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

Medical conversations between patients and medical professionals haveimplicit functional sections, such as "history taking", "summarization","education", and "care plan." In this work, we are interested in learning toautomatically extract these sections. A direct approach would requirecollecting large amounts of expert annotations for this task, which isinherently costly due to the contextual inter-and-intra variability betweenthese sections. This paper presents an approach that tackles the problem oflearning to classify medical dialogue into functional sections withoutrequiring a large number of annotations. Our approach combines pseudo-labelingand human-in-the-loop. First, we bootstrap using weak supervision withpseudo-labeling to generate dialogue turn-level pseudo-labels and train atransformer-based model, which is then applied to individual sentences tocreate noisy sentence-level labels. Second, we iteratively refinesentence-level labels using a cluster-based human-in-the-loop approach. Eachiteration requires only a few dozen annotator decisions. We evaluate theresults on an expert-annotated dataset of 100 dialogues and find that while ourmodels start with 69.5% accuracy, we can iteratively improve it to 82.5%. Thecode used to perform all experiments described in this paper can be found here:https://github.com/curai/curai-research/tree/main/functional-sections.

Learning functional sections in medical conversations: iterative pseudo-labeling and human-in-the-loop approach