Inhalt

Abstract:

Artificial Intelligence is rapidly transforming how societies detect, prevent, and respond to health challenges, from predicting disease outbreaks to personalizing prevention strategies. As these technologies become increasingly embedded in health systems worldwide, understanding their potential and limitations will be essential for the next generation of health professionals.

This course introduces students in Public Health, Epidemiology, and related fields to the fundamentals and practical relevance of Artificial Intelligence (AI) in Public Health and the Public Health Service. The course focuses primarily on Germany, while also offering international insights.

With a focus on both the technical understanding of AI and practical and ethical applications, the course aims to establish a connection between AI and Public Health.

Gliederung:

Module 1: Introduction to course areas

Module 2: Fundamentals of AI and Machine Learning

Module 3: AI tools and techniques for health data

Module 4: Applications of AI in digital healthcare

Module 5: Ethics and regulation of AI in digital healthcare

Detaillierter Inhalt:

Module 1: Introduction to course areas

This module covers the definitions of Public Health, the Public Health Service in Germany and Bavaria, Digital Public Health, and Artificial Intelligence. It explains how Digital Public Health relates to, yet differs from, general Public Health. It also clarifies how AI as a technology differs from its application in health contexts. The module concludes with examples of AI applications used in Public Health and the Public Health Service.

Module 2: Fundamentals of AI and Machine Learning

This module covers the foundations of AI and data in health. It introduces Machine Learning, Deep Learning, algorithms, and health data, including its sources, quality, and protection. Learners will understand key AI and ML terminology and the three main types of Machine Learning: supervised, unsupervised, and reinforcement. The module explains how data trains, validates, and tests ML models. It also covers common algorithms and their applications, using infection outbreak risk prediction as a real-world example.

Module 3: AI tools and techniques for health data

This module introduces AI tools and platforms, including open-source tools such as Python and WHO data portals. It covers common AI techniques such as decision trees, classification models, and natural language processing through a guided notebook. Learners will apply these techniques to health-related data sets.

Module 4: Applications of AI in digital healthcare

This module investigates real-world applications of AI in public health and public health services. It covers early warning systems for infectious diseases and AI-supported personalized prevention. Learners will also explore Electronic Health Records, as well as AI in the international digital health context and Smart Cities. The module examines an AI-powered tool for assessing the risk of domestic violence. Finally, it provides an example of the use of LLMs for qualitative research.

Module 5: Ethics and regulation of AI in digital healthcare

This module discusses the ethical, legal, and social implications of using AI in healthcare. It focuses on bias in data, algorithms, and models, as well as fairness and transparency. The module also covers legal framework conditions such as the GDPR and the EU AI Act. Finally, it highlights the opportunities and risks of AI in Public Health and Public Health Services.

Lern-/Qualifikationsziele:

In general, the course aims to provide a basic understanding of how Artificial Intelligence works and to enable students to apply this knowledge to real-world challenges in the field of Public Health. In addition, the course equips students with interdisciplinary skills that combine digital literacy, ethical awareness, and applied Public Health analysis.

Learning goals per Module:

Module 1: Introduction to course areas

• Define Public Health, the Public Health Service in Germany and Bavaria, Digital Public Health, and Artificial Intelligence
• Summarize and distinguish between these concepts, e.g., how Digital Public Health relates to but differs from general Public Health, and how AI as a technology differs from its application in health contexts
• List examples of AI applications used in Public Health and the Public Health Service

Module 2: Fundamentals of AI and Machine Learning

• Define key Artificial Intelligence (AI) and data concepts and define health data, in-cluding its sources, quality criteria, and data protection requirements
• List and label the fundamental terminology used in AI and Machine Learning (ML)
• Identify and describe the main types of Machine Learning
• Explain how data is used to train, validate, and test ML models
• Summarize typical algorithms and classify their application areas
• Apply basic ML concepts to real-world examples, such as predicting risk for infec-tion outbreaks

