> ## Documentation Index
> Fetch the complete documentation index at: https://medlogprotocol.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Storage and retention

> Logging volume depends on workflow design; retention policies keep it manageable.

Recording model use creates substantial storage and data management requirements. Logging volume depends
on workflow design, inference frequency, deployment duration, and operational scale.

These requirements are consistent with broader trends in healthcare data generation, which is projected to
exceed **10,800 exabytes annually by 2025**, with a single hospitalization producing on the order of
**150,000 data elements**. MedLog extends existing clinical data systems by recording model inputs,
outputs, metadata, and optional execution traces associated with AI use.

## Retention strategies

Institutions may retain all MedLog records for retrospective analysis or apply selective retention
policies to manage storage, cost, and operational requirements. Retention strategies include:

<AccordionGroup>
  <Accordion title="Full tracing" icon="flask">
    During pilot studies or after major model updates.
  </Accordion>

  <Accordion title="Sampling or risk-triggered tracing" icon="shuffle">
    During steady-state deployment.
  </Accordion>

  <Accordion title="Tiered retention" icon="layer-group">
    With long-term summaries and shorter-lived detailed artifacts.
  </Accordion>
</AccordionGroup>