Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

Emerging clinical applications of text analytics

Spasic, Irena ORCID: https://orcid.org/0000-0002-8132-3885, Uzuner, Özlem and Zhou, Li 2020. Emerging clinical applications of text analytics. International Journal of Medical Informatics 134 , 103974. 10.1016/j.ijmedinf.2019.103974

Full text not available from this repository.

Abstract

Clinical narratives are used as a key communication stream within healthcare and associated research. In comparison to structured elements of electronic health records, free text conveys individualized patient history and assessments, providing a rich context for clinical decision making. Natural language processing (NLP), one foundational technique used in text analytics, has repeatedly demonstrated its feasibility to unlock information described in free text efficiently and effectively. The development of text analytics beyond basic NLP has been facilitated by increased adoption of machine learning techniques. In particular, recent years have witnessed the greatest leap in performance in the history of computer science following the arrival of deep learning. Human-like performance in a wide range of text analytics tasks has opened the gate to its routine use in various clinical care settings. Unfortunately, clinical narratives are yet to be routinely analysed on a large scale. This is largely associated with accessibility of clinical narratives in relation to privacy concerns. Another reason for the slow adoption of text analytics in routine clinical care is the scarcity of evidence that clearly demonstrates its utility in the wider context of clinical applications.

Item Type: Article
Date Type: Publication
Status: Published
Schools: Computer Science & Informatics
Data Innovation Research Institute (DIURI)
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Q Science > QA Mathematics > QA76 Computer software
Publisher: Elsevier
ISSN: 1386-5056
Last Modified: 26 Oct 2022 07:58
URI: https://orca.cardiff.ac.uk/id/eprint/126300

Citation Data

Cited 9 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item Edit Item