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...
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Dokumenttyp: | Article (Journal) |
| Sprache: | Englisch |
| Veröffentlicht: |
March 2024
|
| In: |
The journal of pathology
Year: 2024, Jahrgang: 262, Heft: 3, Pages: 310-319 |
| ISSN: | 1096-9896 |
| DOI: | 10.1002/path.6232 |
| Online-Zugang: | Verlag, kostenfrei, Volltext: https://doi.org/10.1002/path.6232 Verlag, kostenfrei, Volltext: https://pathsocjournals.onlinelibrary.wiley.com/doi/10.1002/path.6232 
|
| Verfasserangaben: | 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 |
MARC
| LEADER | 00000caa a2200000 c 4500 | ||
|---|---|---|---|
| 001 | 188527209X | ||
| 003 | DE-627 | ||
| 005 | 20240703163025.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 240408s2024 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1002/path.6232 |2 doi | |
| 035 | |a (DE-627)188527209X | ||
| 035 | |a (DE-599)KXP188527209X | ||
| 035 | |a (OCoLC)1443668366 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rda | ||
| 041 | |a eng | ||
| 084 | |a 33 |2 sdnb | ||
| 100 | 1 | |a Truhn, Daniel |e VerfasserIn |0 (DE-588)1047348306 |0 (DE-627)778145913 |0 (DE-576)400927314 |4 aut | |
| 245 | 1 | 0 | |a Extracting structured information from unstructured histopathology reports using generative pre-trained transformer 4 (GPT-4) |c 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 |
| 264 | 1 | |c March 2024 | |
| 300 | |a 10 | ||
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Gesehen am 08.04.2024 | ||
| 500 | |a Online veröffentlicht: 14. Dezember 2023 | ||
| 520 | |a 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. | ||
| 650 | 4 | |a artificial intelligence | |
| 650 | 4 | |a large language models | |
| 650 | 4 | |a named entity recognition | |
| 650 | 4 | |a natural language processing | |
| 650 | 4 | |a pathology report | |
| 650 | 4 | |a text mining | |
| 700 | 1 | |a Löffler, Chiara |e VerfasserIn |0 (DE-588)1254183493 |0 (DE-627)1796796646 |4 aut | |
| 700 | 1 | |a Mueller-Franzes, Gustav |e VerfasserIn |4 aut | |
| 700 | 1 | |a Nebelung, Sven |d 1986- |e VerfasserIn |0 (DE-588)1029969981 |0 (DE-627)734545851 |0 (DE-576)377792241 |4 aut | |
| 700 | 1 | |a Hewitt, Katherine J. |e VerfasserIn |4 aut | |
| 700 | 1 | |a Brandner, Sebastian |d 1981- |e VerfasserIn |0 (DE-588)139873228 |0 (DE-627)61381472X |0 (DE-576)313613613 |4 aut | |
| 700 | 1 | |a Bressem, Keno |e VerfasserIn |0 (DE-588)1188764799 |0 (DE-627)1667689347 |4 aut | |
| 700 | 1 | |a Försch, Sebastian |d 1985- |e VerfasserIn |0 (DE-588)1018553894 |0 (DE-627)682860832 |0 (DE-576)356024814 |4 aut | |
| 700 | 1 | |a Kather, Jakob Nikolas |d 1989- |e VerfasserIn |0 (DE-588)1064064914 |0 (DE-627)812897587 |0 (DE-576)423589091 |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t The journal of pathology |d Bognor Regis [u.a.] : Wiley, 1892 |g 262(2024), 3 vom: März, Seite 310-319 |h Online-Ressource |w (DE-627)269536957 |w (DE-600)1475280-3 |w (DE-576)078590132 |x 1096-9896 |7 nnas |a Extracting structured information from unstructured histopathology reports using generative pre-trained transformer 4 (GPT-4) |
