511625 - APPLIED HEALTH INFORMATICS

On successful completion of the course, students will be able to demonstrate:
Knowledge and Understanding
• CLO1: Distinguish the concepts of data, information, and knowledge, and recognise different types of clinical data as well as how they are generated and collected through process-oriented models.
• CLO2: Understand and apply the principles of clinical data organisation, including the relational model, ER diagrams, and redundancy reduction.
• CLO3: Describe the main standards for syntactic interoperability (XML, JSON, HL7, FHIR) and the overall architecture of health information systems (EHR, national Electronic Health Record, HIS, RIS, PACS).
• CLO4: Understand the fundamentals of predictive and generative Artificial Intelligence, including supervised and unsupervised learning algorithms, Foundation Models, and Large Language Models (LLMs) in clinical contexts.
Applying Knowledge and Understanding
• CLO5: Apply relational database design principles and utilize taxonomies, ontologies, and standard coding systems (ICD, SNOMED, LOINC, ATC) for semantic interoperability.
• CLO6: Evaluate machine learning model performance and apply tools for data exploration (e.g., Orange software) and generative AI tasks.
Making Judgements
• CLO7: Recognize key methodological issues such as bias, variance, and overfitting in predictive models, and critically evaluate the ethical and regulatory aspects of AI in medicine (including the EU AI Act).
Communication Skills
• CLO8: Communicate concepts of medical informatics, data interoperability, and artificial intelligence using standard medical and technical terminology.
Learning Skills
• CLO9: Develop independent practical and evaluation skills through hands-on lab exercises utilizing relational database models, machine learning software, and generative AI portals.