Inhalt

Abstract:

This course is designed for medical students who want to understand AI and for engineering students interested in applying AI to medicine. It combines technical foundations with clinical relevance, enabling students to understand how AI systems learn from data and how they can be evaluated and used responsibly in healthcare.
Throughout the course, students will learn core concepts in AI and machine learning, including how algorithms learn from data, how models are developed and evaluated, and how their performance and generalizability are assessed, while also exploring emerging areas of medical AI, such as AI in medical imaging, clinical decision support, precision medicine and large language models in medicine. They will explore major applications of AI in medicine and examine its current technical and clinical limitations, as well as important ethical, privacy, fairness, and regulatory considerations.
Understanding AI is also reinforced through learning-by-doing. The guided programming exercises allow students to gain practical experience with AI tools. These guided exercises, that are designed with minimal technical barriers, ensure that even students without programming expertise can engage in hands-on learning.

Gliederung:

01 Introduction to AI and Its Role in Medicine

02 Core Concepts of Machine Learning and Deep Learning

03 Neural Networks

04 AI in Medical Imaging

05 AI for Clinical Decision Support and Precision Medicine

06 Natural Language Processing and Large Language Models in Medicine

07 Ethics, Privacy, Fairness and Regulation of Medical AI

08 Introduction to Coding in Python

09 Build an AI Pipeline from Scratch

10 Detecting COVID-19 with AI

11 Brain Tumor Classification

12 Evaluating Medical AI Literature

13 Future of AI in Medicine

Detaillierter Inhalt:

• Introduction to AI and Its Role in Medicine
This module introduces the basic concepts and historical development of artificial intelligence and explains how AI systems learn from data. Participants explore representative applications of AI in healthcare, as well as its potential benefits, limitations, and responsible use.
• Core Concepts of Machine Learning and Deep Learning
This module introduces the fundamental principles of machine learning and deep learning, including major learning paradigms, neural networks, and commonly used approaches for medical data analysis. It also discusses how machine learning problems are formulated and how model outputs can support medical decision-making.
• Neural Networks
Participants learn how neural networks are structured, trained, and evaluated. The module covers key concepts of model optimization, data splitting, network design, performance assessment, and common challenges such as underfitting and overfitting.
• AI in Medical Imaging
This module presents major applications of AI in medical imaging, including classification, detection, segmentation, reconstruction, and image generation. Participants are introduced to commonly used deep learning architectures and more recent developments in medical image analysis.
• AI for Clinical Decision Support and Precision Medicine
Participants explore how AI can support clinical decision-making by combining different types of patient data and identifying clinically relevant patterns. The module also introduces precision medicine and discusses practical challenges related to data quality, explainability, bias, and clinical implementation.
• Natural Language Processing and Large Language Models in Medicine
This module introduces the foundations of natural language processing and large language models and explains how they can be applied to medical text and clinical information. Applications, limitations, risks, and requirements for responsible use of language-based AI systems in healthcare are discussed.
• Ethics, Privacy, Fairness, and Regulation of Medical AI
Participants examine ethical, legal, and societal considerations associated with medical AI. Key topics include privacy, fairness, bias, transparency, patient safety, human oversight, and regulatory requirements for AI-based medical systems.
• Introduction to Coding in Python
This module provides a practical introduction to Python programming using simple healthcare-related examples. Participants learn basic programming concepts, data organization and processing, and simple approaches to data analysis and visualization.
• Build an AI Pipeline from Scratch
Participants learn how to construct a basic end-to-end machine learning workflow using clinical-style data. The module covers data preparation, model training, evaluation, and the application of a trained model to new data.
• Detecting COVID-19 with AI
This hands-on module demonstrates how an AI-based image classification workflow can be applied to chest X-ray images. Participants work through the main steps from data preparation and model training to performance evaluation.
• Brain Tumor Classification
This module provides a second practical example of medical image classification using brain MRI data. 
• Evaluating Medical AI Literature
Participants learn how to critically evaluate scientific studies on AI in medicine using a real-world research example. 
• The Future of AI in Medicine
The final module explores emerging developments in medical AI, including foundation models, multimodal systems.

Lern-/Qualifikationsziele:

After completing the course, participants will be able to explain fundamental concepts of artificial intelligence, machine learning, and deep learning and describe their relevance to medicine. They will be able to identify common AI applications in healthcare, understand the basic steps of developing and evaluating AI models, and apply introductory programming and data analysis skills in simple practical examples. Participants will also be able to critically assess the quality, limitations, and clinical relevance of medical AI systems and scientific studies, and discuss key ethical, legal, and regulatory considerations related to the responsible use of AI in medicine.

Lehrveranstaltungstyp:

Kurs

Interaktionsformen mit Betreuer/in:

E-Mail

Interaktionsformen mit Mitlernenden:

Forum

Kursdemo:

zur Kursdemo

Nutzung

Kurs ist konzipiert für:

Universität Erlangen-Nürnberg (FAU):

• Medizin (Staatsexamen)
• Zahnmedizin (Staatsexamen)
• Medizintechnik (B Sc. / M. Sc.)

Universität Regensburg:

• Zahnmedizin (Staatsexamen)

Universität Würzburg:

• Zahnmedizin (Staatsexamen)

Formale Voraussetzungen:

none

Erforderliche Vorkenntnisse:

No specific prior knowledge is required. The course is designed as an introductory course and does not require previous experience in AI, machine learning, or programming.

Hinweise zur Nutzung:

-

Kursumsetzung (verwendete Medien):

The course is designed as a modular, self-paced online course. Each module includes learning objectives, videos, reading materials, quizzes. Practical examples and medical case studies are used to link fundamental AI concepts to applications in medicine. Additional resources are provided for further reading.

Erforderliche Technik:

To use the service, you will need a web browser (Edge, Chrome, Firefox, etc.) and an internet connection. As most of the content is in video format, the connection should also be stable.

Nutzungsentgelte:

für andere Personen als (reguläre) Studenten der vhb Trägerhochschulen nach Maßgabe der Benutzungs- und Entgeltordnung der vhb

Rechte hinsichtlich des Kursmaterials:

All course materials are protected by copyright. Course materials are intended for use within the VHB course and may not be redistributed or published without permission.

Verantwortlich

Anbieterhochschule:

Uni Erlangen-Nürnberg (FAU)

Anbieter:

Prof. Dr. med. dent. Lina Gölz

Prof. Dr. Yan Xia

Autoren:

Yan Xia

Betreuer:

Prof. Dr. Yan Xia

Prüfung

Art der Prüfung:

schriftliche Prüfung

Bemerkung:

–

Prüfer:

Prof. Dr. Yan Xia

Prüfungsanmeldung erforderlich:

nein

Anmeldeverfahren:

–

Prüfungsanmeldefrist:

–

Prüfungsabmeldefrist:

–

Kapazität:

–

Prüfungsdatum:

–

Prüfungszeitraum:

–

Prüfungsdauer:

–

Prüfungsort:

–

Zuständiges Prüfungsamt:

–

Zugelassene Hilfsmittel:

–

Formale Voraussetzungen für die Prüfungsteilnahme:

–

Inhaltliche Voraussetzungen für die Prüfungsteilnahme:

–

Zertifikat:

Nein

Anerkennung:

–