Module 3: AI tools and techniques for health data

• Identify and explain common AI tools and platforms, including open-source tools such as Python and WHO data portals
• Describe common AI techniques such as decision trees, classification models, and natural language processing (NLP)

Module 4: Applications of AI in digital healthcare

• Describe real-world applications of AI in Public Health and Public Health Services
• Apply AI application concepts to practical exercises across these domains
• Analyze case discussions to identify how AI is used differently across these application areas
• Compare the opportunities and challenges of AI use across contexts, such as clinical/individual applications versus population-level or social applications
• Appraise the ethical, social, or practical implications of a specific AI application discussed in the case studies

Module 5: Ethics and regulation of AI in digital healthcare

• Explain key ethical, legal, and social implications of using AI in healthcare, including bias in data, algorithms, and models, and the principles of fairness and transparency
• Describe relevant legal frameworks governing AI in healthcare, such as the GDPR and the EU AI Act
• Analyze how bias can enter AI systems at different stages (data, algorithm, model) and examine its potential effects on fairness and health outcomes
• Appraise a given AI application in healthcare against ethical principles (fairness, transparency) and legal requirements (e.g., GDPR, EU AI Act) to judge its compliance and appropriateness
• Assess whether the opportunities of a specific AI use case in Public Health outweigh its risks, using evidence and stated criteria

Lehrveranstaltungstyp:

Virtuelle Vorlesung

Interaktionsformen mit Betreuer/in:

E-Mail

Interaktionsformen mit Mitlernenden:

Forum

Kursdemo:

zur Kursdemo

Nutzung

Kurs ist konzipiert für:

LMU München: Epidemiology (M.Sc.), Public Health (M.Sc.)

Universität Augsburg: Humanmedizin (Staatsexamen) freiwilliger Wahlkurs!

Formale Voraussetzungen:

Einschreibung in den vhb-Kurs

Erforderliche Vorkenntnisse:

Keine besonderen Vorkenntnnisse erforderlich

Hinweise zur Nutzung:

-

Kursumsetzung (verwendete Medien):

-

Erforderliche Technik:

-

Nutzungsentgelte:

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

Rechte hinsichtlich des Kursmaterials:

-

Verantwortlich

Anbieterhochschule:

Uni München (LMU)

Anbieter:

Dr. Michaela Coenen

Prof. Dr. Eva Annette Rehfuess

Prof. Dr. Ludwig Christian Hinske

Autoren:

Ananda Vaishnavi

Melina Voß

Johanna Wenderoth

Hengyan Zhang

Sophia Baierl

Soundiata Bayo

Ludwig Christian Hinske

Carolin Kinzel

Natalie Schirmer

Brigitte Strahwald

Katharina Hell

Eva Annette Rehfuess

Michaela Coenen

Betreuer:

Course Support Team DPH & AI

Prüfung

Exam on "Digital Public Health AI Fundamentals and Applications"

Art der Prüfung:

schriftlicher Leistungsnachweis (Klausur)

Bemerkung:

Online multiple-choice exam

Prüfer:

Prof. Dr. Eva Annette Rehfuess

Prüfungsanmeldung erforderlich:

nein

Anmeldeverfahren:

–

Prüfungsanmeldefrist:

–

Prüfungsabmeldefrist:

–

Kapazität:

–

Prüfungsdatum:

25.02.2027

Prüfungszeitraum:

10:00 bis 10:45

Prüfungsdauer:

45 Minuten

Prüfungsort:

See the information in the Moodle course

Zuständiges Prüfungsamt:

Examinations Office at the Home University

Zugelassene Hilfsmittel:

–

Formale Voraussetzungen für die Prüfungsteilnahme:

Participation in the CLASSIC vhb Course

Inhaltliche Voraussetzungen für die Prüfungsteilnahme:

Course content

Zertifikat:

Ja (Graded or ungraded course credit)

Anerkennung:

–