Building Operational Profiles for Philips MRI Machines

41:23Recorded on 20 June 2019 at TU Eindhoven

Mark Pijnenburg(Philips Healthcare, Netherlands)

Carmen Bratosin(ESI, Netherlands)

Mark and Carmen applied process mining to understand how Philips' MRI machines are actually used by physicians in the field. The discovered usage patterns increase the test coverage based on real-life behavior for these machines.

Synopsis

Philips Healthcare is a global maker of many healthcare products, among which are imaging systems such as X-Ray, CT, Fluoroscopy and Magnetic Resonance Imaging (MRI) machines. ESI is an independent research organisation for high-tech embedded systems design and engineering.

Carmen Bratosin is a research fellow at ESI and Mark Pijnenburg is a Clinical Verification Lead at Philips Healthcare. Mark and Carmen showed how process mining can be used to analyze the system usage of an MRI machine. Understanding the actual usage patterns in the field is especially interesting to improve the system requirements and to increase the test coverage based on real-life behavior for these machines.

Preparing the data for process mining is not easy, because the logging produced by the MRI machines is only available on a technical log level used for debugging. Furthermore, each physician has their own preferences regarding the machine setup for certain exams, which adds to the complexity. They started by selecting the key activities in the technical log and then aligned them with the user interface elements. Finally, they matched the logged events with the steps described by the American College of Radiology to get them on the abstraction level that a radiology expert would understand. In this way, they were able to compare the actual usage of the MRI system with the expected (and designed) behavior.

Join us online for this year's camp!

This year's Process Mining Camp will take place online, from 15 to 24 June 2020Come join us for eight special days, and meet the global process mining community!

Find out more!

More from Process Mining Camp 2019

Process Mining Machine Recoveries to Reduce Downtime

Freerk Jilderda (ASML)

ASML is the leading developer of photolithography systems for the semiconductor industry. Freerk shows how he has used process mining to analyze and improve lithography system start and calibration sequences, resulting in higher system availability.

Process Mining as Enabler for Digital Transformations

Jozef Gruzman (Raiffeisen Bank International) and Claus Mitterlehner (Raiffeisen Bank International)

Jozef and Claus developed a standard approach for black-box process discoveries. Using process mining, they first explore and review the processes on their own and then dive deeper in the analysis with the subject matter experts.

Using Process Mining to Improve Conversational Interfaces

Zvi Topol (MuyVentive)

Zvi shows how process mining techniques can be leveraged to improve natural language interfaces by analyzing conversational data from chatbot interactions with customers.

Process Mining at PGGM

Bas van Beek (PGGM) and Frank Nobel (PGGM)

Bas and Frank Nobel made an impact with process mining at the Dutch pension provider PGGM. The process lies at the heart of most of their improvement initiatives and they are always a multi-disciplinary effort.

Process Mining and Simulation

Sudhendu Rai (AIG)

Sudhendu developed a ‘Process Wind Tunnel’ framework by combining process mining and simulation. Based on real-world data, discrete-event simulation optimization is used for improving insurance business processes within AIG.

Process Mining in Logistics

Boris Nikolov (Vanderlande)

Boris applied process mining in the area of logistic process automation. He validated and optimized test scenarios during some of the most critical phases of a project — acceptance testing and operational trials.

Process Mining Meets Football

Hadi Sotudeh (JADS)

Hadi brought his enthusiasm for football and his love for data together when he analyzed the 2018 World Cup data with process mining. He realized that the key to finding patterns is to make the right assumptions when preparing the data.

Responsible Data Science For Process Miners

Wil van der Aalst (RWTH Aachen)

The final speaker at Process Mining Camp 2019 was Wil van der Aalst, the founding father of process mining. In his closing keynote, Wil talked about responsible data Science for process miners.

Explore Process Mining Camp 2019

© 2020 by Fluxicon BV, all rights reserved.
You can read our privacy policy here.

Page created in 25.7 ms.