Natural Language Processing and Text Mining (Turning Unstructured Data into Structured)

Ayoub Bagheri; Anastasia Giachanou; Pablo Mosteiro Romero; Suzan Verberne

doi:10.1007/978-3-031-36678-9_5

Natural Language Processing and Text Mining (Turning Unstructured Data into Structured)

Ayoub Bagheri^*, Anastasia Giachanou, Pablo Mosteiro Romero, Suzan Verberne

^*Corresponding author for this work

Leiden University

Research output: Chapter in Book/Report/Conference proceeding › Chapter › Academic

Abstract

The integration of natural language processing (NLP) and text mining techniques has emerged as a key approach to harnessing the potential of unstructured clinical text data. This chapter discusses the challenges posed by clinical narratives and explores the need to transform them into structured formats for improved data accessibility and analysis. The chapter navigates through key concepts, including text pre-processing, text classification, text clustering, topic modeling, and advances in language models and transformers. It highlights the dynamic interplay between these techniques and their applications in tasks ranging from disease classification to extraction of side effects. In addition, the chapter acknowledges the importance of addressing bias and ensuring model explainability in the context of clinical prediction systems. By providing a comprehensive overview, the chapter offers insights into the synergy of NLP and text mining techniques in shaping the future of biomedical AI, ultimately leading to safer, more efficient, and more informed healthcare decisions.

Original language	English
Title of host publication	Clinical Applications of Artificial Intelligence in Real-World Data
Editors	Folkert Asselbergs, Spiros Denaxas, Daniel Oberski, Jason Moore
Publisher	Springer
Pages	69-93
Number of pages	25
Edition	1
ISBN (Electronic)	978-3-031-36678-9
ISBN (Print)	978-3-031-36678-9
DOIs	https://doi.org/10.1007/978-3-031-36678-9_5
Publication status	Published - 5 Nov 2023

Keywords

Natural language processing
Text mining
Clinical text
Text pre-processing
Language models
Text classification
Text clustering
Topic modeling
Explainability
Bias detection
Clinical NLP

Access to Document

10.1007/978-3-031-36678-9_5

978-3-031-36678-9_5Final published version, 514 KBLicence: Taverne

Cite this

@inbook{5da390634023415aafaebc35a04d17af,

title = "Natural Language Processing and Text Mining (Turning Unstructured Data into Structured)",

abstract = "The integration of natural language processing (NLP) and text mining techniques has emerged as a key approach to harnessing the potential of unstructured clinical text data. This chapter discusses the challenges posed by clinical narratives and explores the need to transform them into structured formats for improved data accessibility and analysis. The chapter navigates through key concepts, including text pre-processing, text classification, text clustering, topic modeling, and advances in language models and transformers. It highlights the dynamic interplay between these techniques and their applications in tasks ranging from disease classification to extraction of side effects. In addition, the chapter acknowledges the importance of addressing bias and ensuring model explainability in the context of clinical prediction systems. By providing a comprehensive overview, the chapter offers insights into the synergy of NLP and text mining techniques in shaping the future of biomedical AI, ultimately leading to safer, more efficient, and more informed healthcare decisions.",

keywords = "Natural language processing, Text mining, Clinical text, Text pre-processing, Language models, Text classification, Text clustering, Topic modeling, Explainability, Bias detection, Clinical NLP",

author = "Ayoub Bagheri and Anastasia Giachanou and {Mosteiro Romero}, Pablo and Suzan Verberne",

year = "2023",

month = nov,

day = "5",

doi = "10.1007/978-3-031-36678-9_5",

language = "English",

isbn = "978-3-031-36678-9",

pages = "69--93",

editor = "Folkert Asselbergs and Spiros Denaxas and Daniel Oberski and Jason Moore",

booktitle = "Clinical Applications of Artificial Intelligence in Real-World Data",

publisher = "Springer",

edition = "1",

}

Natural Language Processing and Text Mining (Turning Unstructured Data into Structured). / Bagheri, Ayoub ; Giachanou, Anastasia ; Mosteiro Romero, Pablo et al.
Clinical Applications of Artificial Intelligence in Real-World Data. ed. / Folkert Asselbergs; Spiros Denaxas; Daniel Oberski; Jason Moore. 1. ed. Springer, 2023. p. 69-93.

Research output: Chapter in Book/Report/Conference proceeding › Chapter › Academic

TY - CHAP

T1 - Natural Language Processing and Text Mining (Turning Unstructured Data into Structured)

AU - Bagheri, Ayoub

AU - Giachanou, Anastasia

AU - Mosteiro Romero, Pablo

AU - Verberne, Suzan

PY - 2023/11/5

Y1 - 2023/11/5

N2 - The integration of natural language processing (NLP) and text mining techniques has emerged as a key approach to harnessing the potential of unstructured clinical text data. This chapter discusses the challenges posed by clinical narratives and explores the need to transform them into structured formats for improved data accessibility and analysis. The chapter navigates through key concepts, including text pre-processing, text classification, text clustering, topic modeling, and advances in language models and transformers. It highlights the dynamic interplay between these techniques and their applications in tasks ranging from disease classification to extraction of side effects. In addition, the chapter acknowledges the importance of addressing bias and ensuring model explainability in the context of clinical prediction systems. By providing a comprehensive overview, the chapter offers insights into the synergy of NLP and text mining techniques in shaping the future of biomedical AI, ultimately leading to safer, more efficient, and more informed healthcare decisions.

AB - The integration of natural language processing (NLP) and text mining techniques has emerged as a key approach to harnessing the potential of unstructured clinical text data. This chapter discusses the challenges posed by clinical narratives and explores the need to transform them into structured formats for improved data accessibility and analysis. The chapter navigates through key concepts, including text pre-processing, text classification, text clustering, topic modeling, and advances in language models and transformers. It highlights the dynamic interplay between these techniques and their applications in tasks ranging from disease classification to extraction of side effects. In addition, the chapter acknowledges the importance of addressing bias and ensuring model explainability in the context of clinical prediction systems. By providing a comprehensive overview, the chapter offers insights into the synergy of NLP and text mining techniques in shaping the future of biomedical AI, ultimately leading to safer, more efficient, and more informed healthcare decisions.

KW - Natural language processing

KW - Text mining

KW - Clinical text

KW - Text pre-processing

KW - Language models

KW - Text classification

KW - Text clustering

KW - Topic modeling

KW - Explainability

KW - Bias detection

KW - Clinical NLP

U2 - 10.1007/978-3-031-36678-9_5

DO - 10.1007/978-3-031-36678-9_5

M3 - Chapter

SN - 978-3-031-36678-9

SP - 69

EP - 93

BT - Clinical Applications of Artificial Intelligence in Real-World Data

A2 - Asselbergs, Folkert

A2 - Denaxas, Spiros

A2 - Oberski, Daniel

A2 - Moore, Jason

PB - Springer

ER -

Natural Language Processing and Text Mining (Turning Unstructured Data into Structured)

Abstract

Keywords

Access to Document

Fingerprint

Cite this