Extracting structured information from unstructured histopathology reports using generative pre-trained transformer 4 (GPT-4)
Deep learning applied to whole-slide histopathology images (WSIs) has the potential to enhance precision oncology and alleviate the workload of experts. However, developing these models necessitates large amounts of data with ground truth labels, which can be both time-consuming and expensive to obt...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article (Journal) |
| Language: | English |
| Published: |
March 2024
|
| In: |
The journal of pathology
Year: 2024, Volume: 262, Issue: 3, Pages: 310-319 |
| ISSN: | 1096-9896 |
| DOI: | 10.1002/path.6232 |
| Online Access: | Verlag, kostenfrei, Volltext: https://doi.org/10.1002/path.6232 Verlag, kostenfrei, Volltext: https://pathsocjournals.onlinelibrary.wiley.com/doi/10.1002/path.6232 
|
| Author Notes: | Daniel Truhn, Chiara M. L. Loeffler, Gustav Mueller-Franzes, Sven Nebelung, Katherine J. Hewitt, Sebastian Brandner, Keno K. Bressem, Sebastian Foersch and Jakob Nikolas Kather |
| Summary: | Deep learning applied to whole-slide histopathology images (WSIs) has the potential to enhance precision oncology and alleviate the workload of experts. However, developing these models necessitates large amounts of data with ground truth labels, which can be both time-consuming and expensive to obtain. Pathology reports are typically unstructured or poorly structured texts, and efforts to implement structured reporting templates have been unsuccessful, as these efforts lead to perceived extra workload. In this study, we hypothesised that large language models (LLMs), such as the generative pre-trained transformer 4 (GPT-4), can extract structured data from unstructured plain language reports using a zero-shot approach without requiring any re-training. We tested this hypothesis by utilising GPT-4 to extract information from histopathological reports, focusing on two extensive sets of pathology reports for colorectal cancer and glioblastoma. We found a high concordance between LLM-generated structured data and human-generated structured data. Consequently, LLMs could potentially be employed routinely to extract ground truth data for machine learning from unstructured pathology reports in the future.(c) 2023 The Authors. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland. |
|---|---|
| Item Description: | Gesehen am 08.04.2024 Online veröffentlicht: 14. Dezember 2023 |
| Physical Description: | Online Resource |
| ISSN: | 1096-9896 |
| DOI: | 10.1002/path.6232 |