A 7-criteria evaluation approach for the responsible use of synthetic medical data
BJR|Artificial Intelligence · 23.01.2026 · 3 (1)
DOI: 10.1093/bjrai/ubag005 ↗Kurz gefasst
Fachartikel in der Zeitschrift BJR|Artificial Intelligence, online erschienen am 11.08.2026. Verfasst von Ghada Zamzmi und 5 weiteren Autor:innen. Beteiligte Einrichtung: Division of Imaging, Diagnostics, and Software Reliability, Office of Science and Engineering Laboratories, Food and Drug Administration (FDA), Silve…. Die Arbeit nennt 48 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Purpose
To develop an approach for evaluating and reporting the quality of synthetic medical data (SMDs).
Method
As SMDs become increasingly common, their responsible utilization benefits from a detailed characterization of their quality and value within the intended usage context. Here, we introduce an approach to assess SMDs across 7 dimensions: Congruence, Coverage, Constraint, Consistency, Comprehension, Compliance, and Completeness. We also describe an approach for reporting the quality of synthetic data to stakeholders.
Results
We applied the proposed approach to 7 digital mammography datasets. The analysis underscored the strengths and limitations of each dataset across these dimensions. For example, while datasets generated by generative AI methods show high Congruence, they often fall short in Constraint and Completeness compared to those generated by knowledge-based methods. Additionally, our findings highlighted that the quality of generated data varies across different subgroups (eg, breast density) with certain subgroups (ie, dense and hetero) showing lower quality. This suggests that subgroup-specific fine-tuning of the generative process may have an effect on downstream tasks.
Conclusions
The proposed approach provides stakeholders with a tool for assessing data quality, which may be used to better understand and analyse synthetic datasets.. Advances in knowledge This study introduces an approach for assessing SMD quality. The approach offers a practical mechanism for reporting SMD quality, which can enhance the reliability and usefulness of synthetic datasets.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Division of Imaging, Diagnostics, and Software Reliability, Office of Science and Engineering Laboratories, Food and Drug Administration (FDA), Silver Spring, MD 10903, United States.
ORCID-Profile: Ghada Zamzmi, Aldo Badano
Zitieren
APA
Zamzmi, G., Subbaswamy, A., Deshpande, R., Sharma, D., Delfino, J. G., & Badano, A. (2026). A 7-criteria evaluation approach for the responsible use of synthetic medical data. BJR|Artificial Intelligence, 3(1). https://doi.org/10.1093/bjrai/ubag005
Vancouver
Zamzmi G, Subbaswamy A, Deshpande R, Sharma D, Delfino JG, Badano A. A 7-criteria evaluation approach for the responsible use of synthetic medical data. BJR|Artificial Intelligence. 2026;3(1). doi:10.1093/bjrai/ubag005
BibTeX
@article{Zamzmi2026,
author = {Zamzmi, Ghada and Subbaswamy, Adarsh and Deshpande, Rucha and Sharma, Diksha and Delfino, Jana G and Badano, Aldo},
title = {A 7-criteria evaluation approach for the responsible use of synthetic medical data},
journal = {BJR|Artificial Intelligence},
year = {2026},
volume = {3},
number = {1},
doi = {10.1093/bjrai/ubag005}
}
EUVIMED