HPI Digital Health Cluster

Data Management for Digital Health

General Information

  • Teaching staff: Florian Borchert, Dr. Matthieu-P. Schapranow
  • Format: 4 Semesterwochenstunden (SWS) 6 ECTS (graded)
  • Schedule:
    • Tuesdays @ 11.00am (s.t.) on HPI Campus II, L-1.06.
    • Thursdays @ 01.30pm (s.t.) on HPI Campus II, L-1.06.
  • First course:
    • Tue Oct 17, 2023 @ 11.00am (s.t.) on HPI Campus II, L-1.06.


  • Tue Feb 13, 2024: Final exams will start  at 11.00am (s.t.) in HPI lecture hall 1; please be on site at least 15 min prior start.
  • Tue Feb 6, 2024: Review exercise 04 and join us our Q&A  and I like, I wish session.
  • Tue Jan 23, 2024: Review exercise 03 and exercise 04 released.
  • Tue Jan 9, 2024: Exercise 03 released.
  • Tue Dec 19, 2023: Review exercise 02.
  • Thu Dec 7, 2023: Room change, new room is H-2.57/2.58 on HPI campus I. 
  • Thu Nov 30, 2023: Review exercise 01 and exercise 02 released.
  • Tue Nov 20, 2023: Self-paced education in preparation of DNA building workshop taking place on Thu Nov 23, 2023.
  • CW46: Room change for Nov 14 and 16, 2023: new room is H-2.57/2.58 on HPI campus I. 
  • Tue Nov 9, 2023: Exercise 01 released.
  • Tue Oct 31, 2023: No lecture due to a bank holiday in Brandenburg state (Reformation Day).
  • Tue Oct 17, 2023: Lecture kickoff.
  • Tue Sep 19, 2023: Course webpage published.


Scope of the lecture

Welcome to the class: We are very excited that you are interested in learning more about the priciples of data management for digital health and why it might be different from what you have learnt so far. In this lecture, we and selected guest speakers will share with you:

  • Specific examples from selected fields of digital health to understand where and how data is/needs to be acquired,
  • Known challenges in acquiring and processing these types of data in their specific digital health domain,
  • How to deal with and address specific requirements and limitation of accessing and using digital health data,
  • and how the complex analysis of high-dimensional multi-modal digital health data can be facilitated through the use of latest soft- and hardware advances, e.g. clinical prediction models, federated learning infrastructures, large language models, and supervised as well as unsupervised machine learning approaches.

After participating in the course, you will be equipped with the ability to: 

  • Assess requirements of selected real-world use cases from the medical field (oncology, nephrology, infectious diseases),
  • Select latest technology building blocks to create viable healthcare software solutions, and
  • Analyze requirements for data analysis and processing, e.g. for machine learning (supervised and unsupervised learning, large language models and natural language processing, deep learning, federated learning infrastructures).

In the course, we will have invited guest speakers with medical background sharing their real-world experience with you in interactive presentations. Thus, you will have the chance to raise any questions you never dared to ask and discuss them together with us in the course of the lecture.

Further details about the structure of the lecture will be shared with you in the kickoff lecture (please check the date on the top of this page).


In the course of the lecture, you will have to conduct a small number of personal exercises to recap the presented lecture content. You have to pass all of these intermediate exercises prior to participate the final exam (Prüfungsvorleistung).

The final grading will be determined by the following parts:

  • Final exam at the end of the course (100%).