Chapter 7 Review of Data-Driven Generative AI Models for Knowledge Extraction from Scientific Literature in Healthcare

TL;DR

This review explores the evolution of NLP-based text summarization, focusing on generative AI models like GPT-3 and GPT-4, and assesses their potential and challenges in healthcare scientific literature analysis.

Contribution

It provides a comparative analysis of abstractive and extractive summarization techniques, highlighting recent advances with pre-trained models in healthcare literature.

Findings

GPT-4 outperforms GPT-3 in scientific summarization

Limited adoption of generative models in healthcare NLP

Challenges include accuracy and potential biases

Abstract

This review examines the development of abstractive NLP-based text summarization approaches and compares them to existing techniques for extractive summarization. A brief history of text summarization from the 1950s to the introduction of pre-trained language models such as Bidirectional Encoder Representations from Transformer (BERT) and Generative Pre-training Transformers (GPT) are presented. In total, 60 studies were identified in PubMed and Web of Science, of which 29 were excluded and 24 were read and evaluated for eligibility, resulting in the use of seven studies for further analysis. This chapter also includes a section with examples including an example of a comparison between GPT-3 and state-of-the-art GPT-4 solutions in scientific text summarisation. Natural language processing has not yet reached its full potential in the generation of brief textual summaries. As there are acknowledged concerns that must be addressed, we can expect gradual introduction of such models in practise.