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

Automated classification of chief complaints from patient-generated text is acritical first step in developing scalable platforms to triage patients withouthuman intervention. In this work, we evaluate several approaches to chiefcomplaint classification using a novel Chief Complaint (CC) Dataset thatcontains ~200,000 patient-generated reasons-for-visit entries mapped to a setof 795 discrete chief complaints. We examine the use of several fine-tunedbidirectional transformer (BERT) models trained on both unrelated texts as wellas on the CC dataset. We contrast this performance with a TF-IDF baseline. Ourevaluation has three components: (1) a random test hold-out from the originaldataset; (2) a "misspelling set," consisting of a hand-selected subset of thetest set, where every entry has at least one misspelling; (3) a separateexperimenter-generated free-text set. We find that the TF-IDF model performssignificantly better than the strongest BERT-based model on the test (best BERTPR-AUC $0.3597 \pm 0.0041$ vs TF-IDF PR-AUC $0.3878 \pm 0.0148$, $p=7\cdot10^{-5}$), and is statistically comparable to the misspelling sets (best BERTPR-AUC $0.2579 \pm 0.0079$ vs TF-IDF PR-AUC $0.2733 \pm 0.0130$, $p=0.06$).However, when examining model predictions on experimenter-generated queries,some concerns arise about TF-IDF baseline's robustness. Our results suggestthat in certain tasks, simple language embedding baselines may be veryperformant; however, truly understanding their robustness requires furtheranalysis.

Evaluating robustness of language models for chief complaint extraction from patient-generated text