Ashley Batugo
A5043154290- COVID-19 Clinical Research Studies
- Mechanical Circulatory Support Devices
- Biomedical Text Mining and Ontologies
- Semantic Web and Ontologies
- Kawasaki Disease and Coronary Complications
- Thermal Regulation in Medicine
- Cardiovascular Health and Risk Factors
- Acute Kidney Injury Research
- Misinformation and Its Impacts
- Long-Term Effects of COVID-19
- Cardiac Arrest and Resuscitation
- Acute Lymphoblastic Leukemia research
- Health Literacy and Information Accessibility
- Intensive Care Unit Cognitive Disorders
- Genomics and Rare Diseases
University of Pennsylvania
2022-2024
While acute kidney injury (AKI) is a common complication in COVID-19, data on post-AKI function recovery and the clinical factors associated with poor lacking.
Multisystem inflammatory syndrome in children (MIS-C) is a severe complication of SARS-CoV-2 infection. It remains unclear how MIS-C phenotypes vary across variants. We aimed to investigate clinical characteristics and outcomes eras.
Few studies examining the patient outcomes of concurrent neurological manifestations during acute COVID-19 leveraged multinational cohorts adults and children or distinguished between central peripheral nervous system (CNS vs. PNS) involvement. Using a federated network in which local clinicians informatics experts curated electronic health records data, we evaluated risk prolonged hospitalization mortality hospitalized patients from 21 healthcare systems across 7 countries. For adults, used...
Abstract Objective Integrating electronic health record (EHR) data with other resources is essential in rare disease research due to low prevalence. Such integration dependent on the alignment of ontologies used for annotation. The international classification diseases (ICD) annotate clinical diagnoses, while human phenotype ontology (HPO) phenotypes. Although these overlap biomedical entities they describe, extent which are interoperable unknown. We investigate how well aligned and whether...
Patient-generated free-text messages are a well-recognized source of clinical burden and burnout for clinicians. Machine learning approaches such as Large Language Models (LLMs) may be applied to alleviate this by automatically triaging classifying messages, but their performance in domain has not been fully characterized. In study, we analyzed the effectiveness GPT4 patient provider hypertension management through prompt engineering, comparing its an alternative unsupervised generative...
Introduction: In-hospital cardiac arrest (IHCA) is experienced by approximately 200,000 patients annually in the US. While individual care teams can readily identify IHCA at bedside, subsequent event identification for research or quality improvement (QI) purposes challenging and often relies on use of administrative billing codes. Prior has shown that codes from International Classification Diseases-9 (ICD-9) was both insensitive nonspecific events. However, performance this approach using...
Final project for INST490: Integrative Capstone (Fall 2019). University of Maryland, College Park.