Privacy-Preserving Active Learning for precision oncology clinical workflows with inverse simulation verification

Описание и применение

Прототип объединяет федеративное обучение с дифференциальной приватностью, активное обучение и обратную симуляцию для проверки решений модели в онкологии.

Задача

How to train clinically meaningful models on highly sensitive, small, non‑IID oncology datasets without exposing patient data and while providing clinicians a falsifiable audit of model behavior.

Результат

Active learning combined with client‑level DP‑SGD achieved comparable AUROC to random sampling at a higher privacy budget (ε=3 vs ε=8) on a synthetic oncology benchmark, while the inverse‑simulation verifier provided a falsifiable audit of model decisions.

Рабочий процесс

• 1. Deploy a central orchestrator that aggregates encrypted gradients and verification data.
• 2. Each hospital trains a local model with DP‑SGD and per‑feature‑group adaptive clipping.
• 3. Local models send encrypted gradients and acquisition scores to the orchestrator.
• 4. The orchestrator updates the global model and plans active queries for unlabeled cases.
• 5. Hospitals annotate selected cases and send labels back to the orchestrator.
• 6. The inverse‑simulation verifier reconstructs the decision boundary and checks for clinical plausibility.
• 7. The updated global model is redistributed to hospitals for the next round.

Доказательства

The hard part was trust — specifically, how do you prove that a model trained on data it never saw actually learned something clinically meaningful?

Источник

One interesting finding from my experimentation with client‑level DP: the privacy‑utility curve is flatter when you combine it with active learning.

Источник

In my synthetic oncology benchmark, active learning + DP‑SGD at ε=3 matched random sampling + DP‑SGD at ε=8 on AUROC for the actionable‑variant classification task.

Источник