---
title: "Medtech Model Evidence Export — DICOM utility skill"
description: "Exports sanitized metadata, parameters, reproducibility details, quality metrics, and optional review artifacts from Medical AI inference runs or evidence packs to MLflow. Use after inference, including NV-Generate runs; not for live training tracking, model registration, or clinical use."
canonical: https://nvidia-medtech.github.io/skills/medtech-model-evidence-export.html
audience: [engineer]
last_updated: 2026-09-29
source: skills/medtech-model-evidence-export.html
---
# Medtech Model Evidence Export

DICOM utility · no GPU required

DICOM utility

Exports sanitized metadata, parameters, reproducibility details, quality metrics, and optional review artifacts from Medical AI inference runs or evidence packs to MLflow. Use after inference, including NV-Generate runs; not for live training tracking, model registration, or clinical use.

[Skill on GitHub](https://github.com/NVIDIA-Medtech/medical-AI-skills/tree/dev/skills/medtech-model-evidence-export) [Agent Skills spec](https://agentskills.io)

### Run it with an agent

Install the skill, then just ask your agent in plain language. `medagent.medtech_model_evidence_export`

install skill Copy

```bash
npx skills add NVIDIA-Medtech/medical-AI-skills --skill medtech-model-evidence-export
```

Try saying

“Show what this NV-Generate CT evidence pack would send to MLflow without contacting a tracking server.”

“Export this completed inference run to Databricks MLflow and include reviewable slice previews, but not the raw NIfTI volumes. The workspace is approved for these images.”

[Skill on GitHub →](https://github.com/NVIDIA-Medtech/medical-AI-skills/tree/dev/skills/medtech-model-evidence-export) Validation: [Benchmark](https://github.com/NVIDIA-Medtech/medical-AI-skills/blob/dev/skills/medtech-model-evidence-export/BENCHMARK.md)·[Evals](https://github.com/NVIDIA-Medtech/medical-AI-skills/tree/dev/skills/medtech-model-evidence-export/evals)·[Tests](https://github.com/NVIDIA-Medtech/medical-AI-skills/tree/dev/skills/medtech-model-evidence-export/tests)·[Validators](https://github.com/NVIDIA-Medtech/medical-AI-skills/tree/dev/skills/medtech-model-evidence-export/validators) [How agent skills work](https://agentskills.io)

Engineering & research use only — header-level utility, not de-identification or clinical clearance. Skills follow the open [Agent Skills spec](https://agentskills.io).