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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Food effect summarization from New Drug Application (NDA) is an essentialcomponent of product-specific guidance (PSG) development and assessment.However, manual summarization of food effect from extensive drug applicationreview documents is time-consuming, which arouses a need to develop automatedmethods. Recent advances in large language models (LLMs) such as ChatGPT andGPT-4, have demonstrated great potential in improving the effectiveness ofautomated text summarization, but its ability regarding the accuracy insummarizing food effect for PSG assessment remains unclear. In this study, weintroduce a simple yet effective approach, iterative prompting, which allowsone to interact with ChatGPT or GPT-4 more effectively and efficiently throughmulti-turn interaction. Specifically, we propose a three-turn iterativeprompting approach to food effect summarization in which the keyword-focusedand length-controlled prompts are respectively provided in consecutive turns torefine the quality of the generated summary. We conduct a series of extensiveevaluations, ranging from automated metrics to FDA professionals and evenevaluation by GPT-4, on 100 NDA review documents selected over the past fiveyears. We observe that the summary quality is progressively improved throughoutthe process. Moreover, we find that GPT-4 performs better than ChatGPT, asevaluated by FDA professionals (43% vs. 12%) and GPT-4 (64% vs. 35%).Importantly, all the FDA professionals unanimously rated that 85% of thesummaries generated by GPT-4 are factually consistent with the golden referencesummary, a finding further supported by GPT-4 rating of 72% consistency. Theseresults strongly suggest a great potential for GPT-4 to draft food effectsummaries that could be reviewed by FDA professionals, thereby improving theefficiency of PSG assessment cycle and promoting the generic drug productdevelopment.

Leveraging GPT-4 for Food Effect Summarization to Enhance Product-Specific Guidance Development via Iterative Prompting