Analysing effectiveness of multi-label classification in clinical coding

Rajvir Kaur; Jeewani Anupama Ginige

doi:10.1145/3290688.3290728

Analysing effectiveness of multi-label classification in clinical coding

Rajvir Kaur, Jeewani Anupama Ginige

Western Sydney University

Research output: Chapter in Book / Conference Paper › Conference Paper › peer-review

5 Citations (Scopus)

Abstract

In Australia, hospital discharge summaries created at the end of an episode of care contain the patient's medical information based on which clinical codes are assigned. A patient can have multiple diseases and interventions carried out during their stay in the hospital. In this paper, we have done multi-label diseases and interventions classification using Binary Relevance, Label Power-set, and Multi-Layer k-Nearest Neighbor classifier. Our experimental work is divided into three tasks: Random Selection, User Selected, and Repetitive Task. Repetitive task gave better performance in comparison to the other two task.

Original language	English
Title of host publication	Proceedings of the Australasian Computer Science Week Multiconference (ACSW 2019), 29-31 January 2019, Macquarie University, Sydney, Australia
Publisher	Association for Computing Machinery
Number of pages	9
ISBN (Print)	9781450366038
DOIs	https://doi.org/10.1145/3290688.3290728
Publication status	Published - 2019
Event	Australasian Conference on Health Informatics and Knowledge Management - Duration: 29 Jan 2019 → …

Conference

Conference	Australasian Conference on Health Informatics and Knowledge Management
Period	29/01/19 → …

Keywords

classification
digestive organs
diseases
medical records
respiratory organs

Access to Document

10.1145/3290688.3290728

Cite this

@inproceedings{03340f054c60488d8f36e87545bb255e,

title = "Analysing effectiveness of multi-label classification in clinical coding",

abstract = "In Australia, hospital discharge summaries created at the end of an episode of care contain the patient's medical information based on which clinical codes are assigned. A patient can have multiple diseases and interventions carried out during their stay in the hospital. In this paper, we have done multi-label diseases and interventions classification using Binary Relevance, Label Power-set, and Multi-Layer k-Nearest Neighbor classifier. Our experimental work is divided into three tasks: Random Selection, User Selected, and Repetitive Task. Repetitive task gave better performance in comparison to the other two task.",

keywords = "classification, digestive organs, diseases, medical records, respiratory organs",

author = "Rajvir Kaur and Ginige, {Jeewani Anupama}",

year = "2019",

doi = "10.1145/3290688.3290728",

language = "English",

isbn = "9781450366038",

booktitle = "Proceedings of the Australasian Computer Science Week Multiconference (ACSW 2019), 29-31 January 2019, Macquarie University, Sydney, Australia",

publisher = "Association for Computing Machinery",

note = "Australasian Conference on Health Informatics and Knowledge Management ; Conference date: 29-01-2019",

}

Kaur, R & Ginige, JA 2019, Analysing effectiveness of multi-label classification in clinical coding. in Proceedings of the Australasian Computer Science Week Multiconference (ACSW 2019), 29-31 January 2019, Macquarie University, Sydney, Australia. Association for Computing Machinery, Australasian Conference on Health Informatics and Knowledge Management, 29/01/19. https://doi.org/10.1145/3290688.3290728

Analysing effectiveness of multi-label classification in clinical coding. / Kaur, Rajvir; Ginige, Jeewani Anupama.
Proceedings of the Australasian Computer Science Week Multiconference (ACSW 2019), 29-31 January 2019, Macquarie University, Sydney, Australia. Association for Computing Machinery, 2019.

Research output: Chapter in Book / Conference Paper › Conference Paper › peer-review

TY - GEN

T1 - Analysing effectiveness of multi-label classification in clinical coding

AU - Kaur, Rajvir

AU - Ginige, Jeewani Anupama

PY - 2019

Y1 - 2019

N2 - In Australia, hospital discharge summaries created at the end of an episode of care contain the patient's medical information based on which clinical codes are assigned. A patient can have multiple diseases and interventions carried out during their stay in the hospital. In this paper, we have done multi-label diseases and interventions classification using Binary Relevance, Label Power-set, and Multi-Layer k-Nearest Neighbor classifier. Our experimental work is divided into three tasks: Random Selection, User Selected, and Repetitive Task. Repetitive task gave better performance in comparison to the other two task.

AB - In Australia, hospital discharge summaries created at the end of an episode of care contain the patient's medical information based on which clinical codes are assigned. A patient can have multiple diseases and interventions carried out during their stay in the hospital. In this paper, we have done multi-label diseases and interventions classification using Binary Relevance, Label Power-set, and Multi-Layer k-Nearest Neighbor classifier. Our experimental work is divided into three tasks: Random Selection, User Selected, and Repetitive Task. Repetitive task gave better performance in comparison to the other two task.

KW - classification

KW - digestive organs

KW - diseases

KW - medical records

KW - respiratory organs

UR - http://handle.westernsydney.edu.au:8081/1959.7/uws:49816

U2 - 10.1145/3290688.3290728

DO - 10.1145/3290688.3290728

M3 - Conference Paper

SN - 9781450366038

BT - Proceedings of the Australasian Computer Science Week Multiconference (ACSW 2019), 29-31 January 2019, Macquarie University, Sydney, Australia

PB - Association for Computing Machinery

T2 - Australasian Conference on Health Informatics and Knowledge Management

Y2 - 29 January 2019

ER -

Analysing effectiveness of multi-label classification in clinical coding

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this