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

We propose CHiLL (Crafting High-Level Latents), an approach fornatural-language specification of features for linear models. CHiLL promptsLLMs with expert-crafted queries to generate interpretable features from healthrecords. The resulting noisy labels are then used to train a simple linearclassifier. Generating features based on queries to an LLM can empowerphysicians to use their domain expertise to craft features that are clinicallymeaningful for a downstream task of interest, without having to manuallyextract these from raw EHR. We are motivated by a real-world risk predictiontask, but as a reproducible proxy, we use MIMIC-III and MIMIC-CXR data andstandard predictive tasks (e.g., 30-day readmission) to evaluate this approach.We find that linear models using automatically extracted features arecomparably performant to models using reference features, and provide greaterinterpretability than linear models using "Bag-of-Words" features. We verifythat learned feature weights align well with clinical expectations.

CHiLL: Zero-shot Custom Interpretable Feature Extraction from Clinical Notes with Large Language Models