Documentation completeness and demographic representativeness of public dental imaging datasets: a cross-sectional analysis of repository metadata

Diana Belkis Moreno Benítez, Roberto Antonio Vega Bonilla, Flor M Escalante Freitez and Drflorescalante@gmail.com

SAP Artificial Intelligence in Dentistry, 2026

Abstract: Introduction: Public dental imaging datasets are the fuel of dental artificial intelligence, but their documentation and their demographic composition are rarely described in the studies that use them. Methods: A cross-sectional sample of public dental imaging datasets was assembled from a public model repository, and each dataset's metadata was assessed for documentation completeness and for the presence of demographic information in its description. Results: Among 13 datasets, 5 (38.5%; 95% CI 17.7 to 64.5) carried a license and 9 (69.2%) carried a readme, while only 5 (38.5%) mentioned any demographic variable, and none mentioned sex or race or ethnicity. Conclusions: Public dental imaging datasets are documented incompletely and almost never describe the demographic composition of their subjects, which limits their reuse and obscures the representativeness of the models trained on them.

Date: 2026
References: Add references at CitEc
Citations:

Downloads: (external link)
https://southam.pub/journals/files/aid/aid2026137en.pdf (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:cwf:aidart:aid2026137

DOI: 10.62486/aid2026137

Access Statistics for this article

More articles in SAP Artificial Intelligence in Dentistry from South American Publishing
Bibliographic data for series maintained by South American Publishing Journals Manager ().