Background: The rising level of laboratory automation provides an increasing number of logged events that can be used for the characterization of laboratory performance and process improvements. This abundance of data is often underutilized for improving laboratory efficiency.
Objectives: The first aim of this descriptive study is to provide a structured approach for transforming raw laboratory data to data that is suitable for process mining. The second aim is to describe a process mining approach for mapping and characterizing the sample flow in a clinical chemistry laboratory to identify areas for improvement in the testing process.
Methods: Data were extracted from instrument log files and the middleware between laboratory instruments and information technology infrastructure. Process mining was used for automated process discovery and analysis. Laboratory performance was quantified in terms of relevant key performance indicators (KPIs): turnaround time, timeliness, workload, work-in-process, and machine downtime.
Results: The method was applied to two Dutch university hospital clinical chemistry laboratories. We identified areas where alternative routes might increase laboratory efficiency and observed the negative effects of machine downtime on laboratory performance. This encourages the laboratory to review sample routes in its analyzer lines, the routes of high priority samples during instrument downtime, as well as the preventive maintenance policy.
Conclusion: This article provides the first application of process mining to event data from a medical diagnostic laboratory for automated process model discovery. Our study shows that process mining, with the use of relevant KPIs, provides valuable insights for laboratories that motivates the disclosure and increased utilization of laboratory event data, which in turn drive the analytical staff to intervene in the process to achieve the set performance goals. Our approach is vendor independent and widely applicable for all medical diagnostic laboratories.
The Author(s). This is an open access article published by Thieme under the terms of the Creative Commons Attribution License, permitting unrestricted use, distribution, and reproduction so long as the original work is properly cited. (https://creativecommons.org/licenses/by/4.0/).