Text Mining and Automation for Processing of Patient Referrals

James Todd, Brent Richards, Bruce J Vanstone, Adrian Gepp

Research output: Contribution to journalArticleResearchpeer-review

Abstract

Background: Various tasks within healthcare processes are repetitive and time-consuming, requiring personnel who could be better utilized elsewhere. The task of assigning clinical urgency categories to internal patient referrals is such a case of a time-consuming process, which may be amenable to automation through the application of text mining and Natural Language Processing (NLP) techniques.
Objectives: To trial and evaluate a pilot study for the first component of the task – determining reasons for referrals.
Methods: Text is extracted from scanned patient referrals before being processed to remove nonsensical symbols and to identify key information. The processed data are compared against a list of conditions that represent possible reasons for referral. Similarity scores are used as a measure of overlap in terms used in the processed data and the condition list.
Results: This pilot study was successful and results indicate that it would be valuable for future research to develop a more sophisticated classification model for determining reasons for referrals. Issues encountered in the pilot study and methods of addressing them were outlined and should be of use to researchers working on similar problems.
Conclusion: This pilot study successfully demonstrated that there is potential for automating the assignment of reasons for referrals and provides a foundation for further work to build on. This study also outlined a potential application of text mining and NLP to automating a manual task in hospitals to save time of human resources.
Original languageEnglish
Pages (from-to)232-237
Number of pages6
JournalApplied Clinical Informatics
Volume9
Issue number1
DOIs
Publication statusPublished - 28 Mar 2018

Fingerprint

Data Mining
Automation
Referral and Consultation
Personnel
Processing
Natural Language Processing
Research Personnel
Delivery of Health Care

Cite this

@article{5015d364ed3f4b79abf258dbaec50faf,
title = "Text Mining and Automation for Processing of Patient Referrals",
abstract = "Background: Various tasks within healthcare processes are repetitive and time-consuming, requiring personnel who could be better utilized elsewhere. The task of assigning clinical urgency categories to internal patient referrals is such a case of a time-consuming process, which may be amenable to automation through the application of text mining and Natural Language Processing (NLP) techniques. Objectives: To trial and evaluate a pilot study for the first component of the task – determining reasons for referrals.Methods: Text is extracted from scanned patient referrals before being processed to remove nonsensical symbols and to identify key information. The processed data are compared against a list of conditions that represent possible reasons for referral. Similarity scores are used as a measure of overlap in terms used in the processed data and the condition list.Results: This pilot study was successful and results indicate that it would be valuable for future research to develop a more sophisticated classification model for determining reasons for referrals. Issues encountered in the pilot study and methods of addressing them were outlined and should be of use to researchers working on similar problems.Conclusion: This pilot study successfully demonstrated that there is potential for automating the assignment of reasons for referrals and provides a foundation for further work to build on. This study also outlined a potential application of text mining and NLP to automating a manual task in hospitals to save time of human resources.",
author = "James Todd and Brent Richards and Vanstone, {Bruce J} and Adrian Gepp",
year = "2018",
month = "3",
day = "28",
doi = "10.1055/s-0038-1639482",
language = "English",
volume = "9",
pages = "232--237",
journal = "Applied Clinical Informatics",
issn = "1869-0327",
publisher = "Schattauer GmbH",
number = "1",

}

Text Mining and Automation for Processing of Patient Referrals. / Todd, James; Richards, Brent; Vanstone, Bruce J; Gepp, Adrian.

In: Applied Clinical Informatics, Vol. 9, No. 1, 28.03.2018, p. 232-237.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Text Mining and Automation for Processing of Patient Referrals

AU - Todd, James

AU - Richards, Brent

AU - Vanstone, Bruce J

AU - Gepp, Adrian

PY - 2018/3/28

Y1 - 2018/3/28

N2 - Background: Various tasks within healthcare processes are repetitive and time-consuming, requiring personnel who could be better utilized elsewhere. The task of assigning clinical urgency categories to internal patient referrals is such a case of a time-consuming process, which may be amenable to automation through the application of text mining and Natural Language Processing (NLP) techniques. Objectives: To trial and evaluate a pilot study for the first component of the task – determining reasons for referrals.Methods: Text is extracted from scanned patient referrals before being processed to remove nonsensical symbols and to identify key information. The processed data are compared against a list of conditions that represent possible reasons for referral. Similarity scores are used as a measure of overlap in terms used in the processed data and the condition list.Results: This pilot study was successful and results indicate that it would be valuable for future research to develop a more sophisticated classification model for determining reasons for referrals. Issues encountered in the pilot study and methods of addressing them were outlined and should be of use to researchers working on similar problems.Conclusion: This pilot study successfully demonstrated that there is potential for automating the assignment of reasons for referrals and provides a foundation for further work to build on. This study also outlined a potential application of text mining and NLP to automating a manual task in hospitals to save time of human resources.

AB - Background: Various tasks within healthcare processes are repetitive and time-consuming, requiring personnel who could be better utilized elsewhere. The task of assigning clinical urgency categories to internal patient referrals is such a case of a time-consuming process, which may be amenable to automation through the application of text mining and Natural Language Processing (NLP) techniques. Objectives: To trial and evaluate a pilot study for the first component of the task – determining reasons for referrals.Methods: Text is extracted from scanned patient referrals before being processed to remove nonsensical symbols and to identify key information. The processed data are compared against a list of conditions that represent possible reasons for referral. Similarity scores are used as a measure of overlap in terms used in the processed data and the condition list.Results: This pilot study was successful and results indicate that it would be valuable for future research to develop a more sophisticated classification model for determining reasons for referrals. Issues encountered in the pilot study and methods of addressing them were outlined and should be of use to researchers working on similar problems.Conclusion: This pilot study successfully demonstrated that there is potential for automating the assignment of reasons for referrals and provides a foundation for further work to build on. This study also outlined a potential application of text mining and NLP to automating a manual task in hospitals to save time of human resources.

UR - http://www.scopus.com/inward/record.url?scp=85055789912&partnerID=8YFLogxK

U2 - 10.1055/s-0038-1639482

DO - 10.1055/s-0038-1639482

M3 - Article

VL - 9

SP - 232

EP - 237

JO - Applied Clinical Informatics

JF - Applied Clinical Informatics

SN - 1869-0327

IS - 1

ER -