A5082929960- Biomedical Text Mining and Ontologies
- Electronic Health Records Systems
- Data Visualization and Analytics
- Usability and User Interface Design
- COVID-19 epidemiological studies
- Topic Modeling
- Bioinformatics and Genomic Networks
- Genomics and Rare Diseases
- Digital Accessibility for Disabilities
- Time Series Analysis and Forecasting
- Data Management and Algorithms
- Artificial Intelligence in Healthcare and Education
- Influenza Virus Research Studies
- Machine Learning in Healthcare
- Innovative Human-Technology Interaction
- Genetics, Bioinformatics, and Biomedical Research
- Vaccine Coverage and Hesitancy
- Healthcare Technology and Patient Monitoring
- SARS-CoV-2 and COVID-19 Research
- Semantic Web and Ontologies
- Cell Image Analysis Techniques
- Data-Driven Disease Surveillance
- Natural Language Processing Techniques
- Pharmaceutical Practices and Patient Outcomes
- Privacy, Security, and Data Protection
University of Pittsburgh
2016-2025
Intelligent Systems Research (United States)
2017-2023
University of North Carolina at Chapel Hill
2022
London School of Hygiene & Tropical Medicine
2022
Geisinger Medical Center
2022
Center for Discovery
2018-2019
Towson University
2007-2010
National Institute on Aging
2005-2006
University of Baltimore
2006
University of Maryland, College Park
2000-2005
The correlation of phenotypic outcomes with genetic variation and environmental factors is a core pursuit in biology biomedicine. Numerous challenges impede our progress: patient phenotypes may not match known diseases, candidate variants be genes that have been characterized, model organisms recapitulate human or veterinary filling evolutionary gaps difficult, many resources must queried to find potentially significant genotype–phenotype associations. Non-human proven instrumental revealing...
Importance Decreasing mortality in the field of pediatric critical care medicine has shifted practicing clinicians’ attention to preserving patients’ neurodevelopmental potential as a main objective. Earlier identification critically ill children at risk for incurring neurologic morbidity would facilitate heightened surveillance that could lead timelier clinical detection, earlier interventions, and preserved trajectory. Objectives To develop machine-learning models identifying acquired...
The Open Microscopy Environment (OME) defines a data model and software implementation to serve as an informatics framework for imaging in biological microscopy experiments, including representation of acquisition parameters, annotations image analysis results. OME is designed support high-content cell-based screening well traditional applications. Data Model, expressed Extensible Markup Language (XML) realized database, both extensible self-describing, allowing it meet emerging needs.
Timeboxes are rectangular widgets that can be used in direct-manipulation graphical user interfaces (GUIs) to specify query constraints on time series data sets. simultaneously two sets of constraints: given a set N profiles, timebox covering periods x1...x2 (x1<x2) and values y1...y2(y1≤y2) will retrieve only those n ∈N have y1≤y≤y2 during all times x1≤x≤x2. TimeSearcher is an information visualization tool combines queries with overview displays, query-by-example facilities, support for...
Timeboxes are rectangular widgets that can be used in direct-manipulation graphical user interfaces (GUIs) to specify query constraints on time series data sets. simultaneously two sets of constraints: given a set N profiles, timebox covering periods x 1 … 2 ( ≤ ) and values y will retrieve only those n√N have during all times . TimeSearcher is an information visualization tool combines queries with overview displays, query-by-example facilities, support for over multiple time-varying...
Precise phenotype information is needed to understand the effects of genetic and epigenetic changes on tumor behavior responsiveness. Extraction representation cancer phenotypes currently mostly performed manually, making it difficult correlate phenotypic data genomic data. In addition, are being produced at an increasingly faster pace, exacerbating problem. The DeepPhe software enables automated extraction detailed from electronic medical records patients. system implements advanced Natural...
There is an increasing interest in clinical prediction tools that can achieve high accuracy and provide explanations of the factors leading to increased risk adverse outcomes. However, approaches explaining complex machine learning (ML) models are rarely informed by end-user needs user evaluations model interpretability lacking healthcare domain. We used extended revisions previously-published theoretical frameworks propose a framework for design user-centered displays explanations. This new...
Our ability to forecast epidemics far into the future is constrained by many complexities of disease systems. Realistic longer-term projections may, however, be possible under well-defined scenarios that specify state critical epidemic drivers. Since December 2020, U.S. COVID-19 Scenario Modeling Hub (SMH) has convened multiple modeling teams make months ahead SARS-CoV-2 burden, totaling nearly 1.8 million national and state-level projections. Here, we find SMH performance varied widely as a...
The increasing deployment of artificial intelligence (AI) tools to inform decision-making across diverse areas including healthcare, employment, social benefits, and government policy, presents a serious risk for disabled people, who have been shown face bias in AI implementations. While there has significant work on analysing mitigating algorithmic bias, the broader mechanisms how emerges applications are not well understood, hampering efforts address where it begins. In this article, we...
Across many fields, scenario modeling has become an important tool for exploring long-term projections and how they might depend on potential interventions critical uncertainties, with relevance to both decision makers scientists. In the past decade, especially during COVID-19 pandemic, field of epidemiology seen substantial growth in use projections. Multiple scenarios are often projected at same time, allowing comparisons that can guide choice intervention, prioritization research topics,...
Section:ChooseTop of pageAbstract <<Overview SarcoidosisOverview the Lung Micr...Rationale for GRADS S...Clinical Outcome MeasuresStudy Procedures and Samp...Study AnalysesStudy PotentialConclusionsReferencesCITING ARTICLES
The principles of genetics apply across the entire tree life. At cellular level we share biological mechanisms with species from which diverged millions, even billions years ago. We can exploit this common ancestry to learn about health and disease, by analyzing DNA protein sequences, but also through observable outcomes genetic differences, i.e. phenotypes. To solve challenging disease problems need unify heterogeneous data that relates genomics traits. Without a big-picture view phenotypic...
Background Sarcoidosis is a multisystem granulomatous disease of unknown origin with variable and often unpredictable course pattern organ involvement. In this study we sought to identify specific bronchoalveolar lavage (BAL) cell gene expression patterns indicative distinct phenotypic traits. Methods RNA sequencing by Ion Torrent Proton was performed on BAL cells obtained from 215 well-characterised patients pulmonary sarcoidosis enrolled in the multicentre Genomic Research Alpha-1...
In Spring 2021, the highly transmissible SARS-CoV-2 Delta variant began to cause increases in cases, hospitalizations, and deaths parts of United States. At time, with slowed vaccination uptake, this novel was expected increase risk pandemic resurgence US summer fall 2021. As part COVID-19 Scenario Modeling Hub, an ensemble nine mechanistic models produced 6-month scenario projections for July-December 2021 These estimated substantial resurgences across resulting from more variant, projected...
Abstract Human-computer interaction (HCI) is much broader than the study of interface design and input devices. It includes considerations social, political, ethical, societal implications computer systems. Concerns such as privacy, accessibility, universal design, voting usability have led to active HCI research. Our examination responses these other issues informs a model social engagement based on influences that motivate various from community. This provides suggestions for with are...