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

TL;DR

This study introduces an iterative prompting method using GPT-4 to automate and improve the accuracy of food effect summarization from NDA documents, aiding product-specific guidance development.

Contribution

It presents a multi-turn iterative prompting approach with keyword and length control, demonstrating enhanced summary quality and factual consistency over previous methods.

Findings

GPT-4 outperforms ChatGPT in accuracy and consistency.

85% of GPT-4 summaries are factually aligned with references.

Iterative prompting improves summary quality over multiple turns.

Abstract

Food effect summarization from New Drug Application (NDA) is an essential component of product-specific guidance (PSG) development and assessment. However, manual summarization of food effect from extensive drug application review documents is time-consuming, which arouses a need to develop automated methods. Recent advances in large language models (LLMs) such as ChatGPT and GPT-4, have demonstrated great potential in improving the effectiveness of automated text summarization, but its ability regarding the accuracy in summarizing food effect for PSG assessment remains unclear. In this study, we introduce a simple yet effective approach, iterative prompting, which allows one to interact with ChatGPT or GPT-4 more effectively and efficiently through multi-turn interaction. Specifically, we propose a three-turn iterative prompting approach to food effect summarization in which the keyword-focused and length-controlled prompts are respectively provided in consecutive turns to refine the quality of the generated summary. We conduct a series of extensive evaluations, ranging from automated metrics to FDA professionals and even evaluation by GPT-4, on 100 NDA review documents selected over the past five years. We observe that the summary quality is progressively improved throughout the process. Moreover, we find that GPT-4 performs better than ChatGPT, as evaluated by FDA professionals (43% vs. 12%) and GPT-4 (64% vs. 35%). Importantly, all the FDA professionals unanimously rated that 85% of the summaries generated by GPT-4 are factually consistent with the golden reference summary, a finding further supported by GPT-4 rating of 72% consistency. These results strongly suggest a great potential for GPT-4 to draft food effect summaries that could be reviewed by FDA professionals, thereby improving the efficiency of PSG assessment cycle and promoting the generic drug product development.