Anomaly detection in sequential health care data using higher-order network representation

Haoran Niu; Olufemi A. Omitaomu; Qing Cao; Ozgur Ozmen; Hilda B. Klasky; Mohammed M. Olama; Laura L. Pullum; Teja Kuruganti; Merry Ward; Angela Laurio; Jean M. Scott; Frank Drews; Jonathan R. Nebeker

Anomaly detection in sequential health care data using higher-order network representation

Haoran Niu, Olufemi A. Omitaomu, Qing Cao, Ozgur Ozmen, Hilda B. Klasky, Mohammed M. Olama, Laura L. Pullum, Teja Kuruganti, Merry Ward, Angela Laurio, Jean M. Scott, Frank Drews, Jonathan R. Nebeker

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

Abstract

The ever-increasing use of information technology (IT) in health care presents new challenges to patient care. Information errors arising from the use of Health IT and their implications on care delivery and patient outcomes have been widely reported. Information errors can lead to changes in clinical decisions, care processes, and care outcomes, among others. An altered care process, for example, could interrupt the sequence of care, which could lead to changes in care decisions and/or changes in care outcomes. We define interruptions in the care process as anomalies in the care sequence. In this paper, we present a new approach based on the higher-order network (HON) representation to detect anomalies in sequential health care data using electronic health records. The results show that there are higher-order dependencies in health care data; and that the use of HON representation is more effective than the first-order network representation for detecting anomalies in sequential health care data.

Original language	English
Title of host publication	Proceedings of the 2020 IISE Annual Conference
Editors	L. Cromarty, R. Shirwaiker, P. Wang
Publisher	Institute of Industrial and Systems Engineers, IISE
Pages	813-818
Number of pages	6
ISBN (Electronic)	9781713827818
State	Published - 2020
Event	2020 Institute of Industrial and Systems Engineers Annual Conference and Expo, IISE 2020 - Virtual, Online, United States Duration: Nov 1 2020 → Nov 3 2020

Publication series

Name	Proceedings of the 2020 IISE Annual Conference

Conference

Conference	2020 Institute of Industrial and Systems Engineers Annual Conference and Expo, IISE 2020
Country/Territory	United States
City	Virtual, Online
Period	11/1/20 → 11/3/20

Funding

This work is sponsored by the US Department of Veterans Affairs. This manuscript has been authored by UT-Battelle, LLC, under contract DE-AC05-00OR22725 with the US Department of Energy (DOE). The US government retains and the publisher, by accepting the article for publication, acknowledges that the US government retains a nonexclusive, paid-up, irrevocable, worldwide license to publish or reproduce the published form of this manuscript, or allow others to do so, for US government purposes. DOE will provide public access to these results of federally sponsored research in accordance with the DOE Public Access Plan (http://energy.gov/downloads/doe-public-access-plan).

Keywords

Electronic health records
Higher-order dependency
Process improvement
Process monitoring
System reliability

Cite this

Niu, H., Omitaomu, O. A., Cao, Q., Ozmen, O., Klasky, H. B., Olama, M. M., Pullum, L. L., Kuruganti, T., Ward, M., Laurio, A., Scott, J. M., Drews, F., & Nebeker, J. R. (2020). Anomaly detection in sequential health care data using higher-order network representation. In L. Cromarty, R. Shirwaiker, & P. Wang (Eds.), Proceedings of the 2020 IISE Annual Conference (pp. 813-818). (Proceedings of the 2020 IISE Annual Conference). Institute of Industrial and Systems Engineers, IISE.

@inproceedings{ecea822cac6448a48a2616a55d3d1ff9,

title = "Anomaly detection in sequential health care data using higher-order network representation",

abstract = "The ever-increasing use of information technology (IT) in health care presents new challenges to patient care. Information errors arising from the use of Health IT and their implications on care delivery and patient outcomes have been widely reported. Information errors can lead to changes in clinical decisions, care processes, and care outcomes, among others. An altered care process, for example, could interrupt the sequence of care, which could lead to changes in care decisions and/or changes in care outcomes. We define interruptions in the care process as anomalies in the care sequence. In this paper, we present a new approach based on the higher-order network (HON) representation to detect anomalies in sequential health care data using electronic health records. The results show that there are higher-order dependencies in health care data; and that the use of HON representation is more effective than the first-order network representation for detecting anomalies in sequential health care data.",

keywords = "Electronic health records, Higher-order dependency, Process improvement, Process monitoring, System reliability",

author = "Haoran Niu and Omitaomu, {Olufemi A.} and Qing Cao and Ozgur Ozmen and Klasky, {Hilda B.} and Olama, {Mohammed M.} and Pullum, {Laura L.} and Teja Kuruganti and Merry Ward and Angela Laurio and Scott, {Jean M.} and Frank Drews and Nebeker, {Jonathan R.}",

