Der Inhalt dieser Seite ist aktuell nur auf Englisch verfügbar.
Applied AI in Healthcare
FHS: Agile Project Management
| Semester | 1 |
|---|---|
| Studienjahr | 1 |
| Lehrveranstaltungsnummer | AIHM1APM |
| Typ | IL |
| Art | Pflicht |
| Unterrichtssprache | English |
| SWS | 1 |
| ECTS-Punkte | 2 |
| Prüfungscharakter | immanent |
Lehrveranstaltungsinhalte:
This course gives students a foundation in agile project management as a practical approach for organising complex, uncertain, and interdisciplinary work. Students learn core agile values and principles, compare agile and traditional project-management approaches, and explore how iterative planning, prioritisation, feedback, and reflection support project progress. The course connects agile thinking to digital and healthcare-related projects, focusing on communication, adaptability, and value-oriented delivery rather than detailed internal project templates or tool-specific procedures.
Lernergebnis:
Students understand the purpose and theoretical foundations of agile project management. They can apply suitable agile principles and methods to structure their own projects, manage changing requirements, and reflect on how iterative approaches affect project execution. They learn to choose appropriate tools and practices for a given context, communicate project progress clearly, and critically assess the strengths and limitations of agile methods in professional, interdisciplinary, and healthcare-related settings.
Übergeordnetes Modul:
IT-Management
FHS: Foundations in DS & ML
| Semester | 1 |
|---|---|
| Studienjahr | 1 |
| Lehrveranstaltungsnummer | AIHM1FDSIL |
| Typ | IL |
| Art | Pflicht |
| Unterrichtssprache | English |
| SWS | 4 |
| ECTS-Punkte | 6 |
| Prüfungscharakter | immanent |
Lehrveranstaltungsinhalte:
This course introduces the foundations of data science and machine learning in healthcare contexts. Students work with clinical-style datasets and learn how data is prepared, explored, modelled, and evaluated. The course covers typical steps of data-science workflows, from data quality assessment and preprocessing to machine-learning models and performance interpretation. Students also move from visual analytics tools to beginner-friendly Python notebooks and gain an initial understanding of explainability, responsible AI, and human oversight in healthcare applications.
Lernergebnis:
After completing this course, students understand core data-science workflows and basic machine-learning concepts. They can recognise common data-quality issues, prepare and explore datasets, build simple models, and interpret model performance using standard evaluation approaches. Students gain first practical experience with visual analytics tools and Python-based workflows. They can relate clinical questions to analytical tasks, communicate results to interdisciplinary audiences, and reflect on responsible AI principles such as transparency, model limitations, and human-in-the-loop decision-making.
Übergeordnetes Modul:
Technical foundations of AI
FHS: Language-centric AI Methods
| Semester | 1 |
|---|---|
| Studienjahr | 1 |
| Lehrveranstaltungsnummer | AIHM1LAIIL |
| Typ | IL |
| Art | Pflicht |
| Unterrichtssprache | English |
| SWS | 4 |
| ECTS-Punkte | 6 |
| Prüfungscharakter | immanent |
Lehrveranstaltungsinhalte:
This course introduces language-based AI in healthcare, including natural language processing, large language models, and conversational systems. Students explore how clinical text can be processed, summarised, transformed, and used in supportive workflows. The course addresses safe handling of sensitive text, prompting principles, common error patterns, and responsible use of generative AI. Students also gain an overview of how chatbots and natural-language interfaces can support documentation, communication, and workflow automation without exposing detailed implementation designs.
Lernergebnis:
Students understand the role and potential of language-based AI methods in clinical environments. They can describe core NLP and generative-AI concepts, recognise limitations such as hallucinations, bias, and privacy risks, and apply practical strategies for safer use. They learn to formulate precise prompts, evaluate AI-generated outputs, and judge whether language-based tools are appropriate for a healthcare task. Students also gain the ability to reason about simple conversational systems and their responsible deployment in clinical communication and documentation contexts.
Übergeordnetes Modul:
Technical foundations of AI
FHS: Programming Essentials
| Semester | 1 |
|---|---|
| Studienjahr | 1 |
| Lehrveranstaltungsnummer | AIHM1PREIL |
| Typ | IL |
| Art | Pflicht |
| Unterrichtssprache | English |
| SWS | 4 |
| ECTS-Punkte | 6 |
| Prüfungscharakter | immanent |
Lehrveranstaltungsinhalte:
This course introduces programming as a practical tool for solving data-related problems in healthcare. Students learn the foundations of Python, including variables, data structures, control flow, functions, documentation, debugging, and clean coding habits. The course uses beginner-friendly programming environments and introduces common libraries for data handling, basic analysis, and visualisation. The emphasis is on structured problem-solving, reproducible computational workflows, and readable code that can support later work in data science, machine learning, and clinical AI applications.
Lernergebnis:
Students learn to approach simple computational problems systematically and implement them in Python. They can write clear procedural programs, use common data types and structures, apply control flow, and design basic functions with meaningful documentation. They also gain experience reading, writing, cleaning, and visualising data with standard Python tools. By the end of the course, students can apply fundamental coding practices, use simple debugging strategies, and produce readable, maintainable code for introductory clinical data tasks.
Übergeordnetes Modul:
Technical foundations of AI
PMU: Austrian Legislation
| Semester | 1 |
|---|---|
| Studienjahr | 1 |
| Lehrveranstaltungsnummer | AIHM1ATLIL |
| Typ | IL |
| Art | Pflicht |
| Unterrichtssprache | English |
| SWS | 0,5 |
| ECTS-Punkte | 2 |
| Prüfungscharakter | immanent |
Lehrveranstaltungsinhalte:
This course introduces the Austrian legal environment for AI and digital tools in healthcare. Students learn which national actors and legal frameworks shape the deployment of AI-related software, medical devices, electronic health records, data protection, and hospital use cases. The course focuses on practical orientation: when software may become regulated, what responsibilities arise for healthcare organisations, and how Austrian requirements interact with European rules. Specific internal checklists and scenario details are generalised for public communication.
