Medical AI · Track 1 of 10
Foundations
What AI in healthcare is, the kinds of data it learns from, the standards that hold that data together, and the statistics needed to judge any model.
Start here whether you are a clinician or a developer. No prior AI knowledge needed.
By the end of this track you should be able to
- Describe where AI is used across care, research and operations, and where it is not ready
- Recognise the main healthcare data types and the standards used to exchange them
- Explain how de-identification and privacy law shape what data you can use
- Calculate and interpret sensitivity, specificity, predictive values, ROC curves and calibration
Lessons
- The healthcare-AI landscape: what is in use, what works, and what to ask
Beginner · Clinical · 20 min
- Healthcare data types: records, images, signals, notes and omics
Beginner · Clinical · 25 min · Exercise
- Data standards: FHIR, HL7, ICD, SNOMED CT, LOINC and OMOP
Beginner · Technical · 30 min · Exercise
- Privacy and de-identification: HIPAA, GDPR and India's DPDP Act
Beginner · Clinical · 30 min · Exercise
- Setting up Python and Colab for clinical data work
Beginner · Technical · 30 min · Exercise
- Diagnostic accuracy metrics: sensitivity, specificity, PPV, ROC and calibration
Beginner · Clinical · 25 min · Exercise
Next track: Machine learning
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.