🛰️ Daily AI Frontier
‹ back to 2026-08-23

Explainable Transformer Models for Clinical Prediction Tasks on Structured Electronic Health Records

Research Medical/Healthcare AI

Ranking

Overall 79
Content 95
Popularity 41

Observed public metrics from 1 member.

Representative image for Explainable Transformer Models for Clinical Prediction Tasks on Structured Electronic Health Records

Merged summary

TL;DR - BERT-LER is an explainable BERT-style model for structured EHR timelines, pretrained on de-identified records from 75 million patients. It combines percentile-binned laboratory values with token-level Integrated Gradients explanations, delivering competitive clinical predictions and clinically plausible attributions.

  • Represents quantitative laboratory results as discrete tokens while preserving graded information through percentile-based binning.
  • Evaluated on the public EHRShot benchmark and a real-world asthma severity progression study.
  • Matches benchmark models overall and often outperforms them on laboratory-related tasks.
  • Produces input-event attributions that align with established clinical risk factors.

Sources (1)

Explainable Transformer Models for Clinical Prediction Tasks on Structured Electronic Health Records

arXiv cs.LG Jun Ni Du, Lukas Adamek, Maxim Kryukov, Flavio Dormont, Ziv Bar-Joseph, Sven Jager, Brandon Rufino 2026-08-20 arXiv:2608.20315
Public signals Semantic Scholar citations 0 · Semantic Scholar influential citations 0
Providers: Hugging Face · N/A OpenAlex · N/A Publisher · N/A Semantic Scholar · Citations 0 · Influential citations 0 X · N/A Fetched 2026-09-02 14:15:55.162116 UTC

TL;DR - BERT-LER is an explainable BERT-style model for structured EHR timelines, pretrained on de-identified records from 75 million patients. It combines percentile-binned laboratory values with token-level Integrated Gradients explanations, delivering competitive clinical predictions and clinically plausible attributions.

  • Represents quantitative laboratory results as discrete tokens while preserving graded information through percentile-based binning.
  • Evaluated on the public EHRShot benchmark and a real-world asthma severity progression study.
  • Matches benchmark models overall and often outperforms them on laboratory-related tasks.
  • Produces input-event attributions that align with established clinical risk factors.
item →