We want to improve the lives of patients.

Every day. Worldwide.

Our goal is to sustainably improve the lives of patients with chronic kidney failure – with data, algorithms and artificial intelligence.

As a global innovation unit of Fresenius Medical Care, we use access to a unique data pool. We are the only company that combines development, operation and application of dialysis machines under one roof, and provides access to comprehensive technical and medical data.

We develop innovative solutions for patients, doctors and clinics. To this end, we are making our dialysis machines more intelligent, aiming at making better therapies available to all people worldwide in the future.

Our Team

Dr. Matthias Kuss Dr. Matthias Kuss Leadership
Sabine Jesse Sabine Jesse Assistant
Sebastian Kehrlein Sebastian Kehrlein Director Portfolio Management
Aaron Pickering Aaron Pickering Director Data Science
Dr. Felix Brockherde Dr. Felix Brockherde Senior Data Scientist
Dr. Jamie Ye Dr. Jamie Ye Data Scientist
Lena Scherer Lena Scherer Master's degree candidate
Max Botler Max Botler Data Scientist
Nathan Warren Nathan Warren Data Scientist
Radomir Popovic Radomir Popovic Data Scientist


Dr. Matthias Kuss Leadership
Data Solutions is part of Global Research & Development at Fresenius Medical Care. We draw on a global network of excellent engineers and therapy developers and support them in making our devices even "smarter".
Sabine Jesse Assistant
My job combines freedom and responsibility in one. No two days are the same, so it never gets boring. Everyone gets the opportunity to develop, bring in their own ideas, gain experience and make decisions on their own.
Sebastian Kehrlein Director Portfolio Management
Our data-driven approach helps to optimize daily processes and ensure the best possible individual treatment. The intelligent networking of all essential components is the key to success.
Aaron Pickering Director Data Science
In data science there seems to have been a recent shift towards explainable and interpretable machine learning models. On a related note, causal inference also seems to be becoming more popular within the machine learning community. This trend is particularly applicable to the medical devices sector, where explainability is at a premium.
Dr. Felix Brockherde Senior Data Scientist
Firstly, we are analyzing the extent to which we can further individualize the therapy, for example, by making intelligent suggestions for therapy parameters to hospital staff or by using sensor data from previous therapies to detect thrombosis at an earlier stage. Secondly, we use sensor data to analyze the clinical process and thus make the therapy more comfortable for the patients.
Dr. Jamie Ye Data Scientist
We are initiating some cool AI projects to drive the dialysis industry forward. I like the way how team members collaborate. We share knowledges, experiences and support each other. Information is transparent within the team. Every team member is highly motivated and we move towards the same goals.
Lena Scherer Master's degree candidate
If you have lots of ideas about what tomorrow's medical care should look like and are interested in simply trying out new approaches, this is the right place for you. Especially the combination of hardware and data science, the continuous exchange and involvement of patients offer many possibilities to really change something and to think ahead.
Max Botler Data Scientist
The most important aspect is certainly that our work is directly aimed at the well-being of the patients. On the technical level, we work along the entire pipeline, from the first concepts to the implementation of finished products.
Nathan Warren Data Scientist
I enjoy being able to own my projects and know that I am creating solutions that work towards providing patients with better care. There is a tremendous amount of freedom, as we are encouraged to develop our own solutions, with the support of teammates.
Radomir Popovic Data Scientist
Some recent Natural Language Processing (NLP) advancements, which utilize Attention mechanism, seem to be quite powerful in wide range of other Machine Learning areas as well. As these models and algorithms get more sophisticated and accurate, I find interesting the challenge on how to optimally bridge the gap between them and the actual medical staff.