Clinical Decision Support

Theory, methods and use cases of artificial intelligence and decision support for clinicians and patients . Content is aligned with student needs, but may range over: Representation of clinical knowledge, guidelines and recommendations; Interfaces for decision support and decision making; Search and ranking of recommendations; Machine learning for analysis of health trajectories; Methods for authoring and validation of clinical guidelines; Evaluation, efficacy and consistency; Technology for decision support; Precision medicine; Generative methods; Foundation models; Deep phenotyping. Risks, limitations and regulations for decision support and AI in health.

Knowledge about: Understanding areas of use, theory, relevant AI and reasoning models, representations, risks, limitations and regulations.

Abilities: Employ and select research methods for developing and evaluating decision support systems. Ability to make requirements, prototype and evaluate systems in the context of use cases and healthcare settings. Basic AI-based data preparation, analysis and stewardship. Use of infrastructure resources and tools for computational decision support development, deployment and quality. Use tools and methods for anonymization and data preprocessing.

Competence: Understand the relationship with underlying scientific areas like knowledge engineering, information extraction, process support. Understand interplay between data-driven architectures and ethical, privacy and safety considerations and regulations.

Seminars, lectures, (programming) laboratory, field work and collaborative writing. Guest lectures and visits.