Mapping the Flow of Pediatric Trauma Patients Using Process Mining

Ashimiyu B. Durojaiye, Nicolette M. McGeorge, Lisa L. Puett, Fray Dylan Stewart, James C Fackler, Peter L.T. Hoonakker, Harold P Lehmann, Ayse Gurses

Research output: Contribution to journalArticle

Abstract

Background âInhospital pediatric trauma care typically spans multiple locations, which influences the use of resources, that could be improved by gaining a better understanding of the inhospital flow of patients and identifying opportunities for improvement. Objectives âTo describe a process mining approach for mapping the inhospital flow of pediatric trauma patients, to identify and characterize the major patient pathways and care transitions, and to identify opportunities for patient flow and triage improvement. Methods âFrom the trauma registry of a level I pediatric trauma center, data were extracted regarding the two highest trauma activation levels, Alpha (n = 228) and Bravo (n = 1,713). An event log was generated from the admission, discharge, and transfer data from which patient pathways and care transitions were identified and described. The Flexible Heuristics Miner algorithm was used to generate a process map for the cohort, and separate process maps for Alpha and Bravo encounters, which were assessed for conformance when fitness value was less than 0.950, with the identification and comparison of conforming and nonconforming encounters. Results âThe process map for the cohort was similar to a validated process map derived through qualitative methods. The process map for Bravo encounters had a relatively low fitness of 0.887, and 96 (5.6%) encounters were identified as nonconforming with characteristics comparable to Alpha encounters. In total, 28 patient pathways and 20 care transitions were identified. The top five patient pathways were traversed by 92.1% of patients, whereas the top five care transitions accounted for 87.5% of all care transitions. A larger-Than-expected number of discharges from the pediatric intensive care unit (PICU) were identified, with 84.2% involving discharge to home without the need for home care services. Conclusion âProcess mining was successfully applied to derive process maps from trauma registry data and to identify opportunities for trauma triage improvement and optimization of PICU use.

Original languageEnglish (US)
Pages (from-to)654-666
Number of pages13
JournalApplied Clinical Informatics
Volume9
Issue number3
DOIs
StatePublished - Jul 1 2018

Fingerprint

Patient Transfer
Pediatrics
tetrachloroisophthalonitrile
Wounds and Injuries
Intensive care units
Pediatric Intensive Care Units
Triage
Registries
Patient Care
Miners
Data transfer
Trauma Centers
Home Care Services
Chemical activation

Keywords

  • care transition
  • conformance checking
  • patient pathway
  • pediatric trauma
  • process mining
  • trauma registry

ASJC Scopus subject areas

  • Health Informatics
  • Computer Science Applications
  • Health Information Management

Cite this

Mapping the Flow of Pediatric Trauma Patients Using Process Mining. / Durojaiye, Ashimiyu B.; McGeorge, Nicolette M.; Puett, Lisa L.; Stewart, Fray Dylan; Fackler, James C; Hoonakker, Peter L.T.; Lehmann, Harold P; Gurses, Ayse.

In: Applied Clinical Informatics, Vol. 9, No. 3, 01.07.2018, p. 654-666.

Research output: Contribution to journalArticle

Durojaiye, Ashimiyu B. ; McGeorge, Nicolette M. ; Puett, Lisa L. ; Stewart, Fray Dylan ; Fackler, James C ; Hoonakker, Peter L.T. ; Lehmann, Harold P ; Gurses, Ayse. / Mapping the Flow of Pediatric Trauma Patients Using Process Mining. In: Applied Clinical Informatics. 2018 ; Vol. 9, No. 3. pp. 654-666.
@article{caba88264a6e43e3b01c3a921e29328e,
title = "Mapping the Flow of Pediatric Trauma Patients Using Process Mining",
abstract = "Background {\^a}Inhospital pediatric trauma care typically spans multiple locations, which influences the use of resources, that could be improved by gaining a better understanding of the inhospital flow of patients and identifying opportunities for improvement. Objectives {\^a}To describe a process mining approach for mapping the inhospital flow of pediatric trauma patients, to identify and characterize the major patient pathways and care transitions, and to identify opportunities for patient flow and triage improvement. Methods {\^a}From the trauma registry of a level I pediatric trauma center, data were extracted regarding the two highest trauma activation levels, Alpha (n = 228) and Bravo (n = 1,713). An event log was generated from the admission, discharge, and transfer data from which patient pathways and care transitions were identified and described. The Flexible Heuristics Miner algorithm was used to generate a process map for the cohort, and separate process maps for Alpha and Bravo encounters, which were assessed for conformance when fitness value was less than 0.950, with the identification and comparison of conforming and nonconforming encounters. Results {\^a}The process map for the cohort was similar to a validated process map derived through qualitative methods. The process map for Bravo encounters had a relatively low fitness of 0.887, and 96 (5.6{\%}) encounters were identified as nonconforming with characteristics comparable to Alpha encounters. In total, 28 patient pathways and 20 care transitions were identified. The top five patient pathways were traversed by 92.1{\%} of patients, whereas the top five care transitions accounted for 87.5{\%} of all care transitions. A larger-Than-expected number of discharges from the pediatric intensive care unit (PICU) were identified, with 84.2{\%} involving discharge to home without the need for home care services. Conclusion {\^a}Process mining was successfully applied to derive process maps from trauma registry data and to identify opportunities for trauma triage improvement and optimization of PICU use.",
keywords = "care transition, conformance checking, patient pathway, pediatric trauma, process mining, trauma registry",
author = "Durojaiye, {Ashimiyu B.} and McGeorge, {Nicolette M.} and Puett, {Lisa L.} and Stewart, {Fray Dylan} and Fackler, {James C} and Hoonakker, {Peter L.T.} and Lehmann, {Harold P} and Ayse Gurses",
year = "2018",
month = "7",
day = "1",
doi = "10.1055/s-0038-1668089",
language = "English (US)",
volume = "9",
pages = "654--666",
journal = "Applied Clinical Informatics",
issn = "1869-0327",
publisher = "Schattauer GmbH",
number = "3",

