Healthcare AI Learning
Course overview

Module 2 · 120 min

Healthcare Data

EHR structures, imaging, notes and wearables; provenance, time windows, informative missingness, dataset shift, target leakage, FHIR versus SNOMED CT, and what the European Health Data Space changes.

Lesson progress
0 / 11 steps
Not started
Learning objectives
  • Describe the main healthcare data modalities and interrogate the provenance of each.
  • Specify a prediction task with an explicit index time, observation window, prediction window and outcome window.
  • Recognise informative missingness and explain why 'missing' is itself a clinical measurement.
  • Judge whether a dataset represents the population the model will actually serve, and name the shift you fear.
  • Detect target leakage in a proposed feature set before it reaches a model.
  • Explain what FHIR and SNOMED CT each contribute, and why exchange structure/interoperability and clinical terminology/semantics are complementary but distinct concerns.
  • Explain what the European Health Data Space changes about secondary use of health data.
  • Run a structured data readiness assessment and defend a go / fix-first / no-go recommendation.

Data Readiness Assessment

14 items grouped into 5 domains. Score a real dataset — one you have, or the readmission case above. Each item is scored 0 to 3; the maximum is 42. Your answers are saved in this browser and stay there.

Educational decision-support framework — not a validated readiness score, clinical instrument or regulatory checklist. The bands below are course heuristics, not evidence-based cut-offs.
Problem definition & timing
Item 1 · Outcome definition

Is the outcome defined unambiguously and recorded consistently?

Problem definition & timing
Item 2 · Index time & windows

Is the index time defined, and does it match the moment an intervention can start?

Problem definition & timing
Item 3 · Availability at T₀

Is every candidate feature demonstrably available and visible in the system before the index time?

Data quality & provenance
Item 4 · Provenance & documentation

Is the provenance of each data element documented — who generated it, why, and under which system version?

Data quality & provenance
Item 5 · Missingness

Is missingness quantified per variable, with a stated reason for absence?

Data quality & provenance
Item 6 · Measurement consistency

Are units, reference ranges, coding systems and analyser changes reconciled across the period?

Generalisation & evaluation
Item 7 · Representativeness

Has the cohort been compared with the population the model will serve?

Generalisation & evaluation
Item 8 · Validation strategy

Is the validation strategy explicitly linked to the intended generalisation claim?

Generalisation & evaluation
Item 9 · Leakage review

Has the feature set been reviewed for target, decision and preprocessing leakage?

Generalisation & evaluation
Item 10 · Splitting integrity

Do evaluation splits preserve patient-level independence, and are they site-aware when site generalisation is claimed?

Governance & operations
Item 11 · Legal basis & privacy

Is the legal basis, consent position and de-identification approach documented and approved?

Governance & operations
Item 12 · Ownership & monitoring

Is there an owner, a monitoring plan and a stopping rule after deployment?

Interoperability & reproducibility
Item 13 · Linkage & interoperability

Can records be linked across sites and systems, and are codes mapped to a shared terminology?

Interoperability & reproducibility
Item 14 · Reproducibility & infrastructure

Can the exact dataset behind a result be rebuilt months later?

Result

0 / 42

0 of 14 items scored. Complete all items for a banded recommendation.

Problem definition & timing0 / 9
Data quality & provenance0 / 9
Generalisation & evaluation0 / 12
Governance & operations0 / 6
Interoperability & reproducibility0 / 6
Sources & evidence · 19 sources

This module cites primary legal, standards and specifications, public or consensus guidance, scholarly literature, technical documentation, other cited references.

Content reviewed: September 2026. Publication dates of the individual sources are shown in each citation.

  • Regulation (EU) 2025/327 of the European Parliament and of the Council on the European Health Data Space.

    The primary legal text for both primary and secondary use of electronic health data in the EU. In force since 26 March 2025, with staged application: implementing acts due 2027, main provisions from 2029 and remaining categories from 2031 (status checked August 2026).

    Open source

  • European Commission — European Health Data Space: regulation and implementation timeline.

    Official overview of the EHDS regime, its phased application dates and secondary-use arrangements including the individual opt-out.

    Open source

  • FDA, Health Canada and MHRA — Good Machine Learning Practice for Medical Device Development: Guiding Principles (October 2021).

