Towards Process Mining of EMR Data - Case Study for Sepsis Management

Imagine you have cold shivers and a racing heartbeat and high fever. Clear thinking is impossible! Ceiling lights flash by as you are rushed to the emergency department (ED). You feel your body is getting even sicker. Doctors are doing their utmost to treat this acute and threatening condition, while they work piece together all small parts of evidence to set the diagnosis and start targeted treatment. In this situation, the clinical staff depends on a clinical pathway protocol to streamline communication and deliver care according to the latest medical evidence. Today, such clinical pathways are mainly executed and tracked using paper. Hence, there is ample opportunity for technology in a supportive role. Automated process analysis can help improve these processes of delivering standardized care beyond their current level. In this paper, we provide insight into the steps required to perform process mining to EMR data in the challenging domain of sepsis treatment and provide learnings from our preliminary analysis of these data using process mining techniques.

[1]  J. Lord,et al.  The systemic immune response to trauma: an overview of pathophysiology and treatment , 2014, The Lancet.

[2]  Wil M. P. van der Aalst,et al.  Wanna improve process mining results? , 2013, 2013 IEEE Symposium on Computational Intelligence and Data Mining (CIDM).

[3]  M. Levy,et al.  Surviving Sepsis Campaign: International guidelines for management of severe sepsis and septic shock: 2008 , 2007, Intensive Care Medicine.

[4]  Ruy Guilherme Rodrigues Cal,et al.  Brazilian Sepsis Epidemiological Study (BASES study) , 2004, Critical care.

[5]  Wil M. P. van der Aalst,et al.  Process Mining - Discovery, Conformance and Enhancement of Business Processes , 2011 .

[6]  Boudewijn F. van Dongen,et al.  Process Mining Based on Clustering: A Quest for Precision , 2007, Business Process Management Workshops.

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

[8]  Mitchell M. Levy,et al.  Surviving Sepsis Campaign guidelines for management of severe sepsis and septic shock , 2004, Critical care medicine.

[9]  Jorge Munoz-Gama,et al.  Process mining in healthcare: A literature review , 2016, J. Biomed. Informatics.

[10]  C. Torio,et al.  National Inpatient Hospital Costs: The Most Expensive Conditions by Payer, 2011 , 2013 .

[11]  J. Vincent,et al.  Surviving sepsis campaign guidelines , 2006 .

[12]  G. Martin,et al.  The Changing Epidemiology and Definitions of Sepsis. , 2016, Clinics in chest medicine.

[13]  Vladimiro Sassone,et al.  Petri Nets and Other Models of Concurrency , 1996, Petri Nets.

[14]  Wil M. P. van der Aalst,et al.  Process Mining Techniques: an Application to Stroke Care , 2008, MIE.

[15]  Adil Rafiq Rather,et al.  The Third International Consensus Definitions for Sepsis and Septic Shock (Sepsis-3) , 2015 .

[16]  Boudewijn F. van Dongen,et al.  ProM 4.0: Comprehensive Support for Real Process Analysis , 2007, ICATPN.

[17]  Hajo A. Reijers,et al.  Decision Mining Revisited - Discovering Overlapping Rules , 2016, CAiSE.

[18]  W. Knaus,et al.  Definitions for sepsis and organ failure and guidelines for the use of innovative therapies in sepsis. The ACCP/SCCM Consensus Conference Committee. American College of Chest Physicians/Society of Critical Care Medicine. , 1992, Chest.

[19]  A. James,et al.  A Process Mining Driven Framework for Clinical Guideline Improvement in Critical Care , 2011 .

[20]  E F Furstman,et al.  In Focus , 2016, Journal - Southern California Dental Association.

[21]  S. Rafnsson,et al.  Assessing available information on the burden of sepsis: global estimates of incidence, prevalence and mortality , 2012, Journal of global health.