Skip main navigation
We use cookies to give you a better experience, if that’s ok you can close this message and carry on browsing. For more info read our cookies policy.
We use cookies to give you a better experience. Carry on browsing if you're happy with this, or read our cookies policy for more information.

Opportunities for process mining in healthcare

In the previous week we presented several of the challenges in healthcare processes. Another challenge is that healthcare processes are only partly structured. Even though clinical guidelines exist, in most healthcare processes medical staff deviate from these guidelines in the interest of the patient. Furthermore, many exceptions and different stakeholders make healthcare processes complex and highly variable. At the same time, one of the main challenges is the personalization of healthcare: by analyzing data, healthcare can take several characteristics into account to adjust the process in order to increase effectiveness and efficiency.

Luckily, advances in IT and technology have improved the automated recording of data significantly. This results in healthcare IT systems containing much operational data that can be utilized to gain insights into day-to-day operations.

Process mining can provide several operational insights into healthcare processes:

  • Insights into process flows: e.g. what is the path that 80% of our patients follow? Especially since healthcare processes are partly structured with many exceptions, providing these insights helps to discover the ‘main’ process, and to detect deviations.
  • Checking the conformance of the data with set rules and regulations: e.g. do we perform activity A only after we performed test T? How many cases comply with our clinical guideline?
  • Insights into the performance and waiting times in processes: e.g. between which activities do patients wait the longest in a given process?
  • How resources work within a process: e.g. when are certain resources active, or which resources often hand over work between them?

Process mining as such connects data science (data mining, machine learning, statistics, and interactive visualization) with business process management (the design, modelling, execution, monitoring, optimization, and re-engineering of business processes).

Process mining bridges data science and BPM Image taken from the book Process Mining in Healthcare: Evaluating and Exploiting Operational Healthcare Processes

In general process mining can help answer four types of questions:

  1. What happened?
  2. Why did it happen?
  3. What will happen?
  4. What is the best that can happen?

And although question four is the most interesting and impactful question to get an answer to, it is also the most difficult question to answer. In this course we will mainly focus on questions in the ‘what happened’ category, and touch on the ‘why did it happen’ type of question. The ‘what will happen’ and ‘what is the best that can happen’ are rather difficult questions for which no generic approach currently exists.

However, we strongly believe that by providing insights into what happened in the past, the future can be better managed.

Share this article:

This article is from the free online course:

Process Mining in Healthcare

Eindhoven University of Technology

Get a taste of this course

Find out what this course is like by previewing some of the course steps before you join:

Contact FutureLearn for Support