Health Innovation Lab: Bridging Medicine and Machine Learning

To bridge the gap between clinical practice and computational research, the Health Innovation Lab offers an interdisciplinary, project-based seminar bringing together advanced students from medicine and computer science. Designed to simulate authentic collaboration between clinical experts and machine learning researchers, the course guides interdisciplinary teams in developing AI-driven prototypes for real-world medical challenges.

Course Objectives & Core Learning Goals

The seminar addresses the distinct needs of both disciplines to build effective cross-field communication skills:

• For Medical Students: Learn to translate clinical challenges into computationally solvable questions, build practical data literacy, understand core machine learning principles, and critically evaluate AI outputs regarding clinical, regulatory, and ethical standards.
• For Computer Science Students: Gain hands-on experience handling complex medical datasets, implement tailored ML models designed for non-expert end-users, and navigate data privacy, interpretability, and healthcare regulation.

Seminar Structure & Key Phases

The course runs throughout the semester and combines structured instruction with self-organized group work:

• Interactive Preparatory Phase (Oct 19–23, 2026): Methodological workshops covering ML foundations, data programming in Python, and AI ethics in medicine.
• Project Exploration: Joint team formation where medical and CS students co-design feasible research goals using structured project cards.
• Iterative Project Development: Guided prototype creation featuring dedicated faculty supervision, data preparation, and model development.
• Milestones & Synthesis: Interim progress reviews, final project presentations, and a critical reflection on interdisciplinary teamwork.

Participation & Prerequisites

To ensure intensive, high-quality supervision and effective team dynamics, enrollment is capped at 20 participants (10 per discipline). The following prerequisites are expected:

• Medical Students: Completed preclinical studies and at least one clinical clerkship (Famulatur)
• Computer Science / ML / Medinf / Bioinf Students: Python proficiency and foundational experience in implementing ML algorithms.

Interested in participating or collaborating?

Students are invited to review the schedule and apply early on ALMA or SIMED respectively. Researchers interested in learning more about the lab’s teaching methodology or project outcomes are welcome to reach out to the course organizers.

_{Graphic AI generated}