- Biomedical Text Mining and Ontologies
- Topic Modeling
- Natural Language Processing Techniques
- Semantic Web and Ontologies
- Machine Learning in Healthcare
- Advanced Text Analysis Techniques
- Meta-analysis and systematic reviews
- Health Sciences Research and Education
- Text Readability and Simplification
- Electronic Health Records Systems
- Data Quality and Management
- Academic Writing and Publishing
- Speech and dialogue systems
- Artificial Intelligence in Healthcare
- Bioinformatics and Genomic Networks
- Health Systems, Economic Evaluations, Quality of Life
- Expert finding and Q&A systems
- scientometrics and bibliometrics research
- Scientific Computing and Data Management
- Recommender Systems and Techniques
- Nursing Diagnosis and Documentation
- Interpreting and Communication in Healthcare
- Clinical practice guidelines implementation
- Heart Failure Treatment and Management
- Imbalanced Data Classification Techniques
Amazon (United States)
2021-2022
The University of Texas at Austin
2022
Northwestern University
2014-2018
Microsoft (United States)
2017
Mayo Clinic
2012-2014
Mayo Clinic in Florida
2011-2013
Mayo Clinic in Arizona
2013
Arizona State University
2009-2011
San Jose State University
2006
Large volumes of data are continuously generated from clinical notes and diagnostic studies catalogued in electronic health records (EHRs). Echocardiography is one the most commonly ordered tests cardiology. This study sought to explore feasibility reliability using natural language processing (NLP) for large-scale targeted extraction multiple elements echocardiography reports. An NLP tool, EchoInfer, was developed automatically extract pertaining cardiovascular structure function...
High cost for systematic review of biomedical literature has generated interest in decreasing overall workload. This can be done by applying natural language processing techniques to 'automate' the classification publications that are potentially relevant a given question. Existing solutions need training using specific supervised machine-learning algorithm and feature-extraction system separately each review. We propose only uses input feedback human reviewers during course As classify...
Background: An increasing number of people visit online health communities to seek information. In these communities, share experiences and information with others, often complemented links different websites. Understanding how websites can help us understand patients' needs in improve peer patients online. Objective: Our goal was (1) what kinds are shared, (2) quality the shared websites, (3) who shares (4) community differences website-sharing behavior, (5) contexts which We aimed find...
Background Temporal information detection systems have been developed by the Mayo Clinic for 2012 i2b2 Natural Language Processing Challenge.
This paper describes the use of an agile text mining platform (Linguamatics' Interactive Information Extraction Platform, I2E) to extract document-level cardiac risk factors in patient records as defined i2b2/UTHealth 2014 challenge. The approach uses a data-driven rule-based methodology with addition simple supervised classifier. We demonstrate that allows for rapid optimization extraction strategies, while post-processing can leverage annotation guidelines, corpus statistics and logic...
The complexity of sentences characteristic to biomedical articles poses a challenge natural language parsers, which are typically trained on large-scale corpora non-technical text. We propose text simplification process, bioSimplify, that seeks reduce the in abstracts order improve performance syntactic parsers processed sentences. Syntactic parsing is one first steps mining pipeline. Thus, any improvement would have ripple effect over all processing steps. evaluated our method using corpus...
Objective Online health knowledge resources contain answers to most of the information needs raised by clinicians in course care. However, significant barriers limit use these for decision-making, especially clinicians' lack time. In this study we assessed feasibility automatically generating summaries a particular clinical topic composed relevant sentences extracted from Medline citations. Methods The proposed approach combines retrieval and semantic extraction techniques identify...
Background Heart failure ( HF ) with "recovered" ejection fraction rec EF is an emerging phenotype, but no tools exist to predict recovery in acute . We hypothesized that indices of baseline cardiac structure and function nonischemic cardiomyopathy reduced Methods Results identified a cohort <40% during the first hospitalization (n=166). performed speckle-tracking echocardiography measure longitudinal, circumferential, radial strain, average these measures (myocardial systolic performance)....
Proteins and their interactions govern virtually all cellular processes, such as regulation, signaling, metabolism, structure. Most experimental findings pertaining to are discussed in research papers, which, turn, get curated by protein interaction databases. Authors, editors, publishers benefit from efforts alleviate the tasks of searching for relevant evidence physical interactions, proper identifiers each involved. The BioCreative II.5 community challenge addressed these a...
We present Gecko, a compact and versatile text embedding model. Gecko achieves strong retrieval performance by leveraging key idea: distilling knowledge from large language models (LLMs) into retriever. Our two-step distillation process begins with generating diverse, synthetic paired data using an LLM. Next, we further refine the quality retrieving set of candidate passages for each query, relabeling positive hard negative same The effectiveness our approach is demonstrated compactness...
Objective This paper describes the coreference resolution system submitted by Mayo Clinic for 2011 i2b2/VA/Cincinnati shared task Track 1C. The goal of was to construct a that links markables corresponding same entity.
Accurate systems for extracting Protein-Protein Interactions (PPIs) automatically from biomedical articles can help accelerate research. Biomedical Informatics researchers are collaborating to provide metaservices and advance the state-of-art in PPI extraction. One problem often neglected by current Natural Language Processing is characteristic complexity of sentences literature. In this paper, we report on impact that automatic simplification has performance a extraction system, showing...