note = "Publisher Copyright: {\textcopyright} Proceedings of the 2020 IISE Annual. All Rights Reserved.; 2020 Institute of Industrial and Systems Engineers Annual Conference and Expo, IISE 2020 ; Conference date: 01-11-2020 Through 03-11-2020",

year = "2020",

language = "English",

series = "Proceedings of the 2020 IISE Annual Conference",

publisher = "Institute of Industrial and Systems Engineers, IISE",

pages = "813--818",

editor = "L. Cromarty and R. Shirwaiker and P. Wang",

booktitle = "Proceedings of the 2020 IISE Annual Conference",

}

Niu, H , Omitaomu, OA, Cao, Q, Ozmen, O, Klasky, HB , Olama, MM, Pullum, LL, Kuruganti, T, Ward, M, Laurio, A, Scott, JM, Drews, F & Nebeker, JR 2020, Anomaly detection in sequential health care data using higher-order network representation. in L Cromarty, R Shirwaiker & P Wang (eds), Proceedings of the 2020 IISE Annual Conference. Proceedings of the 2020 IISE Annual Conference, Institute of Industrial and Systems Engineers, IISE, pp. 813-818, 2020 Institute of Industrial and Systems Engineers Annual Conference and Expo, IISE 2020, Virtual, Online, United States, 11/1/20.

Anomaly detection in sequential health care data using higher-order network representation. / Niu, Haoran ; Omitaomu, Olufemi A.; Cao, Qing et al.
Proceedings of the 2020 IISE Annual Conference. ed. / L. Cromarty; R. Shirwaiker; P. Wang. Institute of Industrial and Systems Engineers, IISE, 2020. p. 813-818 (Proceedings of the 2020 IISE Annual Conference).

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

TY - GEN

T1 - Anomaly detection in sequential health care data using higher-order network representation

AU - Niu, Haoran

AU - Omitaomu, Olufemi A.

AU - Cao, Qing

AU - Ozmen, Ozgur

AU - Klasky, Hilda B.

AU - Olama, Mohammed M.

AU - Pullum, Laura L.

AU - Kuruganti, Teja

AU - Ward, Merry

AU - Laurio, Angela

AU - Scott, Jean M.

AU - Drews, Frank

AU - Nebeker, Jonathan R.

PY - 2020

Y1 - 2020

N2 - The ever-increasing use of information technology (IT) in health care presents new challenges to patient care. Information errors arising from the use of Health IT and their implications on care delivery and patient outcomes have been widely reported. Information errors can lead to changes in clinical decisions, care processes, and care outcomes, among others. An altered care process, for example, could interrupt the sequence of care, which could lead to changes in care decisions and/or changes in care outcomes. We define interruptions in the care process as anomalies in the care sequence. In this paper, we present a new approach based on the higher-order network (HON) representation to detect anomalies in sequential health care data using electronic health records. The results show that there are higher-order dependencies in health care data; and that the use of HON representation is more effective than the first-order network representation for detecting anomalies in sequential health care data.

AB - The ever-increasing use of information technology (IT) in health care presents new challenges to patient care. Information errors arising from the use of Health IT and their implications on care delivery and patient outcomes have been widely reported. Information errors can lead to changes in clinical decisions, care processes, and care outcomes, among others. An altered care process, for example, could interrupt the sequence of care, which could lead to changes in care decisions and/or changes in care outcomes. We define interruptions in the care process as anomalies in the care sequence. In this paper, we present a new approach based on the higher-order network (HON) representation to detect anomalies in sequential health care data using electronic health records. The results show that there are higher-order dependencies in health care data; and that the use of HON representation is more effective than the first-order network representation for detecting anomalies in sequential health care data.

KW - Electronic health records

KW - Higher-order dependency

KW - Process improvement

KW - Process monitoring

KW - System reliability

UR - http://www.scopus.com/inward/record.url?scp=85105613562&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85105613562

T3 - Proceedings of the 2020 IISE Annual Conference

SP - 813

EP - 818

BT - Proceedings of the 2020 IISE Annual Conference

A2 - Cromarty, L.

A2 - Shirwaiker, R.

A2 - Wang, P.

PB - Institute of Industrial and Systems Engineers, IISE

T2 - 2020 Institute of Industrial and Systems Engineers Annual Conference and Expo, IISE 2020

Y2 - 1 November 2020 through 3 November 2020

ER -

Anomaly detection in sequential health care data using higher-order network representation

Abstract

Publication series

Conference

Funding

Keywords

Other files and links

Fingerprint

Cite this