loading page

Self-Aware SGD: Reliable Incremental Adaptation Framework For Clinical AI Models
  • +2
  • Anshul Thakur ,
  • Jacob Armstrong ,
  • Alexey Youssef ,
  • David Eyre ,
  • David A. Clifton
Anshul Thakur
University of Oxford

Corresponding Author:[email protected]

Author Profile
Jacob Armstrong
Author Profile
Alexey Youssef
Author Profile
David Eyre
Author Profile
David A. Clifton
Author Profile

Abstract

Healthcare is dynamic as demographics, diseases, and therapeutics constantly evolve. This dynamic nature induces inevitable distribution shifts in populations targeted by clinical AI models, often rendering them ineffective. Incremental learning provides an effective method of adapting deployed clinical models to accommodate these contemporary distribution shifts. However, since incremental learning involves modifying a deployed or in-use model, it can be considered unreliable as any adverse modification due to maliciously compromised or incorrectly labelled data can make the model unsuitable for the targeted application. This paper introduces self-aware stochastic gradient descent (SGD), an incremental deep learning algorithm that utilises a contextual bandit-like sanity check to only allow reliable modifications to a model. The contextual bandit analyses incremental gradient updates to isolate and filter unreliable gradients. This behaviour allows self-aware SGD to balance incremental training and integrity of a deployed model. Experimental evaluations on the Oxford University Hospital datasets highlight that self-aware SGD can provide reliable incremental updates for overcoming distribution shifts in challenging conditions induced by label noise
Mar 2023Published in IEEE Journal of Biomedical and Health Informatics volume 27 issue 3 on pages 1624-1634. 10.1109/JBHI.2023.3237592