Automatic biomedical information extraction from free text

Placeholder Show Content

Abstract/Contents

Abstract
Advances in medical research, pharmaceuticals, treatment options, and biotechnology are occurring at an explosive rate. As of 2009, there are 19 million of biomedical research abstracts available on MEDLINE and 1.3 billion searches of MEDLINE are done in 2009. Most of the popular search engines, from Google to PubMed, use keyword-based information retrieval methods, often overloading users with irrelevant information. At the same time, keyword-based search engines cannot answer simple biomedical questions, such as "what are the breast cancer treatment drugs" or "what are the breast cancer associated genes". Answering such questions requires machine understandable knowledge to be extracted from free text. My thesis represents an automated system to extract machine understandable biomedical information from MEDLINE abstracts using machine learning and natural language processing ( NLP ) techniques. The system is different from current biomedical information extraction systems in the following: 1.the system is semi-supervised where the only human supervision is a single pattern for each information type; 2. it can be used to extract broad types of information, including named entities and relationships among entities.

Description

Type of resource text
Form electronic; electronic resource; remote
Extent 1 online resource.
Publication date 2010
Issuance monographic
Language English

Creators/Contributors

Associated with Xu, Rong, Ms
Associated with Stanford University, Program in Biomedical Informatics.
Primary advisor Das, Amar K. (Amar Kumar)
Primary advisor Garber, Alan M
Thesis advisor Das, Amar K. (Amar Kumar)
Thesis advisor Garber, Alan M
Thesis advisor Altman, Russ
Thesis advisor Manning, Christopher D
Advisor Altman, Russ
Advisor Manning, Christopher D

Subjects

Genre Theses

Bibliographic information

Statement of responsibility Ms Rong Xu.
Note Submitted to the Program in Biomedical Informatics.
Thesis Thesis (Ph.D.)--Stanford University, 2010.
Location electronic resource

Access conditions

Copyright
© 2010 by Rong Xu
License
This work is licensed under a Creative Commons Attribution Non Commercial 3.0 Unported license (CC BY-NC).

Also listed in

Loading usage metrics...