Open Access. Powered by Scholars. Published by Universities.®
Library and Information Science Commons™
Open Access. Powered by Scholars. Published by Universities.®
- Discipline
- Keyword
-
- Big data (1)
- CRFs (1)
- Data mining (1)
- Health informatics (1)
- Health information systems (1)
-
- Health surveys (1)
- Information extraction (1)
- Information retrieval (1)
- Information storage and retrieval systems (1)
- Machine learning (1)
- Medical informatics (1)
- Medical records (1)
- NLP (1)
- Named-entity recognition (1)
- Natural language processing (Computer science) (1)
- Public health (1)
- Public health records (1)
- Word embeddings (1)
Articles 1 - 2 of 2
Full-Text Articles in Library and Information Science
Examining Publicly Accessible Data Resources And Applications In Healthcare, Sarah Siddiqui
Examining Publicly Accessible Data Resources And Applications In Healthcare, Sarah Siddiqui
Legacy Theses & Dissertations (2009 - 2024)
This thesis is a study of popular data resources in healthcare and their applications toward health information system design and development. The first section reviews the way data is collected with a list of websites where health datasets can be obtained; along with a summary of the recognized vocabulary standards that make it easier to understand and share this data. The next section discusses ways of data categorization for better analysis, recognizing that a significant proportion of health data is unstructured. The Recent Findings section highlights the changes in the data over the years and the ways in which their …
Clinical Information Extraction From Unstructured Free-Texts, Mingzhe Tao
Clinical Information Extraction From Unstructured Free-Texts, Mingzhe Tao
Legacy Theses & Dissertations (2009 - 2024)
Information extraction (IE) is a fundamental component of natural language processing (NLP) that provides a deeper understanding of the texts. In the clinical domain, documents prepared by medical experts (e.g., discharge summaries, drug labels, medical history records) contain a significant amount of clinically-relevant information that is crucial to the overall well-being of patients. Unfortunately, in many cases, clinically-relevant information is presented in an unstructured format, predominantly consisting of free-texts, making it inaccessible to computerized methods. Automatic extraction of this information can improve accessibility. However, the presence of synonymous expressions, medical acronyms, misspellings, negated phrases, and ambiguous terminologies make automatic extraction …