Lernergebnis:
Students can identify the main Austrian institutions, systems, and legal bases relevant to AI in healthcare. They understand how medical-device law, data protection, and electronic health-record regulation influence clinical AI projects. Students can classify typical legal situations at a high level, describe the immediate implications for clinicians, IT teams, and data specialists, and recognise when expert legal or regulatory clarification is required before deploying AI-supported tools in Austrian healthcare settings.
Übergeordnetes Modul:
Legal Frameworks for Clinical AI (EU/Austria)
PMU: Clinical AI Foundations, Use-Case Landscape, and Healthcare Data Standards in Practice
| Semester | 1 |
|---|---|
| Studienjahr | 1 |
| Lehrveranstaltungsnummer | AIHM1CAFIL |
| Typ | IL |
| Art | Pflicht |
| Unterrichtssprache | English |
| SWS | 0,5 |
| ECTS-Punkte | 2 |
| Prüfungscharakter | immanent |
Lehrveranstaltungsinhalte:
The course focuses on the clinical AI landscape and shows how AI can support healthcare workflows. Students explore typical use cases, the importance of data quality and workflow fit, and the role of electronic health records in Austrian and European healthcare. The course also provides an accessible overview of health-data interoperability, including key standards used for exchanging clinical and imaging data. It connects these topics to current developments in European health-data policy and the practical requirements of safe, interoperable AI systems.
Lernergebnis:
Students can explain how clinical AI systems fit into hospital workflows and why interoperability is essential for safe and useful implementation. They understand the role of electronic health records, core health-data standards, and imaging data formats in connecting clinical systems. Students can relate AI use cases to data quality, patient safety, and workflow requirements. They also gain an introductory understanding of how national and European health-data initiatives shape data sharing, reuse, and future AI applications.
Übergeordnetes Modul:
Clinical AI in Practice: Data, Standards, and Deployment
PMU: EU Legislation
| Semester | 1 |
|---|---|
| Studienjahr | 1 |
| Lehrveranstaltungsnummer | AIHM1EULIL |
| Typ | IL |
| Art | Pflicht |
| Unterrichtssprache | English |
| SWS | 0,5 |
| ECTS-Punkte | 2 |
| Prüfungscharakter | immanent |
Lehrveranstaltungsinhalte:
This course gives students a practical foundation on the major European legal frameworks that shape AI in healthcare, including medical-device regulation, in-vitro diagnostic regulation, the EU AI Act, and the European Health Data Space. Students learn how software may be classified, why clinical evaluation and post-market responsibilities matter, and how high-risk AI obligations interact with medical-device requirements. The course keeps the legal orientation practical and accessible while avoiding the publication of detailed compliance workflows or internal teaching materials.
Lernergebnis:
Students can summarise the main European frameworks relevant to clinical AI and electronic health-data systems. They understand how medical-device classification, conformity assessment, clinical evaluation, and post-market monitoring influence AI software. Students can explain how high-risk AI obligations relate to transparency, human oversight, documentation, and lifecycle monitoring. They also learn to distinguish broad categories such as research use, in-house use, and regulated deployment, and to recognise when a project requires further regulatory assessment.
Übergeordnetes Modul:
Legal Frameworks for Clinical AI (EU/Austria)
PMU: Ethical Foundations, Fairness & Societal Transparency in Clinical AI
| Semester | 1 |
|---|---|
| Studienjahr | 1 |
| Lehrveranstaltungsnummer | AIHM1EFTIL |
| Typ | IL |
| Art | Pflicht |
| Unterrichtssprache | English |
| SWS | 0,5 |
| ECTS-Punkte | 1 |
| Prüfungscharakter | immanent |
Lehrveranstaltungsinhalte:
This course introduces the ethical foundations of AI in healthcare, focusing on beneficence, non-maleficence, autonomy, justice, fairness, explainability, privacy, accountability, and human oversight. Students explore why bias can emerge in clinical AI systems and how explanations can support trust among clinicians and patients. The course links ethical principles to everyday hospital contexts without publishing detailed in-class checklists or specific teaching exercises, keeping the public description accessible and student-oriented.
Lernergebnis:
Students can explain core bioethical principles and relate them to trustworthy AI in healthcare. They learn to recognise potential sources of bias, describe simple fairness considerations, and select explanation approaches that fit the clinical audience and task. Students can communicate model limitations responsibly and understand why transparency, data quality, monitoring, and human oversight are central to ethical AI use. They also reflect on how fairness and explainability decisions affect clinical workflows and patient trust.
Übergeordnetes Modul:
AI, Society & Ethics
PMU: From Data Access & Preprocessing to Ethical Practice: Clinical Decision Support, Validation & Monitoring
| Semester | 1 |
|---|---|
| Studienjahr | 1 |
| Lehrveranstaltungsnummer | AIH1MFDEIL |
| Typ | IL |
| Art | Pflicht |
| Unterrichtssprache | English |
| SWS | 0,5 |
| ECTS-Punkte | 2 |
| Prüfungscharakter | immanent |
Lehrveranstaltungsinhalte:
This course introduces clinical decision support as a practical application area for AI in hospitals. Students learn how patient data from different sources can be prepared for supportive tools, why data quality matters, and how validation, calibration, bias checks, and monitoring contribute to safe use. The course also addresses the European perspective on data reuse and benchmarking. Detailed internal workflow designs are kept out of the public description while preserving the central focus on trustworthy, evaluated decision support.
Lernergebnis:
Students can define key concepts in clinical decision support, validation, calibration, bias assessment, and ongoing monitoring. They understand how data selection, cleaning, harmonisation, and privacy-preserving preparation influence model development and deployment. Students can outline a basic validation strategy, choose suitable evaluation criteria, and recognise why internal and external validation differ. They also learn to situate decision-support tools within hospital workflows and to consider fairness, safety, and governance before and after deployment.
