In our Process Mining Café with Owen Johnson from the University of Leeds, we talked about his applications of process mining in healthcare.

Many interesting lessons emerged from this session, such as:

• Process thinking: Healthcare professionals deal with protocols and guidelines as checklists. As part of the process mining project, the process thinking needs to be developed to combat silos by bringing clinicians from different stages of the pathway together.

• Agile methodology: Owen books his time with all of the medical experts before the project starts. The process mining work then evolves in cycles until the next meeting for domain expert validation, deeper feedback, and finally the development of improvement ideas.

• Eighty-twenty-one percent rule: It makes sense to separate simple from complicated cases and to analyze them separately. Furthermore, the pathways of the last 1% of patients are really complex and you should remove them from the data. They are not appropriate for data analytics.

There are many more insights, such as why you should have a control cohort (also outside of healthcare), why it makes sense to model the process before mining it, and why it is good not to get the credit you deserve.

Watch the recording of the café here if you have missed it. A big thanks to Owen and to all of you for joining us!

Our apologies for the three audio cut-outs in the first five minutes of the session. We have added a text overlay of the questions that Anne asked Owen to the video version of the café, so that you can follow the discussion.

Links

Here are the links that we mentioned during the session:

• Williams, S., Southall, C., Haley, S., Dhafari, T.B., Kemp, S., Relton, S.D., Alty, J.E., Johnson, O., Graham, C.D. and Maguire, M. (2022), To the emergency room and back again: Circular healthcare pathways for acute functional neurological disorders. Journal of the Neurological Sciences, 437, p.120251.

• Johnson, OA, Ba Dhafari, T, Kurniati, A et al. (2019), The ClearPath Method for Care Pathway Process Mining and Simulation. In: Lecture Notes in Business Information Processing. BPM 2018: Business Process Management Workshops, 09-14 Sep 2018, Sydney, Australia. Springer, pp. 239-250. ISBN 9783030116408

• Martin, N., De Weerdt, J., Fernández-Llatas, C., Gal, A., Gatta, R., Ibáñez, G., Johnson, O., Mannhardt, F., Marco-Ruiz, L., Mertens, S. and Munoz-Gama, J., 2020. Recommendations for enhancing the usability and understandability of process mining in healthcare. Artificial Intelligence in Medicine, 109, p.101962.

• Munoz-Gama, J., Martin, N., Fernandez-Llatas, C., Johnson, O.A., Sepúlveda, M., Helm, E., Galvez-Yanjari, V., Rojas, E., Martinez-Millana, A., Aloini, D. and Amantea, I.A., 2022. Process mining for healthcare: Characteristics and challenges. Journal of Biomedical Informatics, 127, p.103994.

• Van Eck, M.L., Lu, X., Leemans, S.J. and Van Der Aalst, W.M. (2015), PM2: A process mining project methodology. In: International conference on advanced information systems engineering (pp. 297-313).

• Our 12-step process mining methodology

• Differences between ClearPath and PM2 methodology

• Process Mining Café on common preprocessing tasks with Xixi Lu

• Process Mining Café about data quality with Kanika Goel and Niels Martin

• Process Mining Café about simulation with Lambros Viennas and Sudhendu Rai

• Process Mining Café about the explorative analysis phase

• Collection of process mining applications in healthcare

• Previous Process Mining Café on healthcare with Luise Pufahl and Fran Batchelor

Contact us anytime at cafe@fluxicon.com if you have questions or suggestions about the café.

Have you seen that the Process Mining Café is also available as a podcast? So, if you prefer to listen to our episodes in your favorite podcast player, you can get them all here.

Sign up for our café mailing list and the YouTube playlist, follow Fluxicon on LinkedIn, or add the café calendar to never miss a Process Mining Café in the future.

We see this frequent mistake people make when they analyze bottlenecks: They look at the average delays in the process. The problem with that is that some of the discovered process paths can be quite low-frequent. So, you run the risk of focusing on an area in the process that will not have a big impact when you improve it.

In this 3-minute video, we demonstrate how to alleviate this problem by combining the total duration with another metric, such as the mean duration, as a secondary metric in Disco.

Process mining is an exciting application area for healthcare processes. At the same time, healthcare processes often present some challenges, for example, in terms of data quality and complexity.

For the upcoming Process Mining Café this Wednesday, we have invited Owen Johnson from the University of Leeds. At a UK hospital, they employed medical students to construct an event log of Functional Neurological Syndrome (FNS) patients by following the paper trail of each patient. The discovered process map illustrated quite how often these patients were misdiagnosed and sent around.

They also developed a process mining methodology specifically for healthcare processes. We’ll discuss how this methodology differs from the classical PM2 and our 12-step process mining methodology. The session will be essential for anyone applying process mining in healthcare, but also inspiring and informative for people outside of the healthcare domain. Join us all!

The café takes place this Wednesday, 17 September, at 15:00 CEST (Check your timezone here). As always, you don’t need to register. Point your browser to fluxicon.com/cafe when it is time.

Sign up for the café mailing list here to receive a reminder one hour before the session starts. Or add the time to your calendar if you don’t want to miss it.

We are happy to announce the release of Disco 4.2.

Forged in the heatwaves of summer, this release is built to melt away any annoyances, and to rid us of all those nasty bugs that have been itching us out on the patio. With some topped-up security and even tighter performance and stability across the board, it’s got all the fixins and then some.

Thanks for lending a hand with all your feedback and your bug reports. Keep us posted and, as always, thank you for using Disco!

How to update

We recommend that you update to the latest version of Disco at your earliest convenience. Disco will automatically download and install this update the next time you run it, if you are connected to the internet¹.

If you prefer to install this update of Disco manually, you can download and run the latest installer packages from fluxicon.com/disco/download

Changes

• Process Map:
  • Improved performance and stability of graph layout.
  • Improved reliability of metrics generation.
• Excel Import:
  • Improved reliability and performance.
  • Security updates.
• Airlift: Improved reliability.
• Control Center: Improved hardware detection.
• Software Update:
  • Fixed a bug that could prevent manual updates in some situations.
  • Improved robustness of automatic updates.
• UI: Fixed a bug where some charts in the analysis view could not be navigated via keyboard input.
• Connectivity:
  • Improved resilience in degraded network conditions.
  • Security updates.
• Platform: Java update.

You can use anonymization to put people at ease. Process mining is not about monitoring employees but about improving the process. But when people are new to process mining, seeing their names in the data can make them uncomfortable and less likely to support you in your process mining project. Removing their names and replacing them with a generic placeholder can help you build trust.

It’s very easy to do. Watch this 4-minute video to learn how to anonymize the resource names in Disco.