Large language models as a diagnostic support tool in neuropathology

The WHO guidelines for classifying central nervous system (CNS) tumours are changing considerably with each release. The classification of CNS tumours is uniquely complex among most other solid tumours as it incorporates not just morphology, but also genetic and epigenetic features. Keeping current with these changes across medical fields can be challenging, even for clinical specialists. Large language models (LLMs) have demonstrated their ability to parse and process complex medical text, but their utility in neuro-oncology has not been systematically tested. We hypothesised that LLMs can effectively diagnose neuro-oncology cases from free-text histopathology reports according to the latest WHO guidelines. To test this hypothesis, we evaluated the performance of ChatGPT-4o, Claude-3.5-sonnet, and Llama3 across 30 challenging neuropathology cases, which each presented a complex mix of morphological and genetic information relevant to the diagnosis. Furthermore, we integrated these models with the latest WHO guidelines through Retrieval-Augmented Generation (RAG) and again assessed their diagnostic accuracy. Our data show that LLMs equipped with RAG, but not without RAG, can accurately diagnose the neuropathological tumour subtype in 90% of the tested cases. This study lays the groundwork for a new generation of computational tools that can assist neuropathologists in their daily reporting practice.

Authors

Institutions

Publication Details

Journal
The Journal of Pathology Clinical Research
Published
2024-11-01
DOI
https://doi.org/10.1002/2056-4538.70009
Citations
19
Primary Topic
Artificial Intelligence in Healthcare and Education
Type
article
Field-Weighted Citation Impact
2.29

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Large language models as a diagnostic support tool in neuropathology

Sebastian Brandner, Laura Bejan, Thomas O Millner, Isabella C. Wiest et al.
19 citations
The Journal of Pathology Clinical Research
Artificial Intelligence in Healthcare and Education
2.29
article

Large language models as a diagnostic support tool in neuropathology

Sebastian Brandner, Laura Bejan, Thomas O Millner, Isabella C. Wiest, Katherine Hewitt, Zunamys I. Carrero, Jakob Nikolas Kather
article en
19 citations

Abstract

The WHO guidelines for classifying central nervous system (CNS) tumours are changing considerably with each release. The classification of CNS tumours is uniquely complex among most other solid tumours as it incorporates not just morphology, but also genetic and epigenetic features. Keeping current with these changes across medical fields can be challenging, even for clinical specialists. Large language models (LLMs) have demonstrated their ability to parse and process complex medical text, but their utility in neuro-oncology has not been systematically tested. We hypothesised that LLMs can effectively diagnose neuro-oncology cases from free-text histopathology reports according to the latest WHO guidelines. To test this hypothesis, we evaluated the performance of ChatGPT-4o, Claude-3.5-sonnet, and Llama3 across 30 challenging neuropathology cases, which each presented a complex mix of morphological and genetic information relevant to the diagnosis. Furthermore, we integrated these models with the latest WHO guidelines through Retrieval-Augmented Generation (RAG) and again assessed their diagnostic accuracy. Our data show that LLMs equipped with RAG, but not without RAG, can accurately diagnose the neuropathological tumour subtype in 90% of the tested cases. This study lays the groundwork for a new generation of computational tools that can assist neuropathologists in their daily reporting practice.

The Journal of Pathology Clinical ResearchVol. 10(6)
Queen Mary University of London (GB), Heidelberg University (DE), University Hospital Heidelberg (DE), National Center for Tumor Diseases (DE), National Hospital for Neurology and Neurosurgery (GB), University Medical Centre Mannheim (DE), University Hospital Carl Gustav Carus (DE), University College London (GB)
Pfizer, AstraZeneca, National Institute for Health and Care Research, Department of Health and Social Care, European Commission, Deutscher Akademischer Austauschdienst, Bundesministerium für Bildung und Forschung, Eisai, Deutsche Krebshilfe, University College London Hospitals NHS Foundation Trust, National Institutes of Health, HORIZON EUROPE Framework Programme, German Academic Exchange Service London, Bundesministerium für Umwelt, Naturschutz, nukleare Sicherheit und Verbraucherschutz, Leeds Biomedical Research Centre, NIH Clinical Center, H2020 European Research Council, HORIZON EUROPE European Innovation Council
Quality Education
Openalex Percentile: Top 11%
Artificial Intelligence in Healthcare and Education
2.29
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.