| 773 | 1 | 8 | |g volume:262 |g year:2024 |g number:3 |g month:03 |g pages:310-319 |g extent:10 |a Extracting structured information from unstructured histopathology reports using generative pre-trained transformer 4 (GPT-4) |
| 856 | 4 | 0 | |u https://doi.org/10.1002/path.6232 |x Verlag |x Resolving-System |z kostenfrei |3 Volltext |
| 856 | 4 | 0 | |u https://pathsocjournals.onlinelibrary.wiley.com/doi/10.1002/path.6232 |x Verlag |z kostenfrei |3 Volltext |
| 951 | |a AR | ||
| 992 | |a 20240408 | ||
| 993 | |a Article | ||
| 994 | |a 2023 | ||
| 998 | |g 1064064914 |a Kather, Jakob Nikolas |m 1064064914:Kather, Jakob Nikolas |d 910000 |d 910100 |e 910000PK1064064914 |e 910100PK1064064914 |k 0/910000/ |k 1/910000/910100/ |p 9 |y j | ||
| 999 | |a KXP-PPN188527209X |e 4508520359 | ||
| BIB | |a Y | ||
| SER | |a journal | ||
| JSO | |a {"recId":"188527209X","physDesc":[{"extent":"10 S."}],"title":[{"title":"Extracting structured information from unstructured histopathology reports using generative pre-trained transformer 4 (GPT-4)","title_sort":"Extracting structured information from unstructured histopathology reports using generative pre-trained transformer 4 (GPT-4)"}],"type":{"bibl":"article-journal","media":"Online-Ressource"},"language":["eng"],"note":["Gesehen am 08.04.2024","Online veröffentlicht: 14. Dezember 2023"],"origin":[{"dateIssuedDisp":"March 2024","dateIssuedKey":"2024"}],"relHost":[{"id":{"doi":["10.1002/(ISSN)1096-9896"],"zdb":["1475280-3"],"issn":["1096-9896"],"eki":["269536957"]},"part":{"volume":"262","year":"2024","issue":"3","extent":"10","text":"262(2024), 3 vom: März, Seite 310-319","pages":"310-319"},"corporate":[{"role":"isb","display":"Pathological Society of Great Britain and Ireland"}],"pubHistory":["1.1892 -"],"disp":"Extracting structured information from unstructured histopathology reports using generative pre-trained transformer 4 (GPT-4)The journal of pathology","physDesc":[{"extent":"Online-Ressource"}],"recId":"269536957","type":{"media":"Online-Ressource","bibl":"periodical"},"language":["eng"],"note":["Gesehen am 28.02.08"],"title":[{"title":"The journal of pathology","title_sort":"journal of pathology","subtitle":"an official journal of the Pathological Society of Great Britain and Ireland"}],"origin":[{"publisher":"Wiley","dateIssuedKey":"1892","dateIssuedDisp":"1892-","publisherPlace":"Bognor Regis [u.a.]"}]}],"person":[{"display":"Truhn, Daniel","family":"Truhn","role":"aut","given":"Daniel"},{"family":"Löffler","role":"aut","given":"Chiara","display":"Löffler, Chiara"},{"role":"aut","given":"Gustav","family":"Mueller-Franzes","display":"Mueller-Franzes, Gustav"},{"display":"Nebelung, Sven","family":"Nebelung","role":"aut","given":"Sven"},{"role":"aut","given":"Katherine J.","family":"Hewitt","display":"Hewitt, Katherine J."},{"family":"Brandner","given":"Sebastian","role":"aut","display":"Brandner, Sebastian"},{"display":"Bressem, Keno","role":"aut","given":"Keno","family":"Bressem"},{"display":"Försch, Sebastian","family":"Försch","role":"aut","given":"Sebastian"},{"display":"Kather, Jakob Nikolas","role":"aut","given":"Jakob Nikolas","family":"Kather"}],"id":{"eki":["188527209X"],"doi":["10.1002/path.6232"]},"name":{"displayForm":["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"]}} | ||
| SRT | |a TRUHNDANIEEXTRACTING2024 | ||