東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Advanced natural language processing...

Mehrabi, Saeed.

FindBook

Google Book

Amazon

博客來

Advanced natural language processing and temporal mining for clinical discovery.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Advanced natural language processing and temporal mining for clinical discovery./
作者:	Mehrabi, Saeed.
面頁冊數:	109 p.
附註:	Source: Dissertation Abstracts International, Volume: 77-07(E), Section: B.
Contained By:	Dissertation Abstracts International77-07B(E).
標題:	Health sciences. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10032405
ISBN:	9781339535647

Advanced natural language processing and temporal mining for clinical discovery.
Mehrabi, Saeed.

Advanced natural language processing and temporal mining for clinical discovery. - 109 p.

Source: Dissertation Abstracts International, Volume: 77-07(E), Section: B.

Thesis (Ph.D.)--Indiana University - Purdue University Indianapolis, 2016.

There has been vast and growing amount of healthcare data especially with the rapid adoption of electronic health records (EHRs) as a result of the HITECH act of 2009. It is estimated that around 80% of the clinical information resides in the unstructured narrative of an EHR. Recently, natural language processing (NLP) techniques have offered opportunities to extract information from unstructured clinical texts needed for various clinical applications. A popular method for enabling secondary uses of EHRs is information or concept extraction, a subtask of NLP that seeks to locate and classify elements within text based on the context. Extraction of clinical concepts without considering the context has many complications, including inaccurate diagnosis of patients and contamination of study cohorts. Identifying the negation status and whether a clinical concept belongs to patients or his family members are two of the challenges faced in context detection. A negation algorithm called Dependency Parser Negation (DEEPEN) has been developed in this research study by taking into account the dependency relationship between negation words and concepts within a sentence using the Stanford Dependency Parser. The study results demonstrate that DEEPEN, can reduce the number of incorrect negation assignment for patients with positive findings, and therefore improve the identification of patients with the target clinical findings in EHRs. Additionally, an NLP system consisting of section segmentation and relation discovery was developed to identify patients' family history. To assess the generalizability of the negation and family history algorithm, data from a different clinical institution was used in both algorithm evaluations. The temporal dimension of extracted information from clinical records representing the trajectory of disease progression in patients was also studied in this project. Clinical data of patients who lived in Olmsted County (Rochester, MN) during 1966 to 2010 was analyzed in this work. The patient records were modeled by diagnosis matrices with clinical events as rows and their temporal information as columns. Deep learning algorithm was used to find common temporal patterns within these diagnosis matrices.

ISBN: 9781339535647Subjects--Topical Terms:

3168359
Health sciences.

Advanced natural language processing and temporal mining for clinical discovery.
LDR:03184nmm a2200277 4500 001 2077724
005 20161114132420.5
008 170521s2016 ||||||||||||||||| ||eng d
020 $a 9781339535647
035 $a (MiAaPQ)AAI10032405
035 $a AAI10032405
040 $a MiAaPQ $c MiAaPQ
100 1 $a Mehrabi, Saeed. $3 3193251
245 1 0 $a Advanced natural language processing and temporal mining for clinical discovery.
300 $a 109 p.
500 $a Source: Dissertation Abstracts International, Volume: 77-07(E), Section: B.
500 $a Advisers: Josette F. Jones; Mathew J. Palakal.
502 $a Thesis (Ph.D.)--Indiana University - Purdue University Indianapolis, 2016.
520 $a There has been vast and growing amount of healthcare data especially with the rapid adoption of electronic health records (EHRs) as a result of the HITECH act of 2009. It is estimated that around 80% of the clinical information resides in the unstructured narrative of an EHR. Recently, natural language processing (NLP) techniques have offered opportunities to extract information from unstructured clinical texts needed for various clinical applications. A popular method for enabling secondary uses of EHRs is information or concept extraction, a subtask of NLP that seeks to locate and classify elements within text based on the context. Extraction of clinical concepts without considering the context has many complications, including inaccurate diagnosis of patients and contamination of study cohorts. Identifying the negation status and whether a clinical concept belongs to patients or his family members are two of the challenges faced in context detection. A negation algorithm called Dependency Parser Negation (DEEPEN) has been developed in this research study by taking into account the dependency relationship between negation words and concepts within a sentence using the Stanford Dependency Parser. The study results demonstrate that DEEPEN, can reduce the number of incorrect negation assignment for patients with positive findings, and therefore improve the identification of patients with the target clinical findings in EHRs. Additionally, an NLP system consisting of section segmentation and relation discovery was developed to identify patients' family history. To assess the generalizability of the negation and family history algorithm, data from a different clinical institution was used in both algorithm evaluations. The temporal dimension of extracted information from clinical records representing the trajectory of disease progression in patients was also studied in this project. Clinical data of patients who lived in Olmsted County (Rochester, MN) during 1966 to 2010 was analyzed in this work. The patient records were modeled by diagnosis matrices with clinical events as rows and their temporal information as columns. Deep learning algorithm was used to find common temporal patterns within these diagnosis matrices.
590 $a School code: 0104.
650 4 $a Health sciences. $3 3168359
650 4 $a Information science. $3 554358
690 $a 0566
690 $a 0723
710 2 $a Indiana University - Purdue University Indianapolis. $b Health Informatics. $3 3193252
773 0 $t Dissertation Abstracts International $g 77-07B(E).
790 $a 0104
791 $a Ph.D.
792 $a 2016
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10032405