A process mining and text analysis approach to analyse the extent of polypharmacy in medical prescribing

Philip Weber; Ruth Backman; Ian Litchfield; Mark Lee

doi:10.1109/ICHI.2018.00008

A process mining and text analysis approach to analyse the extent of polypharmacy in medical prescribing

Philip Weber, Ruth Backman, Ian Litchfield, Mark Lee

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

1 Citation (Scopus)

453 Downloads (Pure)

Abstract

Prescription of conflicting concurrent medications, polypharmacy, is recognised as a significant problem in the UK, but its extent is not fully known. We combined a process mining approach with text analytics, to discover prescription processes for patients from five primary care sites in the UK West
Midlands. Free-text prescription instructions were combined with online knowledge about drug interactions to reveal that almost 62% of patients were prescribed with medication with some level of interaction, during a two year period. We describe a novel domain-specific approach to reduce the complexity of the mined processes, which will nevertheless be applicable to other flexible environments such as knowledge work. We also highlight difficulties encountered in accessing, interpreting and processing the data, which may be significantly mitigated through wider adoption of a mindset of curating data for automated analysis.

Original language	English
Title of host publication	The Sixth IEEE International Conference on Healthcare Informatics (ICHI 2018)
Publisher	IEEE Xplore
Number of pages	11
DOIs	https://doi.org/10.1109/ICHI.2018.00008
Publication status	Published - 26 Jul 2018
Event	The Sixth IEEE International Conference on Healthcare Informatics - Doubletree, New York City, United States Duration: 4 Jun 2018 → 7 Jun 2018 http://hpr.weill.cornell.edu/divisions/health_informatics/ieee_ichi.html

Conference

Conference	The Sixth IEEE International Conference on Healthcare Informatics
Abbreviated title	ICHI 2018
Country/Territory	United States
City	New York City
Period	4/06/18 → 7/06/18
Internet address	http://hpr.weill.cornell.edu/divisions/health_informatics/ieee_ichi.html

Access to Document

10.1109/ICHI.2018.00008

ICHI2018
Checked for eligibility: 02/05/2018 Published in IEEE Xplore: 10.1109/ICHI.2018.00008
Accepted author manuscript, 932 KBLicence: None: All rights reserved

1 Citations
1 Article

Assessing the extent of drug interactions among patients with multimorbidity in primary and secondary care in the West Midlands (UK): a study protocol for the Mixed Methods Multimorbidity Study (MiMMS)
Backman, R., Weber, P., Turner, A., Lee, M. & Litchfield, I., 18 Sept 2017, In: British Medical Journal Open. 7, e016713.
Research output: Contribution to journal › Article › peer-review

Open Access
File
3 Citations (Scopus)

155 Downloads (Pure)

1 Finished

Automated Conflict Resolution in Clinical Pathways
Lee, M., Litchfield, I., Turner, A. & Bordbar, B.
Engineering & Physical Science Research Council
1/08/15 → 30/04/19
Project: Research Councils

Cite this

@inproceedings{d785b6fa1e4148a4aebbc4888516358b,

title = "A process mining and text analysis approach to analyse the extent of polypharmacy in medical prescribing",

abstract = "Prescription of conflicting concurrent medications, polypharmacy, is recognised as a significant problem in the UK, but its extent is not fully known. We combined a process mining approach with text analytics, to discover prescription processes for patients from five primary care sites in the UK WestMidlands. Free-text prescription instructions were combined with online knowledge about drug interactions to reveal that almost 62% of patients were prescribed with medication with some level of interaction, during a two year period. We describe a novel domain-specific approach to reduce the complexity of the mined processes, which will nevertheless be applicable to other flexible environments such as knowledge work. We also highlight difficulties encountered in accessing, interpreting and processing the data, which may be significantly mitigated through wider adoption of a mindset of curating data for automated analysis.",

author = "Philip Weber and Ruth Backman and Ian Litchfield and Mark Lee",

year = "2018",

month = jul,

day = "26",

doi = "10.1109/ICHI.2018.00008",

language = "English",

booktitle = "The Sixth IEEE International Conference on Healthcare Informatics (ICHI 2018)",

publisher = "IEEE Xplore",

note = "The Sixth IEEE International Conference on Healthcare Informatics , ICHI 2018 ; Conference date: 04-06-2018 Through 07-06-2018",

url = "http://hpr.weill.cornell.edu/divisions/health_informatics/ieee_ichi.html",

}

Weber, P, Backman, R, Litchfield, I & Lee, M 2018, A process mining and text analysis approach to analyse the extent of polypharmacy in medical prescribing. in The Sixth IEEE International Conference on Healthcare Informatics (ICHI 2018). IEEE Xplore, The Sixth IEEE International Conference on Healthcare Informatics , New York City, New York, United States, 4/06/18. https://doi.org/10.1109/ICHI.2018.00008

TY - GEN

T1 - A process mining and text analysis approach to analyse the extent of polypharmacy in medical prescribing

AU - Weber, Philip

AU - Backman, Ruth

AU - Litchfield, Ian

AU - Lee, Mark

PY - 2018/7/26

Y1 - 2018/7/26

N2 - Prescription of conflicting concurrent medications, polypharmacy, is recognised as a significant problem in the UK, but its extent is not fully known. We combined a process mining approach with text analytics, to discover prescription processes for patients from five primary care sites in the UK WestMidlands. Free-text prescription instructions were combined with online knowledge about drug interactions to reveal that almost 62% of patients were prescribed with medication with some level of interaction, during a two year period. We describe a novel domain-specific approach to reduce the complexity of the mined processes, which will nevertheless be applicable to other flexible environments such as knowledge work. We also highlight difficulties encountered in accessing, interpreting and processing the data, which may be significantly mitigated through wider adoption of a mindset of curating data for automated analysis.

AB - Prescription of conflicting concurrent medications, polypharmacy, is recognised as a significant problem in the UK, but its extent is not fully known. We combined a process mining approach with text analytics, to discover prescription processes for patients from five primary care sites in the UK WestMidlands. Free-text prescription instructions were combined with online knowledge about drug interactions to reveal that almost 62% of patients were prescribed with medication with some level of interaction, during a two year period. We describe a novel domain-specific approach to reduce the complexity of the mined processes, which will nevertheless be applicable to other flexible environments such as knowledge work. We also highlight difficulties encountered in accessing, interpreting and processing the data, which may be significantly mitigated through wider adoption of a mindset of curating data for automated analysis.

U2 - 10.1109/ICHI.2018.00008

DO - 10.1109/ICHI.2018.00008

M3 - Conference contribution

BT - The Sixth IEEE International Conference on Healthcare Informatics (ICHI 2018)

PB - IEEE Xplore

T2 - The Sixth IEEE International Conference on Healthcare Informatics

Y2 - 4 June 2018 through 7 June 2018

ER -

A process mining and text analysis approach to analyse the extent of polypharmacy in medical prescribing

Abstract

Conference

Access to Document

Fingerprint

Research output

Assessing the extent of drug interactions among patients with multimorbidity in primary and secondary care in the West Midlands (UK): a study protocol for the Mixed Methods Multimorbidity Study (MiMMS)

Projects

Automated Conflict Resolution in Clinical Pathways

Cite this