MedTech Terms
    The authoritative reference
    All pathsSoftware · Data · RA · 9 terms

    SaMD & AI/ML Devices

    From SaMD basics to PCCPs and Good Machine Learning Practice for AI-enabled devices.

    Your progress
    0 of 9 lessons complete · up next: Software as a Medical Device
    Start path
    1. 1
      Software & AI

      Software as a Medical Device(SaMD)

      Software intended for medical purposes that performs without being part of a hardware device.

      Why this term here: The regulatory category for standalone software. Focus on the IMDRF framing and when software is a device at all.

    2. 2
      Software & AI

      Software in a Medical Device(SiMD)

      Software embedded in or required to operate a hardware medical device.

      Why this term here: Software inside a hardware device. Focus on how SiMD changes your risk analysis and lifecycle scope versus SaMD.

    3. 3
      Standards

      IEC 62304

      Lifecycle requirements for medical device software.

      Why this term here: The software lifecycle standard regulators expect. Focus on the process artifacts, not just the class assignment.

    4. 4
      Software & AI

      Software Safety Classification

      IEC 62304 classes A, B, C reflecting potential harm from software failure.

      Why this term here: Class A/B/C drives how much process rigor applies. Focus on how you justify the class in the risk file.

    5. 5
      Software & AI

      Software of Unknown Provenance(SOUP)

      Software not developed for medical device use, or lacking adequate development records, incorporated into a device.

      Why this term here: Third-party software you did not develop. Focus on the evidence you need to keep and the update cadence.

    6. 6
      Software & AI

      Clinical Decision Support(CDS)

      Software providing healthcare professionals with knowledge and patient-specific information.

      Why this term here: Clinical Decision Support. Focus on the four-factor test that determines whether CDS is a device.

    7. 7
      Software & AI

      Predetermined Change Control Plan(PCCP)

      FDA mechanism to pre-authorize specific modifications to AI/ML-enabled devices.

      Why this term here: The mechanism to update a model without a new submission. Focus on what belongs in the plan and what does not.

    8. 8
      Software & AI

      Good Machine Learning Practice(GMLP)

      Guiding principles for the development of AI/ML-enabled medical devices.

      Why this term here: FDA/Health Canada/MHRA principles for AI/ML devices. Focus on the principles most examined in submissions.

    9. 9
      Software & AI

      Interoperability

      Ability of devices and systems to exchange and use information.

      Why this term here: How your software plays with EHRs and other devices. Focus on FDA's interoperability guidance and IEEE 11073.

    Finished the path? Test yourself with a quiz tailored to these 9 terms.

    Take the SaMD & AI/ML Devices quiz