LENS uses content filtering to help identify certain types of inappropriate text and visual content before they come into a board. These safeguards focus on clear categories of prohibited content.

It is important to understand what these filters evaluate and their current limitations, particularly when it comes to Protected Health Information (PHI).

LENS maintains a default text blocklist designed to filter explicit or abusive language.

The blocklist focuses on obvious prohibited terms, including:

Note: The text blocklist is intentionally simple and focuses on specific prohibited terms rather than interpreting the context or meaning surrounding a word.

LENS performs basic default moderation of images and videos. Visual content is evaluated for:

Drug paraphernalia is not currently flagged by this moderation process. This helps prevent needles and other medical tools from being incorrectly flagged when they appear in clinical contexts.

The current LENS text blocklist is not designed to reliably identify Protected Health Information (PHI).

Because the blocklist focuses on specific prohibited words, reliably identifying PHI would require more advanced, specialized classification beyond simple keyword filtering.

PHI detection is not currently supported for visual content.

The image moderation technology used by LENS does not provide categories for identifying PHI, such as:

Note: Content moderation should not be considered a PHI detection tool. Users should continue to follow their organization’s policies and procedures when adding content to LENS.

We’re here to help — email us at LENSsupport@vizientinc.com or click the Help button on your LENS board.