Medical AI · Track 5 of 10
Generative AI & LLMs
How large language models work, how to prompt and adapt them for clinical tasks, and why hallucination and grounding matter more in medicine than anywhere else.
Useful to every reader; code lessons are marked Technical.
By the end of this track you should be able to
- Explain how an LLM generates text and why it can be confidently wrong
- Write and test prompts for clinical tasks
- Read medical-LLM benchmark claims critically
- Fine-tune a small model on synthetic data and evaluate summarisation and documentation tools
Lessons
- How large language models work
Beginner · Clinical · 25 min · Exercise
- Prompting for clinical tasks
Intermediate · Technical · 30 min · Exercise
- Medical LLMs and their benchmarks
Intermediate · Clinical · 30 min · Exercise
- Hallucination and grounding
Intermediate · Clinical · 30 min · Exercise
- Fine-tuning with LoRA on synthetic data
Advanced · Technical · 35 min · Exercise
- Multimodal models: text, images and more
Intermediate · Technical · 30 min · Exercise
- Summarisation and ambient clinical documentation
Beginner · Clinical · 25 min · Exercise
Next track: Retrieval-augmented generation (RAG)
Educational content only. This material teaches methods; it is not clinical advice. Code, models and examples here are not validated medical devices and must not be used to make decisions about real patients without proper clinical validation, governance and any required regulatory approval. Examples use synthetic or openly licensed de-identified data only. Never paste identifiable patient information into public AI tools. Mentions of models, tools or vendors are for identification, not endorsement.