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/

Zendy Plus

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

Zendy Tools

Zendy Open

Background. Large Language Models (LLMs) hold promise for improving geneticvariant literature review in clinical testing. We assessed GenerativePretrained Transformer 4's (GPT-4) performance, nondeterminism, and drift toinform its suitability for use in complex clinical processes. Methods. A2-prompt process for classification of functional evidence was optimized usinga development set of 45 articles. The prompts asked GPT-4 to supply allfunctional data present in an article related to a variant or indicate that nofunctional evidence is present. For articles indicated as containing functionalevidence, a second prompt asked GPT-4 to classify the evidence into pathogenic,benign, or intermediate/inconclusive categories. A final test set of 72manually classified articles was used to test performance. Results. Over a2.5-month period (Dec 2023-Feb 2024), we observed substantial differences inintraday (nondeterminism) and across day (drift) results, which lessened after1/18/24. This variability is seen within and across models in the GPT-4 series,affecting different performance statistics to different degrees. Twenty runsafter 1/18/24 identified articles containing functional evidence with 92.2%sensitivity, 95.6% positive predictive value (PPV) and 86.3% negativepredictive value (NPV). The second prompt's identified pathogenic functionalevidence with 90.0% sensitivity, 74.0% PPV and 95.3% NVP and for benignevidence with 88.0% sensitivity, 76.6% PPV and 96.9% NVP. Conclusion.Nondeterminism and drift within LLMs must be assessed and monitored whenintroducing LLM based functionality into clinical workflows. Failing to do thisassessment or accounting for these challenges could lead to incorrect ormissing information that is critical for patient care. The performance of ourprompts appears adequate to assist in article prioritization but not inautomated decision making.

Preparing to Integrate Generative Pretrained Transformer Series 4 models  into Genetic Variant Assessment Workflows: Assessing Performance, Drift, and  Nondeterminism Characteristics Relative to Classifying Functional Evidence in  Literature