Übergeordnetes Modul:
Clinical AI in Practice: Data, Standards, and Deployment
PMU: Society, Public Perception & Cultural Contexts of AI in Health
| Semester | 1 |
|---|---|
| Studienjahr | 1 |
| Lehrveranstaltungsnummer | AIHM1SPCIL |
| Typ | IL |
| Art | Pflicht |
| Unterrichtssprache | English |
| SWS | 0,5 |
| ECTS-Punkte | 1 |
| Prüfungscharakter | immanent |
Lehrveranstaltungsinhalte:
This course explores how society, culture, media narratives, accessibility, and public trust shape the adoption of AI in healthcare. Students consider what patients and clinicians need to understand and trust AI-supported systems, and how communication influences acceptance. The course also addresses digital divides, inclusion, multilingual healthcare, and cross-border information exchange in Europe. Detailed communication exercises and platform-specific activities are generalised while retaining the focus on responsible, accessible, and patient-centred AI communication.
Lernergebnis:
Students can explain key factors that influence public trust in health AI and relate them to European and Austrian healthcare contexts. They learn to analyse adoption barriers for clinicians and patients, propose communication or workflow improvements, and recognise why accessibility and inclusion matter for patient-facing digital services. Students can communicate limitations responsibly, especially where data availability or participation choices affect fairness, and can reflect on how social context shapes the success of AI implementation.
Übergeordnetes Modul:
AI, Society & Ethics
FHS/PMU: Clinical Innovation Lab I
| Semester | 2 |
|---|---|
| Studienjahr | 1 |
| Lehrveranstaltungsnummer | AIHM2IP1PT |
| Typ | PT |
| Art | Pflicht |
| Unterrichtssprache | English |
| SWS | 2 |
| ECTS-Punkte | 4 |
| Prüfungscharakter | immanent |
Lehrveranstaltungsinhalte:
This project-based course allows students to apply knowledge from data science, programming, clinical AI, ethics, and regulation to a practical healthcare-related challenge. Students work on domain and data understanding, formulate project questions, explore feasible methods, and begin developing solution concepts. The course includes project management, reflection, teamwork, and communication of early results. Public wording intentionally avoids detailed project templates, internal coaching structures, and specific assessment artefacts while conveying the applied, collaborative character of the lab.
Lernergebnis:
Students develop practical implementation skills by working on a clinically relevant AI project. They learn to frame project questions, understand the application domain, assess available data, select suitable methods, and reflect on ethical and legal constraints. Students strengthen experimentation, problem-solving, teamwork, and communication skills. They can justify early methodological decisions, present preliminary outcomes to different audiences, and use structured project practices to refine their ideas toward a feasible clinical AI solution.
Übergeordnetes Modul:
Individual Project Phase I
FHS: Applied Clinical AI
| Semester | 2 |
|---|---|
| Studienjahr | 1 |
| Lehrveranstaltungsnummer | AIHM2ACAIL |
| Typ | IL |
| Art | Pflicht |
| Unterrichtssprache | English |
| SWS | 4,5 |
| ECTS-Punkte | 6 |
| Prüfungscharakter | immanent |
Lehrveranstaltungsinhalte:
This course gives students a broad view of modern AI systems in clinical settings. It covers common application areas, clinical data types, model behaviour, performance interpretation, explainability, workflow integration, and responsible use. Students explore strengths and limits of current AI approaches, including predictive, imaging, language-based, generative, and multimodal systems. The course emphasises clinical usefulness, safety, and workflow fit rather than exposing detailed model-building sequences or proprietary teaching designs.
Lernergebnis:
Students understand the clinical relevance of modern AI systems and can judge where their use is appropriate. They can explain major AI concepts at a high level, recognise risks such as bias, data shift, unreliable outputs, and over-reliance, and interpret basic performance information in clinical terms. Students also learn how data quality, explainability, human oversight, and workflow integration affect usefulness and safety, enabling them to evaluate simple AI-supported clinical workflows responsibly.
Übergeordnetes Modul:
Applied principles of AI, data and code
FHS: Data & Statistics
| Semester | 2 |
|---|---|
| Studienjahr | 1 |
| Lehrveranstaltungsnummer | AIHM2DASIL |
| Typ | IL |
| Art | Pflicht |
| Unterrichtssprache | English |
| SWS | 4 |
| ECTS-Punkte | 6 |
| Prüfungscharakter | immanent |
Lehrveranstaltungsinhalte:
This course introduces the statistical foundations needed for applied data analysis and evidence-based reasoning. Students learn core ideas from probability, descriptive statistics, relationships between variables, regression, estimation, confidence intervals, hypothesis testing, p-values, and effect sizes. The emphasis is on intuitive understanding and practical interpretation rather than advanced mathematical derivation. Students connect statistical reasoning to real-world data questions and develop the language needed to evaluate evidence in clinical and AI-related contexts.
Lernergebnis:
Students can explain and apply foundational statistical concepts in applied analytical settings. They learn to summarise datasets, select and interpret common probability distributions, analyse relationships between variables, and understand basic regression models. Students can interpret estimators, confidence intervals, hypothesis tests, p-values, and effect sizes in context. By the end of the course, they can use statistical reasoning to support evidence-based and practical decisions in healthcare-related data analysis.
Übergeordnetes Modul:
Applied principles of AI, data and code
FHS: Practical Programming Skills
| Semester | 2 |
|---|---|
| Studienjahr | 1 |
| Lehrveranstaltungsnummer | AIHM2PPSIL |
| Typ | IL |
| Art | Pflicht |
| Unterrichtssprache | English |
| SWS | 4 |
| ECTS-Punkte | 6 |
| Prüfungscharakter | immanent |
Lehrveranstaltungsinhalte:
This course develops students' programming ability beyond introductory Python. It focuses on writing clearer, more reliable, and more maintainable code for applied clinical AI tasks. Students learn modular design, handling of clinical-style data sources, error management, reproducible workflows, documentation, and basic software-engineering practices. The course also introduces collaboration and interoperability concepts such as version control, structured data formats, and service interfaces, while omitting detailed internal implementation exercises from the public description.
