NOTES / PART 4 · APPLIED AND REFERENCE

12Healthcare AI

Applying all of the above where mistakes cost the most.

THIS SECTION COVERS

Clinical NLP, evidence appraisal, clinical decision support, validation and safety in medical settings, privacy and regulation.

Related: Safety and guardrails · Evals and observability

TOPICS · 6/6 WRITTEN

  1. 12.1The healthcare AI landscapeWhere AI is used in healthcare, how fast-moving the regulated-device picture is, what the WHO says about large multimodal models, and why medicine raises the bar on everything else in these notes.
  2. 12.2Clinical NLPHow clinical text becomes structured data: sections, entities, assertion status such as negation, concept normalisation, and where LLMs fit and fail, including summary error types.
  3. 12.3Evidence appraisalHow to judge a medical AI claim: GRADE certainty, the difference between reporting guidelines and risk-of-bias tools, and which guideline fits which study stage.
  4. 12.4Clinical decision supportWhat clinical decision support is, why alerts fail, how the US FDA separates device from non-device CDS in broad terms, and how human factors decide whether a tool helps.
  5. 12.5Validation and safety in medicineThe validation ladder from internal tests to trials and monitoring, why external validation matters (with the Epic sepsis model as a cautionary case), and why site shift happens.
  6. 12.6Privacy and regulationHIPAA de-identification routes, GDPR's two-layer rule for health data, the EU AI Act in outline, and what to ask before sending clinical text to any model. Concepts only, not legal advice.