Abstract
Process mining techniques can provide insights into the healthcare domain with the rapid growth of electrical health records. Process mining is about understanding the sequence of activities in event logs, where directly-follows relations identify pairs of activities that follow each other directly. Existing research explores frequent relations, while infrequent relations are often seen as noises and filtered out during discovery. However, important insights may be revealed through these infrequent relations, especially in healthcare processes. This paper aims to use process mining techniques to discover and preserve value-based conditional infrequent relations. We adopt the L* life-cycle methodology and Data-aware Heuristic Miner (DHM) as tools to provide a worded example based on extracted data from the MIMIC-III dataset, which is a publicly available database containing a large amount of electrical health records (EHR), to show how process mining can be used to analyse infrequent relations in a laboratory test’s ordering process.
Recommended Citation
Chen, Qifan; Lu, Yang; Tam, Charmaine; and Poon, Simon, "Process Mining to Discover and Preserve Infrequent Relations in Event Logs: An Application to Understand the Laboratory Test Ordering Process Using the MIMIC-III Dataset" (2021). ACIS 2021 Proceedings. 30.
https://aisel.aisnet.org/acis2021/30