Lernergebnis:
Students can design and implement structured programming solutions for applied clinical AI tasks. They learn to break problems into maintainable components, work reliably with data, and apply validation, error handling, documentation, and reproducibility practices. Students gain experience with basic software-engineering tools and concepts that support collaboration, auditability, and performance awareness. They can also interpret structured data formats and connect simple workflows to external services in a technically responsible manner.
Übergeordnetes Modul:
Applied principles of AI, data and code
PMU: AI Knowledge & Epistemic Authority in Medicine
| Semester | 2 |
|---|---|
| Studienjahr | 1 |
| Lehrveranstaltungsnummer | AIHM2KEAIL |
| Typ | IL |
| Art | Pflicht |
| Unterrichtssprache | English |
| SWS | 0,5 |
| ECTS-Punkte | 1,5 |
| Prüfungscharakter | immanent |
Lehrveranstaltungsinhalte:
This seminar explores philosophical questions raised by AI in medicine: what AI systems can be said to "know", how their outputs differ from clinical expertise, and how authority should be balanced when humans and machines disagree. Students examine epistemic trust, professional judgment, black-box concerns, automation bias, and over-reliance. The public description keeps the conceptual focus visible while avoiding publication of specific debate structures, checklists, or case exercises used in class.
Lernergebnis:
Students can explain how AI-generated outputs differ from clinical knowledge and professional expertise. They learn to assess when AI can support decision-making and when human judgment must remain central. Students can identify risks of automation bias and over-reliance, reason about the limits of algorithmic authority, and discuss how clinical context, evidence quality, alternatives, and potential harms should shape the use of AI recommendations in medicine.
Übergeordnetes Modul:
Philosophy of Artifical Intelligence (Human - Machine Co-Evolution)
PMU: Human Identity, Agency & Professional Roles in the Age of AI
| Semester | 2 |
|---|---|
| Studienjahr | 1 |
| Lehrveranstaltungsnummer | AIHM2IARIL |
| Typ | IL |
| Art | Pflicht |
| Unterrichtssprache | English |
| SWS | 0,5 |
| ECTS-Punkte | 1,5 |
| Prüfungscharakter | immanent |
Lehrveranstaltungsinhalte:
This seminar examines how AI changes professional identity, agency, responsibility, and skill development in healthcare. Students explore how clinicians remain accountable when AI is involved, why current AI systems should not be treated as conscious agents, and how over-trust can affect patient autonomy and clinical judgment. The course also considers shifting professional roles, new human competencies, and the risk of deskilling, while keeping detailed classroom activities and specific prevention programmes private.
Lernergebnis:
Students can explain how AI "in the loop" reshapes clinician roles, responsibility, and patient autonomy. They learn to distinguish human agency and consciousness from current AI capabilities and to recognise risks that arise when systems are treated as if they understand or decide independently. Students can discuss responsibility gaps, over-trust, and deskilling, and propose broad strategies that preserve clinical expertise, reflective judgment, and accountable human decision-making.
Übergeordnetes Modul:
Applied principles of AI, data and code
PMU: Invited Talks - Lecture Series 2nd Semester
| Semester | 2 |
|---|---|
| Studienjahr | 1 |
| Lehrveranstaltungsnummer | AIHM2IT1IL |
| Typ | IL |
| Art | Pflicht |
| Unterrichtssprache | English |
| SWS | 0,5 |
| ECTS-Punkte | 1 |
| Prüfungscharakter | immanent |
Lehrveranstaltungsinhalte:
This lecture series gives students access to current perspectives in applied AI for healthcare through talks by researchers, innovators, clinicians, and other experts. Students encounter real deployment stories, emerging trends, and cross-sector viewpoints that extend beyond textbooks. The format highlights how methods, evidence, ethics, regulation, and workflows intersect in practice. It encourages curiosity, critical questioning, and professional networking while keeping speaker-specific content and assignment details separate from the public course description.
Lernergebnis:
Students learn to identify cross-cutting trends in applied AI for healthcare and connect them to clinical, research, and product contexts. They can critically reflect on evidence, methods, ethical implications, and implementation challenges presented by expert speakers. Students practise formulating informed questions, engaging professionally with external guests, and translating talk insights into concise, structured takeaways that support their broader understanding of the rapidly evolving AI-in-healthcare landscape.
Übergeordnetes Modul:
Invited Talks 1
PMU: Quality Assurance in Medical AI
| Semester | 2 |
|---|---|
| Studienjahr | 1 |
| Lehrveranstaltungsnummer | AIHM2QAMIL |
| Typ | IL |
| Art | Pflicht |
| Unterrichtssprache | English |
| SWS | 1 |
| ECTS-Punkte | 2 |
| Prüfungscharakter | immanent |
Lehrveranstaltungsinhalte:
This course introduces quality assurance for medical AI from a European healthcare perspective. Students learn how regulation, quality management, risk management, software lifecycle thinking, cybersecurity, transparency, logging, and human oversight interact in AI-enabled medical software. The course explains what a responsible quality culture looks like without publishing detailed documentation blueprints, audit checklists, or internal exercises. The focus is on helping students understand how safe and reliable AI systems are planned, evaluated, monitored, and improved.
Lernergebnis:
Students can relate quality-assurance tasks to European rules for AI-enabled medical software. They understand why documentation, transparency, human oversight, risk management, and lifecycle monitoring are necessary across development and use. Students can outline the purpose of a lightweight quality-management approach, identify major risk-control considerations, and explain how user-facing information can support safe interpretation of AI outputs. They also learn to view quality assurance as a continuous process rather than a one-time approval step.
