED) settings. Methods: observational cohort study,...
Background Diagnostic errors are an underappreciated cause of preventable mortality in hospitals and pose a risk for severe patient harm increase hospital length stay. Objective This study aims to explore the potential machine learning natural language processing techniques improving diagnostic safety surveillance. We conducted rigorous evaluation feasibility use electronic health records clinical notes existing case review data. Methods Safety Learning System data from 1 large system...
Predict the onset of presumed serious infection, defined as a positive blood culture drawn and new antibiotic course at least 4 days (PSI
Risks of intimate partner violence (IPV) escalated during the COVID-19 pandemic given mitigation measures, socioeconomic hardships, and isolation concerns. The objective this study was to explore impact on incidence IPV. We conducted an interrupted time series analysis for IPV at a single level 1 trauma center located in United States. cases were identified by triangulation institutional data sources. There 4,624 traumatic injuries which 292 (6.3%) due IPV-related injury admissions increased...
Acute respiratory failure occurs frequently in hospitalized patients and often begins outside the ICU, associated with increased length of stay, cost, mortality. Delays decompensation recognition are worse outcomes.The objective this study is to predict acute requiring any advanced support (including noninvasive ventilation). With advent coronavirus disease pandemic, concern regarding has increased.All admission encounters from January 2014 June 2017 three hospitals Emory Healthcare network...
Cluster analysis provides a data-driven multidimensional approach for identifying distinct subgroups of patients in cohort. Each the clusters represents particular health condition with specific clinical trajectory and medical needs. Patients visiting emergency rooms do not share same condition, therefore discriminating between groups may have implications diagnostic testing resource utilization. We carried out this retrospective cohort study on 13825 who visited three Emory hospitals...
Between 30 and 68% of patients prematurely discontinue their antidepressant treatment, posing significant risks to patient safety healthcare outcomes. Online forums have the potential offer a rich unique source data, revealing dimensions discontinuation that may not be captured by conventional data sources.We analyzed 891 narratives from online forum, "askapatient.com," utilizing content analysis create PsyRisk-a corpus highlighting risk factors associated with discontinuation. Leveraging...
The impact of COVID-19 on intimate partner violence (IPV) in the United States is still relatively unknown, although some early data demonstrate that cases IPV increased during COVID-19. objective this study was to measure prevalence before and pandemic a southeastern urban hospital. We performed retrospective analysis encounters at single high-volume Level I trauma were identified through novel natural language processing algorithm using IPV-related words phrases within unstructured...
Patient safety event reporting systems (PSRS) aim to identify hazards by encouraging hospital staff report adverse events, errors, and potential errors in the healthcare system. PSRS collect different information regarding a such as contributing factors general types. Users select types of incident from predefined lists; therefore, most frequent are commonly recorded together. Contributing often related leading cause an unsafe condition; identifying can help with detecting mitigating issues....
<sec> <title>BACKGROUND</title> Maternal harm is a major crisis that disproportionately affects Black women. Unstructured clinical notes from electronic health records (EHR) data may contain insights for unsafe maternal care delivery. Studies have analyzed unstructured in the EHR using natural language processing tone and sentiment discovered contributes to preventable patient safety events. </sec> <title>OBJECTIVE</title> We potentially negative keywords recorded women who experienced...
<sec> <title>BACKGROUND</title> Diagnostic errors are an underappreciated cause of preventable mortality in hospitals and pose a risk for severe patient harm increase hospital length stay. </sec> <title>OBJECTIVE</title> This study aims to explore the potential machine learning natural language processing techniques improving diagnostic safety surveillance. We conducted rigorous evaluation feasibility use electronic health records clinical notes existing case review data....
Hospital readmission after third-stage palliation for single ventricle physiology (Fontan cavopulmonary anastomosis) approaches 25%. The cause readmissions is varied, and there no clear way to predict those at risk readmission. If an effective predictive model can be used, physicians preempt in either the inpatient or outpatient setting. In this study, we incorporated electronic health records (EHRs), such as vital signs, administered medications, laboratory results, demographic information,...