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: We aim to learn potential novel cures for diseases fromunstructured text sources. More specifically, we seek to extract drug-diseasepairs of potential cures to diseases by a simple reasoning over the structureof spoken text.  Materials and Methods: We use Google Cloud to transcribe podcast episodes ofan NPR radio show. We then build a pipeline for systematically pre-processingthe text to ensure quality input to the core classification model, which feedsto a series of post-processing steps for obtaining filtered results. Ourclassification model itself uses a language model pre-trained on PubMed text.The modular nature of our pipeline allows for ease of future developments inthis area by substituting higher quality components at each stage of thepipeline. As a validation measure, we use ROBOKOP, an engine over a medicalknowledge graph with only validated pathways, as a ground truth source forchecking the existence of the proposed pairs. For the proposed pairs not foundin ROBOKOP, we provide further verification using Chemotext.  Results: We found 30.4% of our proposed pairs in the ROBOKOP database. Forexample, our model successfully identified that Omeprazole can help treatheartburn.We discuss the significance of this result, showing some examples ofthe proposed pairs.  Discussion and Conclusion: The agreement of our results with the existingknowledge source indicates a step in the right direction. Given theplug-and-play nature of our framework, it is easy to add, remove, or modifyparts to improve the model as necessary. We discuss the results showing someexamples, and note that this is a potentially new line of research that hasfurther scope to be explored. Although our approach was originally oriented onradio podcast transcripts, it is input-agnostic and could be applied to anysource of textual data and to any problem of interest.

Text Mining to Identify and Extract Novel Disease Treatments From Unstructured Datasets