Übergeordnetes Modul:
Human Oversight in Medical AI: Technical Explainability, Transparency &, Quality Assurance
PMU: Technical Explainability, Transparency & Human Oversight
| Semester | 2 |
|---|---|
| Studienjahr | 1 |
| Lehrveranstaltungsnummer | AIHM2ETOIL |
| Typ | IL |
| Art | Pflicht |
| Unterrichtssprache | English |
| SWS | 0,5 |
| ECTS-Punkte | 2 |
| Prüfungscharakter | immanent |
Lehrveranstaltungsinhalte:
This course examines how explainability, transparency, documentation, and human oversight make medical AI safer and more trustworthy. Students learn what explanations need to achieve for clinicians and patients, how oversight can reduce over-reliance, and why logging and documentation matter for accountable use. The course connects these themes to European expectations for high-risk AI in healthcare while avoiding publication of detailed templates, audit structures, or in-class evidence-mapping activities.
Lernergebnis:
Students can explain why transparency, explainability, and human oversight are essential for high-risk medical AI. They learn to design a suitable explanation approach for a clinical use case, describe oversight roles and intervention points, and understand how lifecycle logging supports monitoring and accountability. Students can connect fairness, documentation, privacy, and oversight to trustworthy AI practice and reflect on how explanations should be adapted for clinicians, patients, managers, and other stakeholders.
Übergeordnetes Modul:
Human Oversight in Medical AI: Technical Explainability, Transparency &, Quality Assurance
FHS/PMU: Clinical Innovation Lab II
| Semester | 3 |
|---|---|
| Studienjahr | 2 |
| Lehrveranstaltungsnummer | AIHM3IP2IL |
| Typ | PT |
| Art | Pflicht |
| Unterrichtssprache | English |
| SWS | 2 |
| ECTS-Punkte | 4 |
| Prüfungscharakter | immanent |
Lehrveranstaltungsinhalte:
This advanced project-based course continues the development of clinically relevant AI solutions. Students refine earlier project concepts, improve technical and methodological choices, and work toward more mature prototypes that address clinical workflow, feasibility, validation, ethics, and regulation. The course combines project work, supervision, reflection, teamwork, and communication of results. Public wording avoids detailed coaching arrangements, project documentation structures, and assessment procedures while highlighting the applied and integrative character of the lab.
Lernergebnis:
Students deepen their technical, methodological, and professional competencies by advancing a clinical AI project toward a more mature solution. They can refine software or model architecture, apply validation thinking, and consider integration into realistic clinical workflows. Students learn to justify technical and organisational decisions with attention to ethical, legal, and medical constraints. They also reflect on sustainability, risks, and limitations and present their work in a professional, audience-appropriate manner.
Übergeordnetes Modul:
Individual Project Phase II
FHS/PMU: Elective course
| Semester | 3 |
|---|---|
| Studienjahr | 2 |
| Lehrveranstaltungsnummer | AIHM3ELC |
| Typ | IL |
| Art | Pflicht |
| Unterrichtssprache | English |
| SWS | 1 |
| ECTS-Punkte | 3 |
| Prüfungscharakter | immanent |
Lehrveranstaltungsinhalte:
The elective course pool allows students to broaden their academic and professional profile by selecting a suitable course from another discipline or institution. The aim is to encourage interdisciplinary thinking, methodological diversity, and cross-pollination between fields. Students choose an elective that complements, extends, or strategically challenges their learning in applied AI in healthcare. Public wording omits administrative approval details while highlighting the opportunity for individual development and broader professional networking.
Lernergebnis:
Students can purposefully expand their knowledge by selecting and justifying an elective from another discipline. They learn to articulate how the chosen course complements their profile and how concepts, methods, or perspectives from another field can strengthen their projects, ideas, and professional development. Students also practise learning across institutional and teaching formats and documenting how new insights contribute to their scientific, technical, or interdisciplinary competence.
Übergeordnetes Modul:
Elective Course Pool
PMU: AI Systems for Clinical Decision Support
| Semester | 3 |
|---|---|
| Studienjahr | 2 |
| Lehrveranstaltungsnummer | AHIM3CDSIL |
| Typ | IL |
| Art | Pflicht |
| Unterrichtssprache | English |
| SWS | 1 |
| ECTS-Punkte | 2 |
| Prüfungscharakter | immanent |
Lehrveranstaltungsinhalte:
This course introduces AI systems that support clinical decisions at the bedside, in imaging, and across care pathways. Students explore how alerts, dashboards, risk scores, triage tools, and other decision-support applications may help clinicians while also creating risks such as false alarms, workflow disruption, or uneven performance. The course uses European and clinical examples in broad terms but does not publish specific case analyses, evaluation tasks, or detailed implementation material.
Lernergebnis:
Students can explain what clinical decision support means in everyday healthcare work and describe how AI-based tools may assist teams. They learn to judge whether a signal is clinically useful or likely to create noise, and to propose reasonable next steps for a care team. Students also understand why validation, local testing, fair performance across patient groups, regulatory approval, and workflow fit are essential before using such systems in practice.
Übergeordnetes Modul:
AI for Clinical Decision Support
PMU: AI on Shared European Health Data
| Semester | 3 |
|---|---|
| Studienjahr | 2 |
| Lehrveranstaltungsnummer | AIHM3EHDIL |
| Typ | IL |
| Art | Pflicht |
| Unterrichtssprache | English |
| SWS | 1 |
| ECTS-Punkte | 2 |
| Prüfungscharakter | immanent |
Lehrveranstaltungsinhalte:
This course explores how AI applications may benefit from shared European health data. Students consider decision support, population health, learning health systems, and models trained on diverse clinical, imaging, laboratory, and sensor data. The course follows the lifecycle of AI projects using shared data, from access requests to secure analysis, validation, monitoring, and responsible deployment. It also addresses opportunities and risks such as participation, commercial involvement, centralisation, and benefit sharing.
