Improving Pattern Detection in Healthcare Process Mining Using an Interval-Based Event Selection Method

Clinical pathways are highly variable and although many patients may follow similar pathway each individual will experience a unique set of events, for example with multiple repeated activities or varied sequences of activities. Process mining techniques are able to discover generalizable pathways based on data mining of event logs but using process mining techniques on a raw clinical pathway data to discover underlying healthcare processes is challenging due to this high variability. This paper involves two main contributions to healthcare process mining. The first contribution is developing a novel approach for event selection and outlier removing in order to improve pattern detection and thus representational quality. The second contribution is to demonstrate a new open access medical dataset, the MIMIC-III (Medical Information Mart for Intensive Care) database, which has not been used in process mining publications.

[1]  Seppe K. L. M. vanden Broucke,et al.  Advances in Process Mining: Artificial negative events and othertechniques , 2014 .

[2]  Moe Thandar Wynn,et al.  Event log imperfection patterns for process mining: Towards a systematic approach to cleaning event logs , 2017, Inf. Syst..

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

[4]  Luís Filipe Nascimento da Silva.  Process Mining: Application to a Case Study , 2014 .

[5]  Peter Szolovits,et al.  MIMIC-III, a freely accessible critical care database , 2016, Scientific Data.

[6]  David C. Hogg,et al.  The assessment of data quality issues for process mining in healthcare using Medical Information Mart for Intensive Care III, a freely available e-health record database , 2018, Health Informatics J..

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

[8]  Boudewijn F. van Dongen,et al.  The ProM Framework: A New Era in Process Mining Tool Support , 2005, ICATPN.

[9]  Manuel Mucientes,et al.  Mining Duplicate Tasks from Discovered Processes , 2015, ATAED@Petri Nets/ACSD.

[10]  Boudewijn F. van Dongen,et al.  Process mining: a two-step approach to balance between underfitting and overfitting , 2008, Software & Systems Modeling.

[11]  A. H. M. T. Hofstedea,et al.  Event log imperfection patterns for process mining : Towards a systematic approach to cleaning event logs , 2016 .

[12]  Ricardo Seguel,et al.  Process Mining Manifesto , 2011, Business Process Management Workshops.

[13]  Boudewijn F. van Dongen,et al.  Measuring precision of modeled behavior , 2015, Inf. Syst. E Bus. Manag..

[14]  Dirk Fahland,et al.  Handling Duplicated Tasks in Process Discovery by Refining Event Labels , 2016, BPM.

[15]  Chunhua Weng,et al.  Methods and dimensions of electronic health record data quality assessment: enabling reuse for clinical research , 2013, J. Am. Medical Informatics Assoc..

[16]  Jordi Cortadella,et al.  Discovering Duplicate Tasks in Transition Systems for the Simplification of Process Models , 2016, BPM.