Conference
Jul 2026
X-FEMR: A Token-level Explainable Approach for Electronic Health Records Foundation Models using Transformer-based Models
This work trains a Transformer-based surrogate model on input-output pairs from the FEMR across two prediction tasks, approximating its behavior while preserving temporal dynamics, and introduces a novel clinical alignment metric that quantifies the correspondence between the surrogate model’s key tokens and clinically...
Jie Huang, Peng Yin, Zihan Xu et al.
· Proceedings of the Thirty-Fi... · 0 citations