Lernergebnis:
Students can describe AI applications that become more feasible or powerful when high-quality European health data can be shared responsibly. They understand the basic journey of an AI project using health data for care or research, including data access, secure processing, model development, validation, and monitoring. Students can discuss opportunities and risks of large-scale AI on shared health data, including fairness, participation, governance, commercial interests, and societal benefit.
Übergeordnetes Modul:
AI in the European Health Data Space
PMU: Applied AI in Medical Imaging: Current State & Clinical Cases
| Semester | 3 |
|---|---|
| Studienjahr | 2 |
| Lehrveranstaltungsnummer | AIHM3AMIIL |
| Typ | IL |
| Art | Pflicht |
| Unterrichtssprache | English |
| SWS | 1 |
| ECTS-Punkte | 2 |
| Prüfungscharakter | immanent |
Lehrveranstaltungsinhalte:
This course introduces current applications of AI in medical imaging and shows how they affect clinical workflows. Students explore major imaging task types, clinical performance interpretation, workflow impact, and the role of newer generative and multimodal models. Realistic clinical perspectives help students understand where imaging AI can add value and where caution is needed. Specific local cases, detailed metrics exercises, and internal adoption pathways are deliberately generalised for public presentation.
Lernergebnis:
Students can explain the strengths and limits of current AI tools in medical imaging, including emerging generative and foundation-model approaches. They learn to recognise where such tools may support triage, reporting, prioritisation, or decision support, and where risks such as data shift, hallucinations, integration burden, and human oversight requirements arise. Students can describe major imaging task families and discuss their typical inputs, outputs, risks, and governance considerations.
Übergeordnetes Modul:
Medical Imaging & Diagnostics using AI Tools
PMU: Communication, Transformation and Change Management
| Semester | 3 |
|---|---|
| Studienjahr | 2 |
| Lehrveranstaltungsnummer | AIHM3CTCIL |
| Typ | IL |
| Art | Pflicht |
| Unterrichtssprache | English |
| SWS | 0,5 |
| ECTS-Punkte | 2 |
| Prüfungscharakter | immanent |
Lehrveranstaltungsinhalte:
This course introduces the human and organisational side of AI implementation in healthcare. Students explore why AI projects may create uncertainty, resistance, mistrust, or role concerns among clinicians, nurses, managers, IT teams, and patients. The course covers communication, stakeholder engagement, co-design, leadership, training, phased rollout, and monitoring of organisational effects. It presents change management as a central success factor while keeping detailed case work and communication exercises private.
Lernergebnis:
Students can explain why different stakeholders may resist or question the introduction of AI systems in healthcare. They learn to use clear, honest communication to reduce fear and misunderstanding and to involve clinicians, patients, managers, and technical teams constructively. Students can describe the main steps of a realistic change process, from early engagement and training to phased implementation and follow-up, and can reflect on how AI transformation can be conducted ethically, transparently, and safely.
Übergeordnetes Modul:
Communication, Transformation & Change Management
PMU: Data Foundations of the European Health Data Space
| Semester | 3 |
|---|---|
| Studienjahr | 2 |
| Lehrveranstaltungsnummer | AIHM3DFEIL |
| Typ | IL |
| Art | Pflicht |
| Unterrichtssprache | English |
| SWS | 1 |
| ECTS-Punkte | 2 |
| Prüfungscharakter | immanent |
Lehrveranstaltungsinhalte:
This course introduces the European Health Data Space and its importance for digital healthcare and AI. Students learn how health data can be made more accessible and interoperable for individual care, research, policy, and innovation. The course covers primary and secondary data use, health-data access structures, secure environments, interoperability, data quality, representativeness, and fairness. Detailed legal walkthroughs and classroom examples are generalised for the public webpage.
Lernergebnis:
Students can explain the purpose of the European Health Data Space and distinguish between primary and secondary use of health data. They understand how access bodies, secure processing environments, and interoperability frameworks support responsible data reuse. Students can describe why semantic and technical interoperability are necessary for meaningful AI across countries, and why data quality, representativeness, governance, and fairness are central when health data are reused for research and innovation.
Übergeordnetes Modul:
AI in the European Health Data Space
PMU: EU & Austrian Regulations for AI in Clinical Decision Support
| Semester | 3 |
|---|---|
| Studienjahr | 2 |
| Lehrveranstaltungsnummer | AIHM3RCDIL |
| Typ | IL |
| Art | Pflicht |
| Unterrichtssprache | English |
| SWS | 0,5 |
| ECTS-Punkte | 2 |
| Prüfungscharakter | immanent |
Lehrveranstaltungsinhalte:
This course explains the regulatory and professional responsibilities that arise when AI-supported tools inform diagnosis, treatment, or clinical decision-making in Austria. Students learn that such tools can support but not replace medical judgment, and that documentation, transparency, approval status, data protection, safety monitoring, and incident reporting all matter. The public version avoids detailed legal checklists and internal scenarios while preserving the core message of accountable, patient-safe use.
Lernergebnis:
Students can describe what clinicians and healthcare organisations in Austria must consider when using AI-supported decision tools. They understand the importance of valid approval, suitable evidence, clear explanations, auditability, human override, data protection, and monitoring. Students learn to recognise when a tool may be unsafe or unreliable in a given setting and why timely reporting of problems supports patient safety and regulatory oversight.
Übergeordnetes Modul:
AI for Clinical Decision Support
PMU: EU & National Regulation for AI-Based Imaging
| Semester | 3 |
|---|---|
| Studienjahr | 2 |
| Lehrveranstaltungsnummer | AIHM3RAIIL |
| Typ | IL |
| Art | Pflicht |
| Unterrichtssprache | English |
| SWS | 0,5 |
| ECTS-Punkte | 2 |
| Prüfungscharakter | immanent |
Lehrveranstaltungsinhalte:
This course introduces the regulatory landscape for AI-based imaging tools in Europe and national healthcare settings. Students learn when imaging software may qualify as a medical device, how risk classification shapes evidence needs, and why clinical evaluation, monitoring, documentation, and change control matter. The course also explains how high-risk AI obligations interact with medical-device rules. Detailed compliance roadmaps and assessment scenarios are not included in the public description.