    Ten guiding principles published jointly in October 2021 by the U.S. FDA, Health Canada and the UK MHRA, covering intended-population representativeness of datasets and independence of training and test data. The IMDRF later issued a related draft on good machine learning practice in June 2024; check both before citing.

    Open source

  • Regulation (EU) 2016/679 (General Data Protection Regulation), in particular Articles 5, 9, 32 and 89.

    Lawful basis and safeguards for processing special-category health data, including research purposes.

    Open source

  • Regulation (EU) 2024/1689 (Artificial Intelligence Act), Articles 10 and 15.

    Data and data-governance requirements for high-risk AI systems: relevance, representativeness, error-freedom to the extent possible, and examination for bias. Consolidated text as amended by Regulation (EU) 2026/1744 (in force 27 July 2026).

    Open source

  • HL7 FHIR — R5 (v5.0.0, STU) is the current published release; R4 and R4B remain widely deployed (version status checked 10 September 2026).

    The resource and profiling model for health data exchange; supports RESTful APIs and search as well as document, messaging and service-based exchange paradigms. Which release a system implements is a procurement question rather than a fixed fact — verify the published current version before relying on it.

    Open source

  • SNOMED International — SNOMED CT starter guide and editorial guide.

    The clinical terminology: concepts, hierarchies, post-coordination and value sets.

    Open source

  • Regenstrief Institute — LOINC.

    Identifiers for laboratory tests, measurements and clinical observations.

    Open source

  • OHDSI — The Book of OHDSI (OMOP Common Data Model).

    Reference for standardising observational health data so studies replicate across sites.

    Open source

  • Collins GS, Moons KGM, Dhiman P, et al. TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods. BMJ 2024;385:e078378.

    The reporting standard to demand for any prediction model — including cohort, index time, predictors and missing-data handling.

    Open source

  • Gianfrancesco MA, Tamang S, Yazdany J, Schmajuk G. Potential biases in machine learning algorithms using electronic health record data. JAMA Intern Med 2018;178(11):1544–1547.

    The canonical short account of missingness, misclassification and informed presence in EHR-derived data.

  • Obermeyer Z, Powers B, Vogeli C, Mullainathan S. Dissecting racial bias in an algorithm used to manage the health of populations. Science 2019;366(6464):447–453.

    How a cost proxy for health need produced large-scale racial bias — the standard example of label choice as an equity decision.

  • Wong A, Otles E, Donnelly JP, et al. External validation of a widely implemented proprietary sepsis prediction model in hospitalized patients. JAMA Intern Med 2021;181(8):1065–1070.

    What happens when a widely deployed model meets external data and real alert burden.

  • Finlayson SG, Subbaswamy A, Singh K, et al. The clinician and dataset shift in artificial intelligence. N Engl J Med 2021;385(3):283–286.

    A practical taxonomy of dataset shift written for clinicians rather than statisticians.

  • Kaushal A, Altman R, Langlotz C. Geographic distribution of US cohorts used to train deep learning algorithms. JAMA 2020;324(12):1212–1213.

    Concrete evidence of how narrow the geographic base of published clinical AI actually is.

  • Sáez C, Gutiérrez-Sacristán A, Kohane I, García-Gómez JM, Avillach P. EHRtemporalVariability: delineating temporal dataset shifts in electronic health records. GigaScience 2020;9(8):giaa079.

    Methods for detecting the temporal shifts caused by system, coding and protocol changes.

  • Groenwold RHH. Informative missingness in electronic health record systems: the curse of knowing. Diagn Progn Res 2020;4:8.

    Why the act of measuring is itself data, and what that means for imputation.

  • Rajkomar A, Oren E, Chen K, et al. Scalable and accurate deep learning with electronic health records. npj Digital Medicine 2018;1:18.

    A reference point for FHIR-based feature pipelines and rigorous temporal cohort construction.

  • Kapoor S, Narayanan A. Leakage and the reproducibility crisis in machine-learning-based science. Patterns 2023;4(9):100804.

    A taxonomy of leakage types across scientific fields, with the specific errors reproduced in the Leakage Detective.

Capstone Board Pack

Add what you just learned to your own strategy document while it is fresh.

Open capstone