Data extraction from free-text reports on mechanical thrombectomy in acute ischemic stroke using ChatGPT: a retrospective analysis

Background - - Procedural details of mechanical thrombectomy in patients with ischemic stroke are important predictors of clinical outcome and are collected for prospective studies or national stroke registries. To date, these data are collected manually by human readers, a labor-intensive task tha...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Lehnen, Nils Christian (VerfasserIn) , Dorn, Franziska (VerfasserIn) , Wiest, Isabella (VerfasserIn) , Zimmermann, Hanna (VerfasserIn) , Radbruch, Alexander (VerfasserIn) , Kather, Jakob Nikolas (VerfasserIn) , Paech, Daniel (VerfasserIn)
Dokumenttyp: Article (Journal)
Sprache:Englisch
Veröffentlicht: April 2024
In: Radiology
Year: 2024, Jahrgang: 311, Heft: 1, Pages: 1-8
ISSN:1527-1315
DOI:10.1148/radiol.232741
Online-Zugang:Verlag, lizenzpflichtig, Volltext: https://doi.org/10.1148/radiol.232741
Verlag, lizenzpflichtig, Volltext: https://pubs.rsna.org/doi/10.1148/radiol.232741
Volltext
Verfasserangaben:Nils C. Lehnen, MD, Franziska Dorn, MD, Isabella C. Wiest, MD, MSc, Hanna Zimmermann, MD, Alexander Radbruch, MD, JD, Jakob Nikolas Kather, MD, MSc, Daniel Paech, MD, PhD,

