Job Detail

Healthcare Xplorers is a new way and platform to foster academic collaborations in the space of data. The focus is on real challenges from Roche business areas where data plays a crucial role, and where new perspectives from academia complement our industry perspective. Fresh thinking is key to develop new solutions – and this is where you as a student or PhD come in. Do you love data? Are you an out-of-the-box thinker? Then join us to make a change!

Question to be solved

How can we represent real world population-level oncology data and events in a medically meaningful way to enable patient care optimization?

General Background

Patient pathways provide a population-level view on how cancer patients are treated in the real clinical practice. Health care professionals can learn from these pathways how current clinical care is organized leading to improved patients’ outcomes. However, each patient undergoes their own history of diagnosis, testing and treatment cycles. This makes it very difficult to summarize population-level treatment histories in a clinically meaningful way. One way to visually represent this patient-level summary is to use directed networks where nodes represent events in the medical cancer history. Here we are proposing to study how these nodes can be clustered together in single activities and how to obtain clinically meaningful activities out of real-world oncology data. We then can use this technique to generate patient pathways with zoom-in features where high-level and more detailed views of the data are presented to the user.

Data Types & Technologies

• We use real world oncology data


• Techniques from process mining can be a starting point to cluster meaningful nodes


• Part of the project will also be to implement a visualization of the node features in the pathways


• The project can be done in R or python, a prototype dashboard is served in Rshiny

Supporting Material or Links

These papers shall only serve as a starting point for the project but should not narrow down your own literature search nor your suggested ideas

• Günther and Fuzzy Mining – Adaptive Process Simplification Based on Multi-Perspective Metrics. citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.81.1207&rep=rep1&type=pdf


• Van Zelst et al. Event abstraction in process mining: literature review and 2020: link.springer.com/article/10.1007/s41066-020-00226-2


• Huang et al. Probabilistic modeling personalized treatment pathways using electronic health records. doi.org/10.1016/j.jbi.2018.08.004.


• Huang et al. Predictive modeling of clinical pathways. doi.org/10.1016/j.eswa.2016.02.052

Needed Skills

• good analytical/mathematical thinking


• preferable process mining knowledge


• programming skills (R and/or python, Rshiny)


• Interest in Real World Data


• At least on Master student level in quantitative science like computational biology, mathematics, statistics

Mentors

Celia Bel
Senior Data Scientist, Roche Information Solutions
LinkedIn Profile

Dr. Carsten Magnus
Principle Data Scientist, Roche Information Solutions
LinkedIn Profile

Form of Cooperation

• Preferred option: 6 months full-time internship


• Possible options: Full-time internship, with potential to develop into Master Thesis or part of PhD research project

How to present your Idea

Show us how you would approach the problem in 3 to 5 slides. We do not expect a bullet-proof solution to the problem. Be as creative as possible – Be aware you only have 10 minutes to sell your idea.

By sending this to us via the submit button you agree to the following:

• you confirm that you are the author of the submission and entitled to dispose of rights of use and exploitation of the contents of your submission, and that you have not yet granted any rights of use and exploitation to third parties that would be infringed by your submission;


• you grant to Roche Diagnostics GmbH the unrestricted, sublicensable and exclusive right  to use and exploit your submission by all means known today or in the future. This includes without limitation the rights to reproduce, distribute, and exhibit your submission, as well as the right to communicate your submission to the public. You also grant to Roche Diagnostics GmbH the right to edit the submission, to translate it, and to create abbreviations and summaries (abstracts); the aforesaid rights to use and exploit also apply to such edited versions, translations, abbreviations and summaries. 


• Roche Diagnostics GmbH will designate you as the author of the submission, and will recognize and respect your moral rights in the submission.


• The relationship you enter into by sending this via the submit button is governed by the laws of the Federal Republic of Germany, and the courts of Germany have international jurisdiction for any disputes arising under or in connection with this relationship.