Tayebi Arasteh, Ziller et al. investigate how strict privacy safeguards affect AI learning in medical imaging. Their study finds that while enforcing privacy leads to a modest drop in accuracy, it does not exacerbate biases for different patient groups, though accuracy for intricate cases and specific subgroups may be more affected.
- Soroosh Tayebi Arasteh
- Alexander Ziller
- Georgios Kaissis
