This is an old revision of the document!


Philips Flagship

Description

The Data Science Centre Eindhoven (DSC/e) is TU/e’s response to the growing volume and importance of data and the need for data & process scientists (http://www.tue.nl/dsce/). The DSC/e has recently started a long-term strategic cooperation with Philips Research Eindhoven on three topics: data science, health and lighting. As a first concrete action, 70 PhD students are being hired for these three topics using joint funding from the TU/e and Philips, of which 18 PhD students work on the data science topic. These students form together with researchers from the TU/e and Philips a strong research community working together on scientific and industrial challenges.

The following four PhD positions will be related to the topic of process mining:

  1. Product-centric Consumer Data Analytics: Product Usage Lifecycle Analysis [part of the Data Driven Value Proposition theme]. Digital components are being added to Philips lifestyle products. The data from these products as well as from Philips touch points must be combined to optimize user experience and maintain customer satisfaction. Process mining techniques will be used to analyze the usage of products over a longer period of time.
  2. Transforming Event Data into Predictive Models [part of the Healthcare Smart Maintenance theme]. Philips has strong leadership positions in healthcare imaging and patient monitoring systems. In the healthcare domain, reducing equipment downtime and cost of ownership for hospitals is of vital importance. Smart maintenance exploits that professional equipment is connected to the internet and aims to use event and sensor data for overall cost reduction. Process mining techniques will be used to learn dynamic models that can be used for prediction and optimization.
  3. Predictive Analytics for Healthcare Workflows [part of the Optimizing Healthcare Workflows theme]. Processes play an important role in pathology and radiology. It is not just about collecting data and supporting individual activities, but also about improving the underlying end-to-end workflow processes. To improve these operational processes in terms of costs, efficiency, speed, reliability, and conformance, we can learn from the way that processes are conducted in practice. One can learn from problems in the past and compare different process variants and process instances. This project aims to obtain insight in these workflows, in order to understand what goes well and what can be improved, using a process mining approach. The cross-fertilization between process mining and visualization will provide a novel angle on workflow improvements in pathology and radiology.
  4. Radiology Workflow Optimization and Orchestration [also part of the Optimizing Healthcare Workflows theme]. Radiology, involves complex workflows, especially when seen in its clinical context. This project aims to obtain insight in these workflows and their visualization, in order to understand what goes well and what can be improved, using a visual analytics approach, where automated processing and interactive exploration are tightly integrated.

Optimization of patient care at reduced cost requires the orchestration of multiple clinical workflows. Timely getting the imaging/lab tests done and getting the results back to physicians can help quickly diagnose/treat the patient, and save lives. The rapid digitization of diagnostics in radiology and pathology calls for a data-driven optimization of the workflows. Process mining will be used to learn models for the as-is situation. However, process technology will also be used to improve the processes.

Staff involved