Predetermined Change Control Plan

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

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

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

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

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

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

Lifecycle requirements for medical device software.

A structured analysis that identifies how an attacker could compromise a medical device and what controls mitigate each threat.

The federal statute that gives FDA explicit premarket authority over cybersecurity for cyber devices.

A documented, risk-based set of processes that build cybersecurity into a medical device across its full lifecycle.

Medical device that uses artificial intelligence or machine learning to perform its intended use.

Methods (SHAP, saliency maps, prototype explanations) that help users understand why a model made a given prediction.

Large pretrained model adaptable to many downstream clinical tasks via fine-tuning or prompting.

Devices that use LLMs or diffusion models to generate text, images, or recommendations within a clinical workflow.