Representation and Bias in Artificial Intelligence Models for Thyroid Cancer: A Systematic Review
Authors' conclusion
The findings highlight significant gaps in the diversity and representativeness of data used in thyroid cancer AI models. Current models align with epidemiological trends but lack comprehensive demographic inclusion.
Study context
- Population
- Studies of AI models for thyroid cancer management providing demographic details; EMBASE, PubMed and Google Scholar up to January 2024
- Participants
- 197 studies
- Outcome
- Demographic representation in thyroid cancer AI model studies
Methodological detailsPRISMA-reported, Cochrane handbook, two independent reviewers
- PRISMA-reported
- Cochrane handbook
- Two independent reviewers
Pooled result
As reported in the abstract
- Studies focusing on diagnosis
- 133
- Studies focusing on prediction/prognosis
- 47
- Studies with participants from China
- 124
- Studies with participants from the US
- 26
- Female participants
- 12,410
- Male participants
- 4222
- East Asians (underrepresented; global thyroid cancer prevalence 18.7%)
- 14.6%
- White participants (overrepresented; global prevalence 20.7%)
- 26.8%
- Black participants (overrepresented; global prevalence 11.3%)
- 26.8%
Original publication
Representation and Bias in Artificial Intelligence Models for Thyroid Cancer: A Systematic Review. Thyroid. Published 28 August 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →