東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Using automated extraction from the ...

Mendonca, Eneida Abrantes.

Linked to FindBook

Google Book

Amazon

博客來

Using automated extraction from the medical record to access biomedical literature.

Record Type:	Language materials, printed : Monograph/item
Title/Author:	Using automated extraction from the medical record to access biomedical literature./
Author:	Mendonca, Eneida Abrantes.
Description:	134 p.
Notes:	Adviser: James J. Cimino.
Contained By:	Dissertation Abstracts International63-04B.
Subject:	Health Sciences, General. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3048191
ISBN:	0493625089

Using automated extraction from the medical record to access biomedical literature.
Mendonca, Eneida Abrantes.

Using automated extraction from the medical record to access biomedical literature. - 134 p.

Adviser: James J. Cimino.

Thesis (Ph.D.)--Columbia University, 2002.

The practice of evidence-based medicine, which gained popularity in the last decade, has encouraged clinicians to understand and utilize critically appraised published research evidence. Despite the increased availability of information and the increased number of clinicians who routinely perform their own searches, clinicians still find comprehensive review of biomedical literature unmanageable. Attention has also been given to the assessment of medical errors and other adverse events in health care. Researchers have shown that most of these failures have in common problems in the access to information. Decision support tools have been advertised as capable of substantially improving health care quality and reduce medical errors. Electronic medical records may provide these tools with useful information about the patient that may result in recommendations that are better tailored to individual patients, and eventually associated with improved outcomes.

ISBN: 0493625089Subjects--Topical Terms:

1017817
Health Sciences, General.

Using automated extraction from the medical record to access biomedical literature.
LDR:03240nam 2200313 a 45 001 932434
005 20110505
008 110505s2002 eng d
020 $a 0493625089
035 $a (UnM)AAI3048191
035 $a AAI3048191
040 $a UnM $c UnM
100 1 $a Mendonca, Eneida Abrantes. $3 1256178
245 1 0 $a Using automated extraction from the medical record to access biomedical literature.
300 $a 134 p.
500 $a Adviser: James J. Cimino.
500 $a Source: Dissertation Abstracts International, Volume: 63-04, Section: B, page: 1769.
502 $a Thesis (Ph.D.)--Columbia University, 2002.
520 $a The practice of evidence-based medicine, which gained popularity in the last decade, has encouraged clinicians to understand and utilize critically appraised published research evidence. Despite the increased availability of information and the increased number of clinicians who routinely perform their own searches, clinicians still find comprehensive review of biomedical literature unmanageable. Attention has also been given to the assessment of medical errors and other adverse events in health care. Researchers have shown that most of these failures have in common problems in the access to information. Decision support tools have been advertised as capable of substantially improving health care quality and reduce medical errors. Electronic medical records may provide these tools with useful information about the patient that may result in recommendations that are better tailored to individual patients, and eventually associated with improved outcomes.
520 $a I have focused my research on the case-specific evidence present in patient medical record (e.g., clinical data and demographics), and the use of this evidence to rank biomedical literature. My ultimate goal is to improve the way retrieved biomedical literature is presented by identifying critical information in the individual medical record that is useful for determining the relevance of literature data, also called research evidence. In preliminary studies, I evaluated techniques for automated knowledge extraction from biomedical literature, and the use of natural language processing and indexing theory to identify critical information in an individual's medical record. I then applied the result of these studies to build knowledge-based approaches to rank citations retrieved from biomedical literature databases.
520 $a The results of the research presented here support the belief that clinical data can facilitate presentation of biomedical literature. The use of conceptual graph representation and graph matching techniques, as well as indexing measures (<italic>tf*idf</italic>) correlated significantly with the average of physicians when judging the relevance of citations to the care of an individual patient. Additional studies are needed in order to understand if this performance is acceptable in a clinical environment.
590 $a School code: 0054.
650 4 $a Health Sciences, General. $3 1017817
650 4 $a Health Sciences, Medicine and Surgery. $3 1017756
650 4 $a Information Science. $3 1017528
690 $a 0564
690 $a 0566
690 $a 0723
710 2 0 $a Columbia University. $3 571054
773 0 $t Dissertation Abstracts International $g 63-04B.
790 $a 0054
790 1 0 $a Cimino, James J., $e advisor
791 $a Ph.D.
792 $a 2002
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3048191