{
  "abstract": "AI-generated synthetic data are increasingly used to address data scarcity, privacy constraints and experimental limitations in biomedicine, but how far these methods have translated into practice remains unclear. We conducted a systematic mapping and bibliometric analysis of 4,143 publications spanning 2015-2025, combining expert annotation with LLM-assisted classification across data modality, medical domain, paper type, deployment status and research stance. Publication volume grew continuously; 77.8% of papers were strongly supportive while critical work remained below 1%. Medical imaging dominated the corpus, consistent with well-characterized transformation-group invariances supporting data augmentation and generative modeling. Highly cited primary research concentrated disproportionately in molecular and pharmaceutical applications, where SE(3)-equivariant architectures and structure-prediction models accelerated generative approaches. Only 27 publications reported operational use; omics and tabular clinical data, lacking well-characterized invariance structures, remained underrepresented. These findings reveal a gap between methodological growth and deployment, motivating investment in evaluation standards, deployment reporting and encoding domain-relevant invariances.",
  "abstract_shown": true,
  "affiliations": [
    "Hebrew University"
  ],
  "article_type": "PUBLISHAHEADOFPRINT",
  "arxiv": null,
  "author_total": 8,
  "authors": [
    {
      "name": "N. Asgari"
    },
    {
      "name": "I. F. Perez"
    },
    {
      "name": "G. Epelde"
    },
    {
      "name": "L. Zhang"
    },
    {
      "name": "L. Horesh"
    },
    {
      "name": "C. Saab"
    },
    {
      "name": "M. Muszkat"
    },
    {
      "affs": [
        0
      ],
      "name": "M. Rosen-Zvi"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/1sjjeznbbkdx7.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.09.12.26360876",
  "fulltext_url": "https://www.medrxiv.org/content/10.64898/2026.09.12.26360876v1.full",
  "id": "1sjjeznbbkdx7",
  "issns": [],
  "landing_url": "https://www.medrxiv.org/content/10.64898/2026.09.12.26360876v1",
  "language": null,
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "medrxiv",
      "health informatics"
    ],
    [
      "openalex",
      "2718|Artificial Intelligence in Healthcare and Education"
    ]
  ],
  "openalex": "W7213222543",
  "pdf_url": "https://www.medrxiv.org/content/10.64898/2026.09.12.26360876v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-12",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/1sjjeznbbkdx7.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:18:33Z",
      "native_id": "10.64898/2026.09.12.26360876",
      "source": "medrxiv",
      "url": "https://www.medrxiv.org/content/10.64898/2026.09.12.26360876v1"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "medrxiv:health informatics",
      "subfield": "epidemiology-public-health"
    }
  ],
  "title": "AI-Based Synthetic Data in Biomedicine: A Decade of Growth and a Persistent Translation Gap",
  "title_text": "AI-Based Synthetic Data in Biomedicine: A Decade of Growth and a Persistent Translation Gap",
  "type": "preprint",
  "updated_at": "2026-10-30T12:18:33Z",
  "url": "https://research.draconitic.com/paper/1sjjeznbbkdx7",
  "venue": "medRxiv",
  "versions": []
}