Lernergebnis:
Students can decide at a high level whether an imaging AI tool may fall under medical-device regulation and what this means for risk classification, evidence, and accountability. They understand key obligations linked to high-risk AI, including data quality, transparency, human oversight, and lifecycle monitoring. Students can outline the main elements of a responsible compliance approach and recognise how European and national requirements interact in imaging-related clinical AI projects.
Übergeordnetes Modul:
Medical Imaging & Diagnostics using AI Tools
PMU: Human-AI Collaboration and Clinical Workflow Integration
| Semester | 3 |
|---|---|
| Studienjahr | 2 |
| Lehrveranstaltungsnummer | AIHM3HACIL |
| Typ | IL |
| Art | Pflicht |
| Unterrichtssprache | English |
| SWS | 1 |
| ECTS-Punkte | 2 |
| Prüfungscharakter | immanent |
Lehrveranstaltungsinhalte:
This course explores how clinicians, patients, and AI-supported tools interact in everyday hospital workflows. Students examine trust, usability, explanations, role clarity, system integration, privacy, safety, and the organisational conditions that influence whether a tool helps or hinders care. The course focuses on practical human-AI collaboration and workflow fit while keeping detailed care-pathway exercises and specific early-warning checks unpublished.
Lernergebnis:
Students can explain how humans and AI-supported tools share work in clinical settings. They understand what makes a tool trustworthy in daily practice, including clear explanations, simple displays, appropriate task fit, integration with existing systems, and strong privacy and safety protections. Students can review a care pathway at a high level, identify where AI may add value without disrupting work, and suggest practical checks to monitor benefit and risk.
Übergeordnetes Modul:
AI for Clinical Decision Support
PMU: Imaging AI in Practice
| Semester | 3 |
|---|---|
| Studienjahr | 2 |
| Lehrveranstaltungsnummer | AIHM3IAPIL |
| Typ | IL |
| Art | Pflicht |
| Unterrichtssprache | English |
| SWS | 1 |
| ECTS-Punkte | 2 |
| Prüfungscharakter | immanent |
Lehrveranstaltungsinhalte:
This course focuses on the practical use of AI in medical imaging after development and deployment. Students explore imaging workflows involving detection, segmentation, radiomics, multimodal data, and emerging generative models. The course emphasises monitoring, safety, fairness, privacy, governance, and the responsible use of shared health data. It highlights the opportunities and risks of advanced imaging AI without publishing detailed monitoring dashboards, validation exercises, or site-specific implementation procedures.
Lernergebnis:
Students can explain how modern imaging AI systems operate within hospital environments and how they may support workflow efficiency, triage, and decision-making. They understand key risks such as data shift, bias, privacy concerns, safety incidents, and misuse. Students can outline a basic post-deployment monitoring approach, recognise when performance changes over time or across patient groups, and propose practical responses that support safe and fair use in clinical imaging workflows.
Übergeordnetes Modul:
Medical Imaging & Diagnostics using AI Tools
PMU: Invited Talks - Lecture Series 3rd Semester
| Semester | 3 |
|---|---|
| Studienjahr | 2 |
| Lehrveranstaltungsnummer | AIHM3IT2IL |
| Typ | IL |
| Art | Pflicht |
| Unterrichtssprache | English |
| SWS | 0,5 |
| ECTS-Punkte | 1 |
| Prüfungscharakter | immanent |
Lehrveranstaltungsinhalte:
This lecture series continues to expose students to the state of the art in applied AI for healthcare. Through expert talks and real-world examples, students see how technological developments, clinical workflows, regulation, ethics, and implementation challenges interact. The series supports awareness of emerging use cases and helps students distinguish robust evidence from hype. Public wording remains general and does not reveal speaker-specific material or detailed assessment formats.
Lernergebnis:
Students deepen their ability to analyse expert input across several sessions and identify recurring concepts, methods, and challenges in applied AI for healthcare. They can assess methodological quality, clinical relevance, and ethical implications of presented approaches. Students also practise professional communication with speakers and peers, transforming diverse insights into structured, context-aware summaries that inform their own projects, research questions, and understanding of current developments.
Übergeordnetes Modul:
Invited Talks 2
PMU: Law, Ethics and Governance for AI in the European Health Data Space
| Semester | 3 |
|---|---|
| Studienjahr | 2 |
| Lehrveranstaltungsnummer | AIHM3LEGIL |
| Typ | IL |
| Art | Pflicht |
| Unterrichtssprache | English |
| SWS | 0,5 |
| ECTS-Punkte | 2 |
| Prüfungscharakter | immanent |
Lehrveranstaltungsinhalte:
This course examines the legal, ethical, and governance questions that arise when AI systems use data within the European Health Data Space. Students learn how the European Health Data Space regulation relates to the AI Act, data protection, and wider responsibilities for developers, researchers, and healthcare organisations. The course focuses on rights, fairness, benefit sharing, discrimination risks, and governance structures without disclosing detailed compliance planning activities.
Lernergebnis:
Students can explain how the European Health Data Space, the AI Act, and data-protection rules interact when AI systems use health data. They understand key rights and interests of individuals whose data are reused, including fairness, transparency, protection from discrimination, and responsible benefit sharing. Students can outline the main elements of a realistic governance and compliance approach, identify relevant bodies and responsibilities, and discuss ethical expectations for AI projects using shared health data.
