English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In this work we introduce Labrador, a pre-trained Transformer model forlaboratory data. Labrador and BERT were pre-trained on a corpus of 100 millionlab test results from electronic health records (EHRs) and evaluated on variousdownstream outcome prediction tasks. Both models demonstrate mastery of thepre-training task but neither consistently outperform XGBoost on downstreamsupervised tasks. Our ablation studies reveal that transfer learning showslimited effectiveness for BERT and achieves marginal success with Labrador. Weexplore the reasons for the failure of transfer learning and suggest that thedata generating process underlying each patient cannot be characterizedsufficiently using labs alone, among other factors. We encourage future work tofocus on joint modeling of multiple EHR data categories and to includetree-based baselines in their evaluations.

Labrador: Exploring the Limits of Masked Language Modeling for Laboratory Data