Back to selection
80652-01 - Lecture with internship: Machine Learning for Healthcare (3 CP)
| Semester | fall semester 2026 |
| Course frequency | Every fall sem. |
| Lecturers |
Paul Fischer (paul.fischer@unibas.ch)
Ece Özkan Elsen (ece.oezkanelsen@unibas.ch, Assessor) Simon Pezold (simon.pezold@unibas.ch) |
| Content | This course introduces core and advanced machine learning methods for healthcare applications. Students learn to work with diverse medical data (e.g. EHR or imaging) and apply techniques such as supervised and unsupervised learning, deep learning, transfer and causal models, and generative models. The course emphasizes trust, safety, and ethics, covering interpretability, fairness, privacy, and regulatory. Through case studies and discussions, students develop both technical understanding and critical insight into how machine learning can be applied responsibly in clinical and biomedical settings. |
| Learning objectives | - Apply core and advanced machine learning methods (supervised and unsupervised learning, deep learning, transfer learning, causal models, generative models) to healthcare problems - Work with diverse medical data types, including electronic health records and medical imaging - Select and adapt appropriate methods for different clinical and biomedical contexts - Understand the principles of trustworthy and responsible AI in healthcare, including interpretability, fairness, and privacy - Navigate relevant regulatory considerations for machine learning in clinical settings - Critically evaluate the applicability and limitations of ML solutions in clinical and biomedical contexts - Reflect on the ethical implications of deploying machine learning in healthcare |
| Admission requirements | 53822 - Deep Learning for Medical Image Analysis |
| Language of instruction | English |
| Use of digital media | No specific media used |
| Interval | Weekday | Time | Room |
|---|---|---|---|
| wöchentlich | Thursday | 13.15-15.00 | Hegenheimermattweg 167B, Teaching Laboratory 02.098 |
| wöchentlich | Friday | 13.15-14.00 | Hegenheimermattweg 167B, Lecture Hall 02. 097 |
Dates
| Modules |
Module: Computer- and Robot-Assisted Medicine (Master's Studies: Biomedical Engineering) |
| Assessment format | record of achievement |
| Assessment details | Students complete two graded projects in groups of 2–3, applying machine learning methods to real healthcare datasets. Successful completion of both projects is required to be eligible for the final exam. |
| Assessment registration/deregistration | Reg.: course registration, dereg: cancel course registration |
| Repeat examination | one repetition, best attempt counts |
| Scale | 1-6 0,1 |
| Repeated registration | as often as necessary |
| Responsible faculty | Faculty of Medicine |
| Offered by | Departement Biomedical Engineering (DBE) |