Learning from the past, structuring the future: using large language models to unlock a century of paediatric research in Archives of Disease in Childhood

Abstract

Background and aims: the centenary of Archives of Disease in Childhood (ADC) presents an opportunity to reflect on a century of paediatric research and consider how best to leverage this ever-growing repository for future use. While content is indexed via PubMed and medical subject headings terms, this provides a superficial representation of complex journal content, leading to limited accessibility. We discuss the potential utility of large language models (LLMs)—advanced artificial intelligence systems that can understand, summarise and generate human-like language—and demonstrate their feasibility for structuring historical ADC articles, proposing a future pipeline to enhance indexing, retrieval and discoverability.

Methods: for demonstrative purposes, five articles from ADC December 1999 issue were locally downloaded and processed using a closed deployment of an LLM, Mistral (V.0.3, 7B). A structured prompt was used to extract key metadata. Outputs were manually compared with source texts and scored for accuracy. Hallucinations, fabricated or incorrect outputs, were recorded.

Results: the LLM achieved a mean accuracy of 86.9%, aligning with previous benchmarks for medical research assistance. No hallucinations were identified. Some repetition and verbosity were noted, likely due to chunk-based processing, but key fields were accurately extracted when explicitly present.

Conclusion: ADC holds a vast but underutilised body of research. This article shows that lightweight, locally hosted LLMs could structure ADC content without compromising intellectual property. Such methods could enable improved access, support automation of systematic reviews and enhance discoverability through biomedical ontologies, laying the foundation for a searchable, semantically enriched Archives that bridges historical insight with modern research needs.

More information

Identifiers

ORCID for Zachary Green: orcid.org/0000-0002-2907-5538

ORCID for James Ashton: orcid.org/0000-0003-0348-8198

Catalogue record

Export record

Altmetrics