Process Mining and Conformance Checking of Long Running Processes in the Context of Melanoma Surveillance

Abstract

BACKGROUND: Process mining is a relatively new discipline that helps to discover and analyze actual process executions based on log data. In this paper we apply conformance checking techniques to the process of surveillance of melanoma patients. This process consists of recurring events with time constraints between the events. OBJECTIVES: The goal of this work is to show how existing clinical data collected during melanoma surveillance can be prepared and pre-processed to be reused for process mining. METHODS: We describe an approach based on time boxing to create process models from medical guidelines and the corresponding event logs from clinical data of patient visits. RESULTS: Event logs were extracted for 1023 patients starting melanoma surveillance at the Department of Dermatology at the Medical University of Vienna between January 2010 and June 2017. Conformance checking techniques available in the ProM framework and explorative applied process mining techniques were applied. CONCLUSIONS: The presented time boxing enables the direct use of existing process mining frameworks like ProM to perform process-oriented analysis also with respect to time constraints between events.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 24 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.