AI-Based Synthetic Data in Biomedicine: A Decade of Growth and a Persistent Translation Gap
- 1Hebrew University
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.
Related
- Gender Disparity in Movement Disorders Research Authorship: Progress and Persistent Gaps Across a Decade
- Persistent shortfalls in government health expenditure: a decade-long analysis of Abuja 15% target attainment across 52 African countries, 2014-2023.
- Artificial Intelligence-Driven Dietary Assessment Software: A Structured Narrative Review of Technological Advances, Persistent Measurement Error and Barriers to Clinical Translation
- A transient RNP compartment boosts translation and growth of mammalian oocytes
- YY1 Suppresses Tumor Growth by Negatively Regulating the Expression and Translation Activity of eIF4E in Nasopharyngeal Carcinoma
BibTeX
@misc{asgari2026aibased,
title = {{AI-Based Synthetic Data in Biomedicine: A Decade of Growth and a Persistent Translation Gap}},
author = {N. Asgari and I. F. Perez and G. Epelde and L. Zhang and L. Horesh and C. Saab and M. Muszkat and M. Rosen-Zvi},
howpublished = {medRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.12.26360876},
url = {https://www.medrxiv.org/content/10.64898/2026.09.12.26360876v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - AI-Based Synthetic Data in Biomedicine: A Decade of Growth and a Persistent Translation Gap
AU - N. Asgari
AU - I. F. Perez
AU - G. Epelde
AU - L. Zhang
AU - L. Horesh
AU - C. Saab
AU - M. Muszkat
AU - M. Rosen-Zvi
PY - 2026
DA - 2026/09/12
PB - medRxiv
DO - 10.64898/2026.09.12.26360876
UR - https://www.medrxiv.org/content/10.64898/2026.09.12.26360876v1
AB - 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.
ER -