AI in Clinical Practice and Training

Recommended Prerequisites

NA

Teaching Methods

Lectures, aimed at presenting the fundamental concepts; Case-based learning, promoting the sharing of experiences between subjects from different academic and professional backgrounds; Fostering interdisciplinary collaboration, encouraging the building of contact networks and partnerships; Work in which students apply the knowledge acquired in the evaluation and critical analysis of a scientific article.

Learning Outcomes

Relate the fundamentals of AI to clinical needs and practices; Identify and analyse practical applications of AI in domains such as medical imaging and remote patient monitoring (e.g. via wearables); Explore the potential of AI as a tool to support medical education and clinical simulation, including the use of generative AI and augmented/virtual reality environments Explore the potential of AI as a tool to support medical training and clinical simulation, including the use of generative AI and augmented/virtual reality environments; Develop critical capacity to assess the benefits, risks and limitations associated with the adoption of AI solutions in clinical practice; Recognise the main barriers to the implementation of AI in healthcare, and discuss strategies for its responsible and effective integration.

Work Placement(s)

No

Syllabus

1) Fundamentals of AI applied to health
- Basic concepts and types of algorithms applied to healthcare
- Characteristics of clinical and biomedical data;
- Differences between biomedical and general AI: specific requirements and limitations
2) Medical training: challenges and opportunities with AI
- Traditional medical training methods and limitations
- The need for innovation in clinical teaching
- AI as a tool to support medical training: adaptive tutorials, personalisation of learning and simulation
3) Emerging technologies
- Generative AI applications in medical education
- Virtual, augmented and robotic reality in clinical training and medical simulation
4) Adoption of AI in healthcare
- Factors driving AI adoption
- Barriers to adoption
- Strategies for integrating AI solutions

Head Lecturer(s)

Francisco José Santiago Fernandes Amado Caramelo

Assessment Methods

Assessment
Quantitative evaluation in a scale of 0 to 20 values. Students who obtain a minimum final mark of 10 values are considered approved.: 100.0%

Bibliography

Simon, G. J., & Aliferis, C. (Eds.). (2024). Artificial intelligence and machine learning in health care and medical sciences: Best practices and pitfalls.
Bohr, A., & Memarzadeh, K. (2020). Artificial intelligence in healthcare. Academic Press.
Selected papers from international scientific journals.