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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Recent advances in large language models have led to renewed interest innatural language processing in healthcare using the free text of clinicalnotes. One distinguishing characteristic of clinical notes is their long timespan over multiple long documents. The unique structure of clinical notescreates a new design choice: when the context length for a language modelpredictor is limited, which part of clinical notes should we choose as theinput? Existing studies either choose the inputs with domain knowledge orsimply truncate them. We propose a framework to analyze the sections with highpredictive power. Using MIMIC-III, we show that: 1) predictive powerdistribution is different between nursing notes and discharge notes and 2)combining different types of notes could improve performance when the contextlength is large. Our findings suggest that a carefully selected samplingfunction could enable more efficient information extraction from clinicalnotes.

Making the Most Out of the Limited Context Length: Predictive Power Varies with Clinical Note Type and Note Section