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

Objective: The 2022 n2c2 NLP Challenge posed identification of socialdeterminants of health (SDOH) in clinical narratives. We present three systemsthat we developed for the Challenge and discuss the distinctive taskformulation used in each of the three systems. Materials and Methods: The firstsystem identifies target pieces of information independently using machinelearning classifiers. The second system uses a large language model (LLM) toextract complete structured outputs per document. The third system extractscandidate phrases using machine learning and identifies target relations withhand-crafted rules. Results: The three systems achieved F1 scores of 0.884,0.831, and 0.663 in the Subtask A of the Challenge, which are ranked third,seventh, and eighth among the 15 participating teams. The review of theextraction results from our systems reveals characteristics of each approachand those of the SODH extraction task. Discussion: Phrases and relationsannotated in the task is unique and diverse, not conforming to the conventionalevent extraction task. These annotations are difficult to model with limitedtraining data. The system that extracts information independently, ignoring theannotated relations, achieves the highest F1 score. Meanwhile, LLM with itsversatile capability achieves the high F1 score, while respecting the annotatedrelations. The rule-based system tackling relation extraction obtains the lowF1 score, while it is the most explainable approach. Conclusion: The F1 scoresof the three systems vary in this challenge setting, but each approach hasadvantages and disadvantages in a practical application. The selection of theapproach depends not only on the F1 score but also on the requirements in theapplication.

Task formulation for Extracting Social Determinants of Health from Clinical Narratives