| Dozent/in |
Javier Montoya Dr. sc. ETH |
| Veranstaltungsart |
Vorlesung |
| Code |
HS251110 |
| Semester |
Herbstsemester 2025 |
| Durchführender Fachbereich |
Gesundheitswissenschaften |
| Studienstufe |
Bachelor
Master |
| Termin/e |
Do, 18.09.2025, 14:15 - 16:00 Uhr, E.508
Do, 25.09.2025, 14:15 - 16:00 Uhr, E.508
Do, 09.10.2025, 14:15 - 16:00 Uhr, E.508
Do, 16.10.2025, 14:15 - 16:00 Uhr, E.508
Do, 23.10.2025, 14:15 - 16:00 Uhr, E.508
Do, 30.10.2025, 14:15 - 16:00 Uhr, E.508
Do, 06.11.2025, 14:15 - 16:00 Uhr, E.508
Do, 13.11.2025, 14:15 - 16:00 Uhr, E.508
Do, 20.11.2025, 14:15 - 16:00 Uhr, E.508
Do, 27.11.2025, 14:15 - 16:00 Uhr, E.508
Do, 04.12.2025, 14:15 - 16:00 Uhr, E.508
Do, 11.12.2025, 14:15 - 16:00 Uhr, E.508
Do, 18.12.2025, 14:15 - 16:00 Uhr, E.508 |
| Weitere Daten |
This is an introductory course on applied Artificial Intelligence in Digital Health. |
| Umfang |
2 Semesterwochenstunden |
| Inhalt |
• Introduction to AI: Overview, course organization, and real-world motivations in digital health.
• Foundations of AI and Deep Learning: The learning pipeline, key models, and performance metrics.
• Introduction to Clinical Data: Data types, sources (e.g., radiology, lab reports), and structure.
• AI for Personalized Medicine: From segmentation to synthetic image generation.
• Supervised Learning: Regression and classification for diagnostic tasks.
• Unsupervised Learning: Clustering and dimensionality reduction in patient data.
• Self-Supervised Learning: Representation learning from unlabeled data.
• Neural Networks: Architecture, training, and optimization principles.
• Deep Learning: Advanced architectures and evaluation methods.
• Computer Vision in Medical Imaging: Data-driven applications for visual-based diagnose.
• Natural Language Processing in Healthcare: Reasoning from clinical texts.
• Trustworthy and Ethical AI: Interpretability, biases, and regulatory frameworks. |
| Schlagworte |
Nachhaltigkeit |
| Lernziele |
After completing the course, students will be able to:
• Understand and explain fundamental concepts and historical milestones of Artificial Intelligence (AI) and Deep Learning (DL).
• Identify core components of data-driven systems and describe their training, evaluation, and deployment processes.
• Explore different applications of AI in digital health, including medical imaging and clinical text analysis.
• Differentiate between supervised, unsupervised, self-supervised, and reinforcement learning methods.
• Interpret different types of clinical data and understand how they are used in AI-based decision-support systems.
• Evaluate the performance, limitations, and ethical considerations of AI models applied to medical contexts.
• Discuss current regulatory frameworks and societal implications of deploying AI in healthcare settings.
• Strengthen critical thinking and communication skills through case studies, group work, and project presentations. |
| Voraussetzungen |
While the different contents to be covered are self-contained and no prior technical background is required, commitment and openness to learn both
new technical concepts and tools will enhance the learning experience.
• Attendance and Engagement: regular attendance to the class and self-study are beneficial to successfully complete the course.
• Collaborative Learning: collaboration and exchange with peers through group discussions will help to improve the learning experience.
• Active Learning and Critical Thinking: Proactively learning and analyzing the applicability of data-driven systems together with their benefits, challenges, and limitations are important for succeeding in the course.
• No prior technical background is required, but a willingness to learn new concepts is essential. |
| Sprache |
Englisch |
| Anmeldung |
https://elearning.hsm-unilu.ch/course/edit.php?id=899 |
| Prüfung |
100% oral exam (1 randomly selected topic and 1 use case preparation in advance)
IMPORTANT: In order to earn credits and participate at the exam registration via Uni Portal within the exam registration period is MANDATORY. Further information: www.unilu.ch/en/study/courses-exams-regulations/health-sciences-and-medicine/exams/ |
| Abschlussform / Credits |
Oral exam / 3 Credits
|
| Hinweise |
Teaching methods:
The course combines lectures with practical, interactive, and student-centered methods to reinforce understanding:
• Lectures with visual slides and real-world examples.
• Group discussions and Q&A to encourage critical thinking.
• Guided case studies on AI applications in digital health.
• Guest lectures from clinicians. |
| Hörer-/innen |
Nein |
| Kontakt |
javier.montoya@doz.unilu.ch |
| Material |
The teaching material includes slide decks for each session, case studies and datasets relevant to AI in health (e.g., clinical text, medical images), short videos, visual illustrations, and infographics for intuitive learning. |
| Literatur |
The corresponding references and readings will be provided in digital form on the moodle e-learning platform. |