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

A Meta-narrative Approach to the Ext...

Chartash, David Samuel.

Linked to FindBook

Google Book

Amazon

博客來

A Meta-narrative Approach to the Extraction of Meaningful Semantic Information for Differential Diagnosis from the Clinical Record.

Record Type:	Electronic resources : Monograph/item
Title/Author:	A Meta-narrative Approach to the Extraction of Meaningful Semantic Information for Differential Diagnosis from the Clinical Record./
Author:	Chartash, David Samuel.
Published:	Ann Arbor : ProQuest Dissertations & Theses, : 2018,
Description:	132 p.
Notes:	Source: Dissertation Abstracts International, Volume: 79-09(E), Section: B.
Contained By:	Dissertation Abstracts International79-09B(E).
Subject:	Medicine. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10790949
ISBN:	9780355935325

A Meta-narrative Approach to the Extraction of Meaningful Semantic Information for Differential Diagnosis from the Clinical Record.
Chartash, David Samuel.

A Meta-narrative Approach to the Extraction of Meaningful Semantic Information for Differential Diagnosis from the Clinical Record. - Ann Arbor : ProQuest Dissertations & Theses, 2018 - 132 p.

Source: Dissertation Abstracts International, Volume: 79-09(E), Section: B.

Thesis (Ph.D.)--Indiana University, 2018.

During the clinical encounter, physicians make a record of their diagnostic reasoning through the use of descriptive language. The encoding of information using natural language is predicated on the clinical actions taken during the encounter: history-taking, physical examination, and ancillary investigation, all coupled with the meta-cognition that is clinical reasoning. In the typology of notes, consult notes, discharge summaries, and complex case or procedure reports all contain illocutionary acts and a greater degree of linguistic coherence than laboratory reports or progress notes. In order to model the information within the diagnostic record, given the clinical sequentiality of the encoding process, this dissertation proposes a meta-narrative model. The complexity of clinical language used to generate the diagnostic record is modeled by examining the retrieval of both information and semantic structure of the note. The retrieval of the meta-cognitive propositional and structural semantic perspectives of reasoning is achieved through the use of computational linguistic techniques. From a propositional perspective, these techniques are applied to rheumatology discharge summaries to model the clinical information within a narrative, given known approaches to biomedical factuality detection. From a structural semantic perspective, these techniques are applied to a story from The Decameron to test the generalizability of the structural semantic perspective given a known model of narrative elements for the story. Validating and integrating these meta-cognitive perspectives into a single complex model for a clinical use case, information retrieved can be compared against an extant model of clinical information. For the use case of a nuclear medicine scan followed by a pathology examination, analyzing the resultant reports suggests that the similarities between diagnostic radiology and pathology lie in both their report structure, and the information model that frames the practice of diagnostic radiology. This suggests that for prospective efforts to integrate diagnostic workflow across these specialties, diagnostic radiology and pathology are similar as they provide information in a written form to the referring physician. Furthermore, procedural radiology (and procedural imaging more generally) stands as a separate approach for diagnostic information retrieval and generation.

ISBN: 9780355935325Subjects--Topical Terms:

641104
Medicine.

A Meta-narrative Approach to the Extraction of Meaningful Semantic Information for Differential Diagnosis from the Clinical Record.
LDR:03440nmm a2200313 4500 001 2164658
005 20181116131021.5
008 190424s2018 ||||||||||||||||| ||eng d
020 $a 9780355935325
035 $a (MiAaPQ)AAI10790949
035 $a (MiAaPQ)indiana:15150
035 $a AAI10790949
040 $a MiAaPQ $c MiAaPQ
100 1 $a Chartash, David Samuel. $3 3352709
245 1 2 $a A Meta-narrative Approach to the Extraction of Meaningful Semantic Information for Differential Diagnosis from the Clinical Record.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2018
300 $a 132 p.
500 $a Source: Dissertation Abstracts International, Volume: 79-09(E), Section: B.
500 $a Adviser: Stephen M. Downs.
502 $a Thesis (Ph.D.)--Indiana University, 2018.
520 $a During the clinical encounter, physicians make a record of their diagnostic reasoning through the use of descriptive language. The encoding of information using natural language is predicated on the clinical actions taken during the encounter: history-taking, physical examination, and ancillary investigation, all coupled with the meta-cognition that is clinical reasoning. In the typology of notes, consult notes, discharge summaries, and complex case or procedure reports all contain illocutionary acts and a greater degree of linguistic coherence than laboratory reports or progress notes. In order to model the information within the diagnostic record, given the clinical sequentiality of the encoding process, this dissertation proposes a meta-narrative model. The complexity of clinical language used to generate the diagnostic record is modeled by examining the retrieval of both information and semantic structure of the note. The retrieval of the meta-cognitive propositional and structural semantic perspectives of reasoning is achieved through the use of computational linguistic techniques. From a propositional perspective, these techniques are applied to rheumatology discharge summaries to model the clinical information within a narrative, given known approaches to biomedical factuality detection. From a structural semantic perspective, these techniques are applied to a story from The Decameron to test the generalizability of the structural semantic perspective given a known model of narrative elements for the story. Validating and integrating these meta-cognitive perspectives into a single complex model for a clinical use case, information retrieved can be compared against an extant model of clinical information. For the use case of a nuclear medicine scan followed by a pathology examination, analyzing the resultant reports suggests that the similarities between diagnostic radiology and pathology lie in both their report structure, and the information model that frames the practice of diagnostic radiology. This suggests that for prospective efforts to integrate diagnostic workflow across these specialties, diagnostic radiology and pathology are similar as they provide information in a written form to the referring physician. Furthermore, procedural radiology (and procedural imaging more generally) stands as a separate approach for diagnostic information retrieval and generation.
590 $a School code: 0093.
650 4 $a Medicine. $3 641104
650 4 $a Information science. $3 554358
650 4 $a Linguistics. $3 524476
690 $a 0564
690 $a 0723
690 $a 0290
710 2 $a Indiana University. $b Informatics. $3 1680747
773 0 $t Dissertation Abstracts International $g 79-09B(E).
790 $a 0093
791 $a Ph.D.
792 $a 2018
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10790949