> ## Content Index
> Fetch the complete content index at: https://www.coios.me/llms.txt
> Use this file to discover other available public pages before exploring further.

# A local multi-agent AI system deidentified multimodal hospital data at 99.8% sensitivity
- URL: https://www.coios.me/a-local-multi-agent-ai-system-deidentified-multimodal/
- Published: 2026-09-16T21:06:26.000Z
- Updated: 2026-09-16T22:08:59.000Z
- Description: A locally deployable multi-agent system combining multimodal large language models, task-specific networks and rule-based steps removed 99.82% of injected identifiers across text, imaging, handwriting and audio while preserving 99.61% of clinically important content.
- Author: Daniel Ryan
- Tags: Emergent technology, AI in medicine, What linked data reveals, Germany, #preprint, #new, #item, #source-2026-09

The authors built and benchmarked a modular, on-premises multi-agent deidentification system across 16 orchestrator configurations, using 250 MIMIC-IV records with synthetically injected identifiers alongside head CT, face images, handwriting, audio and German clinical text. The best local configuration reached per-identifier sensitivity of 99.82% (95% CI 99.76-99.88) with clinical preservation of 99.61% per file, and matched a proprietary model on sensitivity with higher specificity. On the institution's own data, per-patient sensitivity was 100%.

*Why it is interesting: Deidentification that runs inside the hospital and keeps clinical content intact is the bottleneck for reusing multimodal records in research.*

Source

[medRxiv (preprint), 2026-09-14](https://doi.org/10.64898/2026.05.28.26353952?ref=coios.me)

DOI

10.64898/2026.05.28.26353952

Type

Preprint

Design

benchmark evaluation of 16 orchestrator model configurations on 250 MIMIC-IV patients with injected identifiers plus imaging, audio, handwriting and German clinical text, including local hospital data

Verdict

New finding

Driver

[AI in medicine](https://www.coios.me/d-ai-medicine/)

Driver

[What linked data reveals](https://www.coios.me/d-linked-data/)