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

Representing, extracting and reasoni...

Zhou, Li.

Linked to FindBook

Google Book

Amazon

博客來

Representing, extracting and reasoning with temporal information in clinical narrative reports.

Record Type:	Language materials, printed : Monograph/item
Title/Author:	Representing, extracting and reasoning with temporal information in clinical narrative reports./
Author:	Zhou, Li.
Description:	218 p.
Notes:	Adviser: George M. Hripcsak.
Contained By:	Dissertation Abstracts International68-06B.
Subject:	Biology, Bioinformatics. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3266710
ISBN:	9780549056645

Representing, extracting and reasoning with temporal information in clinical narrative reports.
Zhou, Li.

Representing, extracting and reasoning with temporal information in clinical narrative reports. - 218 p.

Adviser: George M. Hripcsak.

Thesis (Ph.D.)--Columbia University, 2007.

Temporal information is crucial in electronic medical records (EMR) and biomedical information systems. Reasoning automatically with temporal data can enhance our understanding of the dynamics of medical phenomena and may potentially improve the quality of patient care. Currently, the effective use of temporal information from narrative clinical notes within the EMR represents an important challenge for researchers in the field of biomedical informatics.

ISBN: 9780549056645Subjects--Topical Terms:

1018415
Biology, Bioinformatics.

Representing, extracting and reasoning with temporal information in clinical narrative reports.
LDR:03314nam 2200301 a 45 001 947626
005 20110524
008 110524s2007 ||||||||||||||||| ||eng d
020 $a 9780549056645
035 $a (UMI)AAI3266710
035 $a AAI3266710
040 $a UMI $c UMI
100 1 $a Zhou, Li. $3 1271095
245 1 0 $a Representing, extracting and reasoning with temporal information in clinical narrative reports.
300 $a 218 p.
500 $a Adviser: George M. Hripcsak.
500 $a Source: Dissertation Abstracts International, Volume: 68-06, Section: B, page: 3485.
502 $a Thesis (Ph.D.)--Columbia University, 2007.
520 $a Temporal information is crucial in electronic medical records (EMR) and biomedical information systems. Reasoning automatically with temporal data can enhance our understanding of the dynamics of medical phenomena and may potentially improve the quality of patient care. Currently, the effective use of temporal information from narrative clinical notes within the EMR represents an important challenge for researchers in the field of biomedical informatics.
520 $a The objective of this work is to develop a comprehensive treatment of temporal information in clinical narrative data, including representation, extraction, and reasoning. The goal is to initiate and build a foundation that supports further applications that assist healthcare practice and research.
520 $a In this thesis, I propose a systematic methodology and present a corresponding temporal reasoning system, TimeText, which consists of several components, including: (1) a formal temporal model based on simple temporal constraint satisfaction problem (STP) for representing and reasoning about time-oriented information in clinical reports; (2) a formal model called the Temporal Constraint Structure (TCS) for formalizing and annotating temporal expressions, with the TCS tagger, a computer program that implements the TCS; (3) an integration component that uses an existing medical NLP system (MedLEE) for processing other clinical information; and (4) a subsystem (called T-Order) for handling implicit temporal information and resolving issues such as granularity and uncertainty.
520 $a The results have shown that a STP appears sufficient to represent most temporal assertions in discharge summaries, although repeating events and hypothetical events (e.g. follow-up plans) were considered beyond the scope of this thesis. We also conclude that the proposed TCS embodies a sufficient and successful implementation method to encode the diversity of temporal information in discharge summaries. In addition, the post-processing subsystem demonstrates an innovative approach by utilizing domain and linguistic knowledge and by employing several methodological components to handle implicit and uncertain temporal information. The evaluation of the temporal reasoning system, TimeText, shows that it can encode the majority of temporal relations identified by domain experts, and it is able to answer time-oriented clinical queries.
590 $a School code: 0054.
650 4 $a Biology, Bioinformatics. $3 1018415
690 $a 0715
710 2 $a Columbia University. $3 571054
773 0 $t Dissertation Abstracts International $g 68-06B.
790 $a 0054
790 1 0 $a Hripcsak, George M., $e advisor
791 $a Ph.D.
792 $a 2007
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3266710