Differential privacy for medical deep learning: methods, tradeoffs, and deployment implications

TL;DR

This review examines recent advances in applying differential privacy to medical deep learning, highlighting tradeoffs between privacy, accuracy, and fairness across various methods and settings.

Contribution

It synthesizes current research on DP in medical DL, emphasizing the challenges, tradeoffs, and emerging approaches, and identifies gaps in fairness and evaluation standards.

Findings

Strong privacy budgets can preserve performance in imaging tasks

Privacy often degrades model accuracy in complex or underrepresented modalities

Demographic fairness is disproportionately impacted by privacy constraints

Abstract

Differential privacy (DP) is a key technique for protecting sensitive patient data in medical deep learning (DL). As clinical models grow more data-dependent, balancing privacy with utility and fairness has become a critical challenge. This scoping review synthesizes recent developments in applying DP to medical DL, with a particular focus on DP-SGD and alternative mechanisms across centralized and federated settings. Using a structured search strategy, we identified 74 studies published up to March 2025. Our analysis spans diverse data modalities, training setups, and downstream tasks, and highlights the tradeoffs between privacy guarantees, model accuracy, and subgroup fairness. We find that while DP-especially at strong privacy budgets-can preserve performance in well-structured imaging tasks, severe degradation often occurs under strict privacy, particularly in underrepresented or complex modalities. Furthermore, privacy-induced performance gaps disproportionately affect demographic subgroups, with fairness impacts varying by data type and task. A small subset of studies explicitly addresses these tradeoffs through subgroup analysis or fairness metrics, but most omit them entirely. Beyond DP-SGD, emerging approaches leverage alternative mechanisms, generative models, and hybrid federated designs, though reporting remains inconsistent. We conclude by outlining key gaps in fairness auditing, standardization, and evaluation protocols, offering guidance for future work toward equitable and clinically robust privacy-preserving DL systems in medicine.