Private, fair and accurate: Training large-scale, privacy-preserving AI models in radiology. (arXiv:2302.01622v1 [eess.IV])

Artificial intelligence (AI) models are increasingly used in the medical
domain. However, as medical data is highly sensitive, special precautions to
ensure the protection of said data are required. The gold standard for privacy
preservation is the introduction of differential privacy (DP) to model
training. However, prior work has shown that DP has negative implications on
model accuracy and fairness. Therefore, the purpose of this study is to
demonstrate that the privacy-preserving training of AI models for chest
radiograph diagnosis …

ai models artificial artificial intelligence data differential privacy domain fair fairness intelligence introduction large medical medical data model training preservation privacy private protection scale special standard study training work