MARC

LEADER 00000caa a2200000 c 4500
001 1909635545
003 DE-627
005 20241205223234.0
007 cr uuu---uuuuu
008 241127s2024 xx |||||o 00| ||eng c
024 7 |a 10.1148/radiol.232741  |2 doi 
035 |a (DE-627)1909635545 
035 |a (DE-599)KXP1909635545 
035 |a (OCoLC)1475648158 
040 |a DE-627  |b ger  |c DE-627  |e rda 
041 |a eng 
084 |a 33  |2 sdnb 
100 1 |a Lehnen, Nils Christian  |e VerfasserIn  |0 (DE-588)1068546816  |0 (DE-627)820445215  |0 (DE-576)427853028  |4 aut 
245 1 0 |a Data extraction from free-text reports on mechanical thrombectomy in acute ischemic stroke using ChatGPT  |b a retrospective analysis  |c Nils C. Lehnen, MD, Franziska Dorn, MD, Isabella C. Wiest, MD, MSc, Hanna Zimmermann, MD, Alexander Radbruch, MD, JD, Jakob Nikolas Kather, MD, MSc, Daniel Paech, MD, PhD, 
264 1 |c April 2024 
300 |b Illustrationen 
300 |a 8 
336 |a Text  |b txt  |2 rdacontent 
337 |a Computermedien  |b c  |2 rdamedia 
338 |a Online-Ressource  |b cr  |2 rdacarrier 
500 |a Online veröffentlicht: 16. April 2024 
500 |a Gesehen am 27.11.2024 
520 |a Background - - Procedural details of mechanical thrombectomy in patients with ischemic stroke are important predictors of clinical outcome and are collected for prospective studies or national stroke registries. To date, these data are collected manually by human readers, a labor-intensive task that is prone to errors. - - Purpose - - To evaluate the use of the large language models (LLMs) GPT-4 and GPT-3.5 to extract data from neuroradiology reports on mechanical thrombectomy in patients with ischemic stroke. - - Materials and Methods - - This retrospective study included consecutive reports from patients with ischemic stroke who underwent mechanical thrombectomy between November 2022 and September 2023 at institution 1 and between September 2016 and December 2019 at institution 2. A set of 20 reports was used to optimize the prompt, and the ability of the LLMs to extract procedural data from the reports was compared using the McNemar test. Data manually extracted by an interventional neuroradiologist served as the reference standard. - - Results - - A total of 100 internal reports from 100 patients (mean age, 74.7 years ± 13.2 [SD]; 53 female) and 30 external reports from 30 patients (mean age, 72.7 years ± 13.5; 18 male) were included. All reports were successfully processed by GPT-4 and GPT-3.5. Of 2800 data entries, 2631 (94.0% [95% CI: 93.0, 94.8]; range per category, 61%-100%) data points were correctly extracted by GPT-4 without the need for further postprocessing. With 1788 of 2800 correct data entries, GPT-3.5 produced fewer correct data entries than did GPT-4 (63.9% [95% CI: 62.0, 65.6]; range per category, 14%-99%; P < .001). For the external reports, GPT-4 extracted 760 of 840 (90.5% [95% CI: 88.3, 92.4]) correct data entries, while GPT-3.5 extracted 539 of 840 (64.2% [95% CI: 60.8, 67.4]; P < .001). - - Conclusion - - Compared with GPT-3.5, GPT-4 more frequently extracted correct procedural data from free-text reports on mechanical thrombectomy performed in patients with ischemic stroke. - - © RSNA, 2024 - - Supplemental material is available for this article. 
700 1 |a Dorn, Franziska  |d 1976-  |e VerfasserIn  |0 (DE-588)130278580  |0 (DE-627)497359049  |0 (DE-576)298102293  |4 aut 
700 1 |a Wiest, Isabella  |d 1992-  |e VerfasserIn  |0 (DE-588)1198882956  |0 (DE-627)168103638X  |4 aut 
700 1 |a Zimmermann, Hanna  |e VerfasserIn  |4 aut 
700 1 |a Radbruch, Alexander  |d 1977-  |e VerfasserIn  |0 (DE-588)1022344501  |0 (DE-627)716953951  |0 (DE-576)362851166  |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 
700 1 |a Paech, Daniel  |d 1986-  |e VerfasserIn  |0 (DE-588)1080278214  |0 (DE-627)844124893  |0 (DE-576)453464742  |4 aut 
773 0 8 |i Enthalten in  |t Radiology  |d Oak Brook, Ill. : Soc., 1923  |g 311(2024), 1 vom: Apr., Artikel-ID e232741, Seite 1-8  |h Online-Ressource  |w (DE-627)320487253  |w (DE-600)2010588-5  |w (DE-576)094056706  |x 1527-1315  |7 nnas  |a Data extraction from free-text reports on mechanical thrombectomy in acute ischemic stroke using ChatGPT a retrospective analysis 
773 1 8 |g volume:311  |g year:2024  |g number:1  |g month:04  |g elocationid:e232741  |g pages:1-8  |g extent:8  |a Data extraction from free-text reports on mechanical thrombectomy in acute ischemic stroke using ChatGPT a retrospective analysis 
856 4 0 |u https://doi.org/10.1148/radiol.232741  |x Verlag  |x Resolving-System  |z lizenzpflichtig  |3 Volltext 
856 4 0 |u https://pubs.rsna.org/doi/10.1148/radiol.232741  |x Verlag  |z lizenzpflichtig  |3 Volltext 
951 |a AR 
992 |a 20241127 
993 |a Article 
994 |a 2024 
998 |g 1080278214  |a Paech, Daniel  |m 1080278214:Paech, Daniel  |d 50000  |e 50000PP1080278214  |k 0/50000/  |p 7  |y j 
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 6 
998 |g 1022344501  |a Radbruch, Alexander  |m 1022344501:Radbruch, Alexander  |d 50000  |e 50000PR1022344501  |k 0/50000/  |p 5 
998 |g 1198882956  |a Wiest, Isabella  |m 1198882956:Wiest, Isabella  |d 60000  |d 61100  |e 60000PW1198882956  |e 61100PW1198882956  |k 0/60000/  |k 1/60000/61100/  |p 3 
999 |a KXP-PPN1909635545  |e 4623167755 
BIB |a Y 
SER |a journal 
JSO |a {"person":[{"role":"aut","given":"Nils Christian","family":"Lehnen","display":"Lehnen, Nils Christian"},{"family":"Dorn","display":"Dorn, Franziska","role":"aut","given":"Franziska"},{"role":"aut","given":"Isabella","family":"Wiest","display":"Wiest, Isabella"},{"role":"aut","given":"Hanna","family":"Zimmermann","display":"Zimmermann, Hanna"},{"role":"aut","given":"Alexander","family":"Radbruch","display":"Radbruch, Alexander"},{"role":"aut","given":"Jakob Nikolas","family":"Kather","display":"Kather, Jakob Nikolas"},{"given":"Daniel","role":"aut","display":"Paech, Daniel","family":"Paech"}],"relHost":[{"corporate":[{"display":"Radiological Society of North America","role":"isb"}],"id":{"issn":["1527-1315"],"eki":["320487253"],"zdb":["2010588-5"]},"physDesc":[{"extent":"Online-Ressource"}],"title":[{"title":"Radiology","title_sort":"Radiology"}],"type":{"media":"Online-Ressource","bibl":"periodical"},"part":{"issue":"1","pages":"1-8","year":"2024","volume":"311","text":"311(2024), 1 vom: Apr., Artikel-ID e232741, Seite 1-8","extent":"8"},"disp":"Data extraction from free-text reports on mechanical thrombectomy in acute ischemic stroke using ChatGPT a retrospective analysisRadiology","pubHistory":["1.1923 -"],"name":{"displayForm":["The Radiological Society of North America"]},"recId":"320487253","note":["Fortsetzung der Druck-Ausgabe","Gesehen 07.11.22"],"language":["eng"],"origin":[{"publisherPlace":"Oak Brook, Ill.","dateIssuedKey":"1923","dateIssuedDisp":"1923-","publisher":"Soc."}]}],"title":[{"subtitle":"a retrospective analysis","title":"Data extraction from free-text reports on mechanical thrombectomy in acute ischemic stroke using ChatGPT","title_sort":"Data extraction from free-text reports on mechanical thrombectomy in acute ischemic stroke using ChatGPT"}],"physDesc":[{"extent":"8 S.","noteIll":"Illustrationen"}],"type":{"media":"Online-Ressource","bibl":"article-journal"},"id":{"eki":["1909635545"],"doi":["10.1148/radiol.232741"]},"name":{"displayForm":["Nils C. Lehnen, MD, Franziska Dorn, MD, Isabella C. Wiest, MD, MSc, Hanna Zimmermann, MD, Alexander Radbruch, MD, JD, Jakob Nikolas Kather, MD, MSc, Daniel Paech, MD, PhD,"]},"origin":[{"dateIssuedKey":"2024","dateIssuedDisp":"April 2024"}],"language":["eng"],"note":["Online veröffentlicht: 16. April 2024","Gesehen am 27.11.2024"],"recId":"1909635545"} 
SRT |a LEHNENNILSDATAEXTRAC2024