• Lectures & Theoretical Presentation
• Laboratory Exercises with Real Data
• Case Studies, Group Presentations
• Application of VR/AR Technologies and Interactive Platforms
• Use of individual workstations (PC) per student.
• Communication with students via the e-class educational platform for updates, presentation and provision of lecture slides, provision of educational material, assignment and submission of coursework.

• Short-answer questions
• Public presentation of assignment
• Problem solving
• Final written examination

The course delves into the uses of modern informatics techniques and their applications in the medical field.

Its syllabus aims at understanding the use of systems, techniques and methods for storing imaging data in medicine (RIS), the management and storage of data generated daily using these methods and storage schemes (HIS), and the presentation of tools and methods supporting clinical decisions (CDSS) — their capabilities, limitations and safe use during medical diagnosis.

The concept of the Electronic Health Record (EHR), its necessity and advantages are explored in depth. Standards for secure data transmission over the internet and data/document certification with digital certificates (DC) are presented.

The possibilities offered by blockchain technologies in the operation of distributed storage systems of medical records are analyzed.

The use and contribution of Large Language Models (LLMs) as an extension of clinical decision support systems are introduced, emphasizing interaction with humans through natural (spoken) language.

Finally, the course aims to help students understand the capabilities currently provided by technology as well as future possibilities of computing technology for creating, storing, disseminating and using structured medical knowledge, and to demonstrate how these capabilities facilitate medical work.

Upon successful completion of the course, students will be able to:

• Understand how an electronic medical patient record is created.
• Know the systems for storing patients’ imaging data.
• Understand the advantages and security issues of patient imaging data storage systems.
• Understand potential security risks arising from the aggregation of medical data in information systems.
• Understand the concept of digital signatures, their capabilities and extensions provided through the issuance and use of digital certificates.
• Understand the advantages and requirements of applying blockchain technology in clinical practice.
• Have knowledge of the need and functioning of medical databases.
• Understand the concept of modeling clinical workflows.
• Use databases and knowledge bases to retrieve medical information and data.
• Understand the usefulness, possibilities and limitations of clinical decision support systems.
• Know and understand the use of Artificial Intelligence, especially Large Language Models, in assisted diagnosis and documentation of diseases.

General Abilities

 Structure and Content of the Course (13 Weeks)

Introduction to Medical Informatics & Modern Technologies

• The role of Informatics in Medicine
• Introduction to Health Technology and Innovation
• Historical Overview, International Standards (HL7, DICOM, SNOMED CT)

 Medical Data Security

• Data storage and transmission – Privacy
• The need for encryption
• Digital Certificates and Digital Signatures
• Blockchain Technology

 Architecture of the Electronic Health Record (EHR)

• Basic characteristics and architecture
• Interoperability and data exchange standards
• Legal and ethical issues (GDPR, consent, security)

 RIS – HIS – PACS: Health Information Systems

• Definitions, functions, interoperability
• Systems integration – Workflows in the hospital environment
• Laboratory: PACS viewer

 Radiology Information Systems (RIS)

• Management of radiology data and appointments
• Connection with PACS and HIS
• Application examples

 Clinical Decision Support Systems (CDSS)

• Basic concepts of Artificial Intelligence
• Definition and operating principles
• Role in supporting clinical decision-making
• Types of CDSS (rule-based, ML-based)

 Large Language Models (LLMs) in Medicine

• What LLMs are and how they work
• Challenges (bias, regulation) and possibilities

 Telemedicine and AI Support

• Use of AI in telemedicine
• Technological platforms and regulatory framework
• Architecture of remote monitoring and management of chronic diseases

 Presentation – Robotic Surgery

• Da Vinci System and other modern surgical robots
• Telesurgery, haptic feedback and precision

 Monte Carlo Simulations in Precision Medicine

• Definitions and simulation tools
• Simulations in diagnosis and therapy
• Use of anthropomorphic phantoms and clinical data
• Examples and applications

 Modern AI Technologies in Medicine

• Computer Vision in medical imaging
• NLP in clinical data
• Robotics & wearables in health

 Application Examples and Future Trends

• Emerging technologies
• The impact of new technologies on Precision Medicine

 Review and Laboratory Exercise

• Comprehensive summary of the modules
• Discussion, questions

– Suggested Bibliography (GREEK):

• Πληροφορική στην Υγεία – Θεωρία & Πράξη

Συγγραφείς: Α. Μακρής, Α. Γκογκίδης, Χ. Δαρδαμανέλης κ.ά.

Έκδοση: University Studio Press (2020)

ISBN: 978-960-12-2481-5

• Ιατρική Πληροφορική – Θεωρία και Εφαρμογές

Συγγραφέας: Παναγιώτης Κ. Πεντάζος

Έκδοση: Τυπωθήτω – Γιώργος Δαρδανός (2018)

ISBN: 978-960-402-252-4

– Suggested Bibliography (ENGLISH):

• Shortliffe & Cimino – Biomedical Informatics: Computer Applications in Health Care and Biomedicine Συγγραφείς: Edward H. Shortliffe, James J. Cimino
   Έκδοση: Springer, 5η έκδοση (2021)
  ISBN: 978-3-030-58767-3
• Hoyt & Yoshihashi – Health Informatics: Practical Guide

Συγγραφείς: Robert E. Hoyt, Ann K. Yoshihashi

Έκδοση: 8η έκδοση (2021)

ISBN: 979-8737445410