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

A key component of deep learning (DL) for natural language processing (NLP)is word embeddings. Word embeddings that effectively capture the meaning andcontext of the word that they represent can significantly improve theperformance of downstream DL models for various NLP tasks. Many existing wordembeddings techniques capture the context of words based on word co-occurrencein documents and text; however, they often cannot capture broaderdomain-specific relationships between concepts that may be crucial for the NLPtask at hand. In this paper, we propose a method to integrate externalknowledge from medical terminology ontologies into the context captured by wordembeddings. Specifically, we use a medical knowledge graph, such as the unifiedmedical language system (UMLS), to find connections between clinical terms incancer pathology reports. This approach aims to minimize the distance betweenconnected clinical concepts. We evaluate the proposed approach using aMultitask Convolutional Neural Network (MT-CNN) to extract six cancercharacteristics -- site, subsite, laterality, behavior, histology, and grade --from a dataset of ~900K cancer pathology reports. The results show that theMT-CNN model which uses our domain informed embeddings outperforms the sameMT-CNN using standard word2vec embeddings across all tasks, with an improvementin the overall micro- and macro-F1 scores by 4.97\%and 22.5\%, respectively.

Integration of Domain Knowledge using Medical Knowledge Graph Deep Learning for Cancer Phenotyping