}

TY - JOUR

T1 - Mapping the Flow of Pediatric Trauma Patients Using Process Mining

AU - Durojaiye, Ashimiyu B.

AU - McGeorge, Nicolette M.

AU - Puett, Lisa L.

AU - Stewart, Fray Dylan

AU - Fackler, James C

AU - Hoonakker, Peter L.T.

AU - Lehmann, Harold P

AU - Gurses, Ayse

PY - 2018/7/1

Y1 - 2018/7/1

N2 - Background âInhospital pediatric trauma care typically spans multiple locations, which influences the use of resources, that could be improved by gaining a better understanding of the inhospital flow of patients and identifying opportunities for improvement. Objectives âTo describe a process mining approach for mapping the inhospital flow of pediatric trauma patients, to identify and characterize the major patient pathways and care transitions, and to identify opportunities for patient flow and triage improvement. Methods âFrom the trauma registry of a level I pediatric trauma center, data were extracted regarding the two highest trauma activation levels, Alpha (n = 228) and Bravo (n = 1,713). An event log was generated from the admission, discharge, and transfer data from which patient pathways and care transitions were identified and described. The Flexible Heuristics Miner algorithm was used to generate a process map for the cohort, and separate process maps for Alpha and Bravo encounters, which were assessed for conformance when fitness value was less than 0.950, with the identification and comparison of conforming and nonconforming encounters. Results âThe process map for the cohort was similar to a validated process map derived through qualitative methods. The process map for Bravo encounters had a relatively low fitness of 0.887, and 96 (5.6%) encounters were identified as nonconforming with characteristics comparable to Alpha encounters. In total, 28 patient pathways and 20 care transitions were identified. The top five patient pathways were traversed by 92.1% of patients, whereas the top five care transitions accounted for 87.5% of all care transitions. A larger-Than-expected number of discharges from the pediatric intensive care unit (PICU) were identified, with 84.2% involving discharge to home without the need for home care services. Conclusion âProcess mining was successfully applied to derive process maps from trauma registry data and to identify opportunities for trauma triage improvement and optimization of PICU use.

AB - Background âInhospital pediatric trauma care typically spans multiple locations, which influences the use of resources, that could be improved by gaining a better understanding of the inhospital flow of patients and identifying opportunities for improvement. Objectives âTo describe a process mining approach for mapping the inhospital flow of pediatric trauma patients, to identify and characterize the major patient pathways and care transitions, and to identify opportunities for patient flow and triage improvement. Methods âFrom the trauma registry of a level I pediatric trauma center, data were extracted regarding the two highest trauma activation levels, Alpha (n = 228) and Bravo (n = 1,713). An event log was generated from the admission, discharge, and transfer data from which patient pathways and care transitions were identified and described. The Flexible Heuristics Miner algorithm was used to generate a process map for the cohort, and separate process maps for Alpha and Bravo encounters, which were assessed for conformance when fitness value was less than 0.950, with the identification and comparison of conforming and nonconforming encounters. Results âThe process map for the cohort was similar to a validated process map derived through qualitative methods. The process map for Bravo encounters had a relatively low fitness of 0.887, and 96 (5.6%) encounters were identified as nonconforming with characteristics comparable to Alpha encounters. In total, 28 patient pathways and 20 care transitions were identified. The top five patient pathways were traversed by 92.1% of patients, whereas the top five care transitions accounted for 87.5% of all care transitions. A larger-Than-expected number of discharges from the pediatric intensive care unit (PICU) were identified, with 84.2% involving discharge to home without the need for home care services. Conclusion âProcess mining was successfully applied to derive process maps from trauma registry data and to identify opportunities for trauma triage improvement and optimization of PICU use.

KW - care transition

KW - conformance checking

KW - patient pathway

KW - pediatric trauma

KW - process mining

KW - trauma registry

UR - http://www.scopus.com/inward/record.url?scp=85052330751&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85052330751&partnerID=8YFLogxK

U2 - 10.1055/s-0038-1668089

DO - 10.1055/s-0038-1668089

M3 - Article

VL - 9

SP - 654

EP - 666

JO - Applied Clinical Informatics

JF - Applied Clinical Informatics

SN - 1869-0327

IS - 3

ER -