| Dozent/in |
Javier Montoya Dr. sc. ETH |
| Veranstaltungsart |
Vorlesung |
| Code |
HS241041 |
| Semester |
Herbstsemester 2024 |
| Durchführender Fachbereich |
Gesundheitswissenschaften |
| Studienstufe |
Bachelor |
| Termin/e |
Do, 19.09.2024, 14:15 - 16:00 Uhr, HS 15
Do, 26.09.2024, 14:15 - 16:00 Uhr, HS 15
Do, 03.10.2024, 14:15 - 16:00 Uhr, HS 15
Do, 10.10.2024, 14:15 - 16:00 Uhr, HS 15
Do, 17.10.2024, 14:15 - 16:00 Uhr, HS 15
Do, 24.10.2024, 14:15 - 16:00 Uhr, HS 15
Do, 31.10.2024, 14:15 - 16:00 Uhr, HS 15
Do, 07.11.2024, 14:15 - 16:00 Uhr, HS 2
Do, 14.11.2024, 14:15 - 16:00 Uhr, HS 15
Do, 21.11.2024, 14:15 - 16:00 Uhr, ZOOM
Do, 28.11.2024, 14:15 - 16:00 Uhr, HS 15
Do, 05.12.2024, 14:15 - 16:00 Uhr, HS 15
Do, 12.12.2024, 14:15 - 16:00 Uhr, HS 15
Do, 19.12.2024, 14:15 - 16:00 Uhr, HS 15 |
| Weitere Daten |
This is an introductory course on applied Artificial Intelligence in Digital Health. |
| Umfang |
2 Semesterwochenstunden |
| Inhalt |
• Introduction and Foundations of Artificial Intelligence and Deep Learning: what are the fundamental concepts associated to Artificial Intelligence/Deep Learning? • Applications of Artificial Intelligence in digital health: what are examples of applications of Artificial Intelligence in the medical field? • Supervised, Unsupervised, and Reinforcement Learning: what are the commontypes of Artificial Intelligence methods? • Introduction to Clinical Data: what are the different types of data available in clinical settings and how can they be used for diagnosis? • The Deep Learning Pipeline in Digital Health: what are the key building blocks of Artificial Intelligence systems and how do such systems are trained and evaluated? • Computer Vision in Medical Imaging: how can visual information be used to assist medical diagnosis in medical imaging? • Natural Language Processing in Healthcare: how can clinical text documents be used to obtain valuable medical insights? • Trustworthy Artificial Intelligence and Interpretability: what are the challenges and considerations aiming at trustworthy and interpretable Artificial Intelligence in Healthcare? • Ethical considerations and Regulations for Artificial Intelligence in Digital Healthwhat are the existing and emerging regulations and guidelines for using ArtificiaIntelligence in the context of Digital Health? • Future Perspectives and emerging trends in AI for digital healthcare: what are the current trends and future perspectives of applied AI in Digital Health? |
| Schlagworte |
Nachhaltigkeit |
| Lernziele |
After completing the course, students will be able to:
• Understand and describe the fundamental principles of Artificial Intelligence in the context of the medical field.
• Identify the different components of AI systems and how such systems are trained and evaluated on medical data.
• Gain familiarity with existing AI models relying on visual and/or text data intended for medical diagnosis.
• Analyze the regulations and ethical implications when developing AI systems for healthcare.
• Understand the different roles among professionals when implementing crossdomain AI projects for healthcare:healthcare
professionals, researchers, and data scientists.
• Evaluate critically the capabilities and limitations of AI models in digital health.
• Improve soft skills: presentation, communication, problem-solving, and teamwork. |
| Voraussetzungen |
• Attendance and Engagement: regular attendance to the class and self-study arebeneficial to successfully complete the course.
• Collaborative Learning: collaboration and exchange with peers through group discussions and joint projects will help to improve the learning experience.
• Active Learning and Critical Thinking: Proactively learning and analyzing the applicability of AI systems together with their benefits, challenges, and
limitations are important for succeeding in the course. |
| Sprache |
Englisch |
| Anmeldung |
https://elearning.hsm-unilu.ch/course/view.php?id=762
|
| Prüfung |
40% group project and 60% final online exam
(multiple choice, short answer, etc.) with open notes. |
| Abschlussform / Credits |
40% group project and 60% final written exam / 3 Credits
|
| Hinweise |
Teaching methods:
The teaching methods are based on lectures, interactive discussions, multimedia resources, case studies, group
project(s), and guest speaker. |
| Hörer-/innen |
Ja |
| Material |
The teaching material includes selected book chapters, research papers, online tutorials, and medical datasets.
moodle e-learning platform for class material and evaluation. |
| Literatur |
The corresponding references and readings will be provided in digital form on the moodle e-learning platform.
|