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: Clinical deep phenotyping and phenotype annotation play a criticalrole in both the diagnosis of patients with rare disorders as well as inbuilding computationally-tractable knowledge in the rare disorders field. Theseprocesses rely on using ontology concepts, often from the Human PhenotypeOntology, in conjunction with a phenotype concept recognition task (supportedusually by machine learning methods) to curate patient profiles or existingscientific literature. With the significant shift in the use of large languagemodels (LLMs) for most NLP tasks, we examine the performance of the latestGenerative Pre-trained Transformer (GPT) models underpinning ChatGPT as afoundation for the tasks of clinical phenotyping and phenotype annotation.Materials and Methods: The experimental setup of the study included sevenprompts of various levels of specificity, two GPT models (gpt-3.5-turbo andgpt-4.0) and two established gold standard corpora for phenotype recognition,one consisting of publication abstracts and the other clinical observations.Results: Our results show that, with an appropriate setup, these models canachieve state of the art performance. The best run, using few-shot learning,achieved 0.58 macro F1 score on publication abstracts and 0.75 macro F1 scoreon clinical observations, the former being comparable with the state of theart, while the latter surpassing the current best in class tool. Conclusion:While the results are promising, the non-deterministic nature of the outcomes,the high cost and the lack of concordance between different runs using the sameprompt and input make the use of these LLMs challenging for this particulartask.

An evaluation of GPT models for phenotype concept recognition