Mapping the Flow of Pediatric Trauma Patients Using Process Mining

BACKGROUND 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 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 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 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 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.

[1]  E. Mackenzie,et al.  Trauma system structure and viability in the current healthcare environment: a state-by-state assessment. , 2005, The Journal of trauma.

[2]  Patricia C. Dykes,et al.  The Current Capabilities of Health Information Technology to Support Care Transitions , 2013, AMIA.

[3]  A. J. M. M. Weijters,et al.  Flexible Heuristics Miner (FHM) , 2011, 2011 IEEE Symposium on Computational Intelligence and Data Mining (CIDM).

[4]  Lawrence T. Post,et al.  American College of Surgeons , 2020, Definitions.

[5]  R. Hall,et al.  Patient flow : reducing delay in healthcare delivery , 2006 .

[6]  Wil M. P. van der Aalst,et al.  Process Mining , 2016, Springer Berlin Heidelberg.

[7]  Boudewijn F. van Dongen,et al.  Conformance Checking Using Cost-Based Fitness Analysis , 2011, 2011 IEEE 15th International Enterprise Distributed Object Computing Conference.

[8]  D. Andrusiek,et al.  Process Mapping of a Regional Trauma System , 2013 .

[9]  Wil M. P. van der Aalst,et al.  Conformance checking of processes based on monitoring real behavior , 2008, Inf. Syst..

[10]  Boudewijn F. van Dongen,et al.  On the Role of Fitness, Precision, Generalization and Simplicity in Process Discovery , 2012, OTM Conferences.

[11]  R. Ramaiah,et al.  Initial assessment and management of pediatric trauma patients , 2012, International journal of critical illness and injury science.

[12]  J. Sherck,et al.  The efficacy of a two-tiered trauma activation system at a level I trauma center. , 2009, The Journal of trauma.

[13]  C. Schulman,et al.  Lost information during the handover of critically injured trauma patients: a mixed-methods study , 2015, BMJ Quality & Safety.

[14]  Boudewijn F. van Dongen,et al.  ProM 6: The Process Mining Toolkit , 2010, BPM.

[15]  Wil M. P. van der Aalst,et al.  Process mining: discovering and improving Spaghetti and Lasagna processes , 2011, CIDM 2011.

[16]  Boudewijn F. van Dongen,et al.  Replaying history on process models for conformance checking and performance analysis , 2012, WIREs Data Mining Knowl. Discov..

[17]  Jörg Desel,et al.  ''What Is a Petri Net?'' , 2001, Unifying Petri Nets.

[18]  Régis Beuscart,et al.  Graphical representation of the comprehensive patient flow through the Hospital , 2007, AMIA.

[19]  D. Chou.  Health IT and Patient Safety: Building Safer Systems for Better Care , 2012 .

[20]  Bart Baesens,et al.  A multi-dimensional quality assessment of state-of-the-art process discovery algorithms using real-life event logs , 2012, Inf. Syst..

[21]  M. Reed,et al.  The effect of introducing a Trauma Network on patient flow, hospital finances and trainee operating. , 2015, Injury.

[22]  Wil M. P. van der Aalst.  Process Mining: The Missing Link , 2016 .

[23]  Randolph W. Hall,et al.  Modeling Patient Flows Through the Health care System , 2013 .

[24]  S. Sharar.  The ongoing and worldwide challenge of pediatric trauma , 2012, International journal of critical illness and injury science.

[25]  L. Lind,et al.  A systematic review of triage-related interventions to improve patient flow in emergency departments , 2011, Scandinavian journal of trauma, resuscitation and emergency medicine.

[26]  F. Debus,et al.  TraumaNetzwerk DGU(®): optimizing patient flow and management. , 2014, Injury.

[27]  Karthik Devarajan,et al.  Minimizing ED Waiting Times and Improving Patient Flow and Experience of Care , 2014, Emergency medicine international.

[28]  Wil M. P. van der Aalst,et al.  Process mining and visual analytics: Breathing life into business process models , 2011 .

[29]  Wil M. P. van der Aalst,et al.  Conformance Testing: Measuring the Fit and Appropriateness of Event Logs and Process Models , 2005, Business Process Management Workshops.

[30]  Rebecca Mitchell,et al.  How is care provided for patients with paediatric trauma and their families in Australia? A mixed‐method study , 2016, Journal of paediatrics and child health.

[31]  Moe Thandar Wynn,et al.  Measuring Patient Flow Variations: A Cross-Organisational Process Mining Approach , 2014, AP-BPM.

[32]  E. Lerner,et al.  A Systematic Review of Hospital Trauma Team Activation Criteria for Children , 2017, Pediatric emergency care.

[33]  Jianhua Liu,et al.  Toward a Fully De-identified Biomedical Information Warehouse , 2009, AMIA.

[34]  Emmanuel Helm,et al.  From IHE Audit Trails to XES Event Logs Facilitating Process Mining , 2015, MIE.

[35]  Hartmut Ehrig,et al.  Unifying Petri Nets , 2001, Lecture Notes in Computer Science.

[36]  A. Kolker.  Interdependency of Hospital Departments and Hospital-Wide Patient Flows , 2013 .

[37]  S. Krug,et al.  Management of Pediatric Trauma , 2008, Pediatrics.

[38]  Rahul C. Basole,et al.  Exploring Clinical Care Processes Using Visual and Data Analytics : Challenges and Opportunities , 2014 .

[39]  Moe Thandar Wynn,et al.  Process Mining for Clinical Processes , 2015, ACM Trans. Manag. Inf. Syst..

[40]  M. Lacher,et al.  Maximizing the sensitivity and specificity of pediatric trauma team activation criteria. , 2000, Academic emergency medicine : official journal of the Society for Academic Emergency Medicine.

[41]  P. Carayon,et al.  Work system design for patient safety: the SEIPS model , 2006, Quality and Safety in Health Care.

[42]  Douglas A Wiegmann,et al.  Flow disruptions in trauma care handoffs. , 2013, The Journal of surgical research.

[43]  Kristan Staudenmayer,et al.  The cost of overtriage: more than one-third of low-risk injured patients were taken to major trauma centers. , 2013, Health affairs.

[44]  Joseph L. Wright,et al.  Handoffs: Transitions of Care for Children in the Emergency Department , 2016, Pediatrics.

[45]  Seppe K. L. M. vanden Broucke,et al.  A guide for the application of analytics on healthcare processes: A dynamic view on patient pathways , 2016, Comput. Biol. Medicine.

[46]  A. Presson,et al.  Preventable pediatric intensive care unit admissions over a 13-year period at a level 1 pediatric trauma center. , 2016, Journal of pediatric surgery.