Übergeordnetes Modul:
AI in the European Health Data Space
PMU: Research Studio: From Idea to Thesis
| Semester | 3 |
|---|---|
| Studienjahr | 2 |
| Lehrveranstaltungsnummer | AIHM3RESIL |
| Typ | IL |
| Art | Pflicht |
| Unterrichtssprache | English |
| SWS | 0,5 |
| ECTS-Punkte | 2 |
| Prüfungscharakter | immanent |
Lehrveranstaltungsinhalte:
This seminar supports students in developing a feasible master's thesis project in clinical AI. Students move from a broad interest to a focused research question, study design, and methodological plan. They practise literature analysis, critical reading of clinical AI studies, and transparent use of AI-supported research tools. The course also introduces research framing, evidence mapping, protocol thinking, and communication of planned work while keeping detailed workshop formats and tool-specific exercises private.
Lernergebnis:
Students can formulate a clear and feasible clinical AI research question and connect it to an appropriate study design, data source, method, and evaluation strategy. They learn to search, select, and critically appraise scientific literature and to document the use of AI-supported research tools transparently. Students can justify their methodological choices, acknowledge limitations, and communicate planned research to different audiences with attention to ethics, academic integrity, open science, and societal relevance.
Übergeordnetes Modul:
Research Studio: From Idea to Thesis
FHS/PMU: Master Defense
| Semester | 4 |
|---|---|
| Studienjahr | 2 |
| Lehrveranstaltungsnummer | AIHM4MAEDP |
| Typ | DP |
| Art | Pflicht |
| Unterrichtssprache | English |
| SWS | 0 |
| ECTS-Punkte | 2 |
| Prüfungscharakter | abschließend |
Lehrveranstaltungsinhalte:
The master defense is the final scientific conversation in which students present their thesis and discuss their work with an examining committee. Students explain the clinical problem, AI approach, methods, results, limitations, and broader implications of their project. Preparation includes shaping a clear presentation for a mixed expert audience and anticipating critical questions about robustness, generalisability, responsible AI, and future work. The public description keeps procedural detail minimal while conveying the capstone character of the defense.
Lernergebnis:
Students can present their thesis clearly and coherently to an expert committee with diverse backgrounds. They learn to explain the clinical relevance, AI method, findings, limitations, and implications of their work. Students can respond thoughtfully to critical questions, demonstrate understanding of the theory and practice behind their methods, and define the boundaries of their claims. They also reflect on future research, clinical translation, and responsible use of AI in healthcare.
Übergeordnetes Modul:
Master Exam
FHS/PMU: Master Project
| Semester | 4 |
|---|---|
| Studienjahr | 2 |
| Lehrveranstaltungsnummer | AIHM4MAPIT |
| Typ | PT |
| Art | Diplom/Masterarbeit |
| Unterrichtssprache | English |
| SWS | 0 |
| ECTS-Punkte | 25 |
| Prüfungscharakter | immanent |
Lehrveranstaltungsinhalte:
In the master research project, students conduct an independent clinical AI study based on a focused research question and a realistic study plan. Projects typically address a clinical or health-system problem using suitable data and AI methods. Students work through the research cycle, including question refinement, data preparation, modelling or analysis, evaluation, interpretation, and reflection on ethical, legal, and fairness aspects. The public description avoids project-specific detail while presenting the thesis as a rigorous, applied research experience.
Lernergebnis:
Students can independently plan, implement, document, and evaluate a clinical AI research project. They learn to align a research question with suitable data, methods, timelines, and evaluation strategies, and to assess strengths, limitations, and risks. Students can recognise ethical, legal, and societal issues such as data protection, bias, fairness, explainability, and responsibility. They can write a structured thesis that situates their work in the literature and communicates findings transparently.
Übergeordnetes Modul:
Master Project
FHS/PMU: Reading Group
| Semester | 4 |
|---|---|
| Studienjahr | 2 |
| Lehrveranstaltungsnummer | AIHM4RGRIL |
| Typ | IL |
| Art | Pflicht |
| Unterrichtssprache | English |
| SWS | 1 |
| ECTS-Punkte | 2 |
| Prüfungscharakter | abschließend |
Lehrveranstaltungsinhalte:
The master reading group provides a structured forum for discussing current clinical AI literature and supporting thesis work. Students, supervisors, and invited guests engage with relevant papers, methodological debates, and work-in-progress questions. Sessions strengthen critical reading, constructive feedback, and the ability to connect literature to project decisions. The public description emphasises scholarly exchange and thesis support while omitting detailed session formats, student work examples, and internal feedback routines.
Lernergebnis:
Students can select, summarise, and discuss scientific papers relevant to their thesis in accessible language. They learn to identify useful methods, limitations, and ideas from the literature and connect them to their own project decisions. Students practise giving and receiving constructive feedback on research work and maintaining an organised, evolving bibliography. They also learn to document how literature and, where appropriate, AI-supported discovery tools inform their thesis development.
Übergeordnetes Modul:
Reading Group
Invited Talks - Lecture Series 4th Semester
| Semester | 4 |
|---|---|
| Studienjahr | 2 |
| Lehrveranstaltungsnummer | AIHM4IT3IL |
| Typ | IL |
| Art | Pflicht |
| Unterrichtssprache | English |
| SWS | 0,5 |
| ECTS-Punkte | 1 |
| Prüfungscharakter | immanent |
Lehrveranstaltungsinhalte:
In the final lecture-series semester, students engage with current developments in applied AI for healthcare from multiple professional perspectives. The talks provide insight into research, innovation, clinical deployment, and sector-specific challenges. Students use the series to connect their thesis and project work to wider developments in the field. The public description highlights the value of exposure to expert practice while keeping individual talk content and task details unpublished.
Lernergebnis:
Students can synthesise insights from expert talks and relate them to broader trends in clinical AI, healthcare innovation, and responsible implementation. They learn to evaluate the relevance and credibility of presented examples, communicate key developments to different audiences, and connect external expert perspectives to their own research or professional interests. The series strengthens critical judgment, professional curiosity, and the ability to follow a fast-moving field.
Übergeordnetes Modul:
Invited Talks 2