Towards Case-based Interpretability for Medical Federated Learning
This addresses the problem of interpretability for clinicians in privacy-sensitive medical AI, though it is incremental as it adapts existing methods to a federated setting.
The paper tackles the challenge of providing case-based explanations for AI decisions in medical federated learning, where data privacy restricts access to past examples, by using deep generative models to create synthetic examples that explain decisions while protecting privacy, with a proof-of-concept applied to pleural effusion diagnosis using Chest X-ray data.
We explore deep generative models to generate case-based explanations in a medical federated learning setting. Explaining AI model decisions through case-based interpretability is paramount to increasing trust and allowing widespread adoption of AI in clinical practice. However, medical AI training paradigms are shifting towards federated learning settings in order to comply with data protection regulations. In a federated scenario, past data is inaccessible to the current user. Thus, we use a deep generative model to generate synthetic examples that protect privacy and explain decisions. Our proof-of-concept focuses on pleural effusion diagnosis and uses publicly available Chest X-ray data.