Mining patient flow patterns in a surgical ward

Christoffer Olling Back; Areti Manataki; Ewen Harrison

doi:10.5220/0009181302730283

Mining patient flow patterns in a surgical ward

Christoffer Olling Back, Areti Manataki, Ewen Harrison

School of Computer Science

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

Abstract

Surgery is a highly critical and costly procedure, and there is an imperative need to improve the efficiency in surgical wards. Analyzing surgical patient flow and predicting cycle times of different peri-operative phases can help improve the scheduling and management of surgeries. In this paper, we propose a novel approach to mining temporal patterns of surgical patient flow with the use of Bayesian belief networks. We present and compare three classes of probabilistic models and we evaluate them with respect to predicting cycle times of individual phases of patient flow. The results of this study support previous work that surgical times are log-normally distributed. We also show that the inclusion of a clustering pre-processing step improves the performance of our models considerably.

Original language	English
Title of host publication	Proceedings of the 13th International Joint Conference on Biomedical Engineering Systems and Technologies
Publisher	SciTePress
Pages	273-283
Number of pages	11
Volume	5
ISBN (Print)	9789897583988
DOIs	https://doi.org/10.5220/0009181302730283
Publication status	Published - 18 Mar 2020
Event	13th International Conference on Health Informatics, part of the 13th International Joint Conference on Biomedical Engineering Systems and Technologies - Valetta, Malta Duration: 24 Feb 2020 → 26 Feb 2020 http://www.healthinf.biostec.org/?y=2020

Conference

Conference	13th International Conference on Health Informatics, part of the 13th International Joint Conference on Biomedical Engineering Systems and Technologies
Abbreviated title	HEALTHINF
Country/Territory	Malta
City	Valetta
Period	24/02/20 → 26/02/20
Internet address	http://www.healthinf.biostec.org/?y=2020

Keywords

Bayesian network
Data mining
Patient flows
Process mining
Surgery
Surgical workflow

Access to Document

10.5220/0009181302730283Licence: CC BY-NC-ND

HEALTHINF_2020_120
Copyright © 2020 by SCITEPRESS - Science and Technology Publications Lda. Open Access Article. This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International Licence.
Final published version, 9.88 MBLicence: CC BY-NC-ND

Cite this

@inproceedings{27f38bf2f40343f9847d77041791e5ad,

title = "Mining patient flow patterns in a surgical ward",

abstract = "Surgery is a highly critical and costly procedure, and there is an imperative need to improve the efficiency in surgical wards. Analyzing surgical patient flow and predicting cycle times of different peri-operative phases can help improve the scheduling and management of surgeries. In this paper, we propose a novel approach to mining temporal patterns of surgical patient flow with the use of Bayesian belief networks. We present and compare three classes of probabilistic models and we evaluate them with respect to predicting cycle times of individual phases of patient flow. The results of this study support previous work that surgical times are log-normally distributed. We also show that the inclusion of a clustering pre-processing step improves the performance of our models considerably.",

keywords = "Bayesian network, Data mining, Patient flows, Process mining, Surgery, Surgical workflow",

author = "{Olling Back}, Christoffer and Areti Manataki and Ewen Harrison",

year = "2020",

month = mar,

day = "18",

doi = "10.5220/0009181302730283",

language = "English",

isbn = "9789897583988",

volume = "5",

pages = "273--283",

booktitle = "Proceedings of the 13th International Joint Conference on Biomedical Engineering Systems and Technologies",

publisher = "SciTePress",

note = "13th International Conference on Health Informatics, part of the 13th International Joint Conference on Biomedical Engineering Systems and Technologies, HEALTHINF ; Conference date: 24-02-2020 Through 26-02-2020",

url = "http://www.healthinf.biostec.org/?y=2020",

}

Olling Back, C, Manataki, A & Harrison, E 2020, Mining patient flow patterns in a surgical ward. in Proceedings of the 13th International Joint Conference on Biomedical Engineering Systems and Technologies. vol. 5, SciTePress, pp. 273-283, 13th International Conference on Health Informatics, part of the 13th International Joint Conference on Biomedical Engineering Systems and Technologies, Valetta, Malta, 24/02/20. https://doi.org/10.5220/0009181302730283

TY - GEN

T1 - Mining patient flow patterns in a surgical ward

AU - Olling Back, Christoffer

AU - Manataki, Areti

AU - Harrison, Ewen

PY - 2020/3/18

Y1 - 2020/3/18

N2 - Surgery is a highly critical and costly procedure, and there is an imperative need to improve the efficiency in surgical wards. Analyzing surgical patient flow and predicting cycle times of different peri-operative phases can help improve the scheduling and management of surgeries. In this paper, we propose a novel approach to mining temporal patterns of surgical patient flow with the use of Bayesian belief networks. We present and compare three classes of probabilistic models and we evaluate them with respect to predicting cycle times of individual phases of patient flow. The results of this study support previous work that surgical times are log-normally distributed. We also show that the inclusion of a clustering pre-processing step improves the performance of our models considerably.

AB - Surgery is a highly critical and costly procedure, and there is an imperative need to improve the efficiency in surgical wards. Analyzing surgical patient flow and predicting cycle times of different peri-operative phases can help improve the scheduling and management of surgeries. In this paper, we propose a novel approach to mining temporal patterns of surgical patient flow with the use of Bayesian belief networks. We present and compare three classes of probabilistic models and we evaluate them with respect to predicting cycle times of individual phases of patient flow. The results of this study support previous work that surgical times are log-normally distributed. We also show that the inclusion of a clustering pre-processing step improves the performance of our models considerably.

KW - Bayesian network

KW - Data mining

KW - Patient flows

KW - Process mining

KW - Surgery

KW - Surgical workflow

U2 - 10.5220/0009181302730283

DO - 10.5220/0009181302730283

M3 - Conference contribution

SN - 9789897583988

VL - 5

SP - 273

EP - 283

BT - Proceedings of the 13th International Joint Conference on Biomedical Engineering Systems and Technologies

PB - SciTePress

T2 - 13th International Conference on Health Informatics, part of the 13th International Joint Conference on Biomedical Engineering Systems and Technologies

Y2 - 24 February 2020 through 26 February 2020

ER -

Mining patient flow patterns in a surgical ward

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this