Material Type  

 학위논문

 

0017164277

Date and Time of Latest Transaction  

20250211152942

ISBN  

9798346867746

DDC  

020

Author  

Balu, Saianand.

Title/Author  

An NLP Enriched Search Engine for Pathology Reports.

Publish Info  

[S.l.] : The University of North Carolina at Chapel Hill., 2024

Publish Info  

Ann Arbor : ProQuest Dissertations & Theses, 2024

Material Info  

85 p.

General Note  

Source: Dissertations Abstracts International, Volume: 86-06, Section: B.

General Note  

Advisor: Mostafa, Javed.

학위논문주기  

Thesis (Ph.D.)--The University of North Carolina at Chapel Hill, 2024.

Abstracts/Etc  

요약This dissertation explores the integration of Natural Language Processing (NLP) techniques to enrich and enhance the searchability and utility of pathology reports within the healthcare research domain. Pathology reports, which provide detailed insights into the diagnosis and progression of diseases, particularly cancer, are often composed of unstructured text. This presents significant challenges in efficiently retrieving and analyzing relevant data. The study aims to develop and evaluate an NLP-enriched search engine tailored for pathology reports, leveraging various text enrichment techniques such as Named Entity Recognition (NER), concept mapping, and negation detection.The research problem addresses the need for robust search tools that can handle the complexity and variability of pathology reports. By implementing a comprehensive NLP pipeline, this dissertation demonstrates the effectiveness of advanced text processing methods in improving information retrieval metrics such as precision, recall, and F1 score. The methodology includes the processing of pathology reports from the UNC Health system, the application of NLP models using scispaCy pipeline and the use of Apache Solr for indexing and search functionalities.Key contributions of this work include the development of enhancing cohort discovery for translational research and providing methodological insights into the relative effectiveness of various NLP techniques. The results indicate significant improvements in search performance metrics, particularly when combining multiple enrichment strategies. These findings have broader implications for the field of medical informatics, offering a roadmap for future research in leveraging NLP to enhance the usability of complex medical texts.This dissertation highlights the transformative potential of NLP in healthcare, particularly in the context of pathology reports. By improving the accessibility and accuracy of critical clinical information, the proposed NLP-enriched search engine has the potential to significantly enhance patient care and support ongoing medical research.

Subject Added Entry-Topical Term  

Information science.

Subject Added Entry-Topical Term  

Bioinformatics.

Index Term-Uncontrolled  

Language model

Index Term-Uncontrolled  

Natural Language Processing techniques

Index Term-Uncontrolled  

Pathology text reports

Added Entry-Corporate Name  

The University of North Carolina at Chapel Hill Health Informatics

Host Item Entry  

Dissertations Abstracts International. 86-06B.

Electronic Location and Access  

로그인을 한후 보실 수 있는 자료입니다.

Control Number  

joongbu:657961