{
  "id": 6771,
  "url": "https://arxiv.org/abs/2604.09645v1",
  "title": "Generating High Quality Synthetic Data for Dutch Medical Conversations",
  "summary": "Medical conversations offer insights into clinical communication often absent from Electronic Health Records. However, developing reliable clinical Natural Language Processing (NLP) models is hampered by the scarcity of domain-specific datasets, as clinical data are typically inaccessible due to privacy and ethical constraints. To address these challenges, we present a pipeline for generating synthetic Dutch medical dialogues using a Dutch fine-tuned Large Language Model, with real medical conve",
  "authors": "Cecilia Kuan, Aditya Kamlesh Parikh, Henk van den Heuvel",
  "category": "research",
  "topics": "privacy-surveillance,healthcare",
  "orgs": null,
  "regions": null,
  "published_at": "2026-03-25T10:27:12.000Z",
  "fetched_at": "2026-07-14T16:32:45.891Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/6771",
  "original_url": "https://arxiv.org/abs/2604.09645v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}