MedTech Terms
    The authoritative reference
    Back to AI/ML Devices Deep Dive
    Software & AIAI / ML in DevicesSoftware Lifecycle

    Model Card

    Structured documentation of a machine learning model's intended use, performance, and limitations.

    Reviewed by Christian Espinosa, Founder, Blue Goat CyberLast reviewed September 19, 2026

    Definition

    A model card summarizes a model's purpose, training and evaluation data, performance metrics across relevant subgroups, ethical considerations, and known limitations to support transparent, responsible use. Model cards were proposed by Mitchell and colleagues in 2019 and are now used widely in AI documentation. In MedTech, they help meet transparency expectations such as FDA, Health Canada and MHRA's 2024 transparency principles for machine learning devices, and FDA's draft guidance suggests a model card format for labeling. They should be written for the intended user and kept in sync with the authorized device version.
    What the regulation says
    Regulators increasingly expect transparency in AI/ML-enabled MedTech. The FDA

    What this means in practice

    Increasingly expected by regulators (e.g., FDA's transparency principles for ML-enabled devices) and procurement teams. Often combined with 'Indications-for-Use'-style cards for clinical AI.

    Examples

    • A MedTech company developing an AI diagnostic tool for radiology creates a model card detailing the training data's demographic representation and the model's sensitivity and specificity across different patient populations.
    • Before deploying an AI-powered insulin pump, the manufacturer publishes a model card outlining the algorithm's performance under various physiological conditions and known limitations, such as interaction with specific medications.
    • A hospital procurement team reviews the model card for an AI-driven surgical planning system to assess its suitability for their patient demographics and to understand its validation against relevant clinical endpoints.
    Common pitfalls
    • •Failing to update model cards when models are retrained or modified, leading to outdated or inaccurate information, is a common pitfall.
    • •Overlooking the inclusion of performance metrics for all relevant subgroups, which can mask biases or disparities, is a mistake to avoid.
    • •Presenting overly technical information without clear, concise summaries for diverse audiences can hinder effective communication.
    • •Ignoring the iterative nature of AI development and not treating the model card as a living document can lead to compliance issues.

    Frequently asked questions

    The primary purpose is to provide a structured, transparent summary of an AI/ML model's characteristics, performance, and limitations, facilitating responsible development and deployment in MedTech.

    Cross-references

    Used by

    Related terms

    Grouped by theme
    Cited by

    Where this term appears across MedTech Terms.

    Learning paths (1)

    Latest in MedTech

    Sources

    3 sources

    Every citation below opens the original document. Each is graded against our source-tier hierarchy so you can see what rests on binding law versus commentary.

    Tier 2Regulator guidance and consensus· 3
    Link health: 3 verified· last checked 2026-06-20
    1. 1
      FDA Transparency Principles for ML Devices
      Tier 2 Verified
      FDAfda.gov
    2. 2
      FDA - Software as a Medical Device (SaMD)
      Tier 2 Verified
      FDAfda.gov
    3. 3
      FDA - AI/ML-Enabled Medical Devices
      Tier 2 Verified
      FDAfda.gov

    Inline markers like [1] jump to the matching reference above.