GPT-4 generates accurate and readable patient education materials aligned with current oncological guidelines: a randomized assessment

Introduction and aim Guideline-based patient educational materials (PEMs) empower patients and reduce misinformation, but require frequent updates and must be adapted to the readability level of patients. The aim is to assess whether generative artificial intelligence (GenAI) can provide readable, a...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Rodler, Severin (VerfasserIn) , Cei, Francesco (VerfasserIn) , Ganjavi, Conner (VerfasserIn) , Checcucci, Enrico (VerfasserIn) , Backer, Pieter De (VerfasserIn) , Belenchon, Ines Rivero (VerfasserIn) , Taratkin, Mark (VerfasserIn) , Puliatti, Stefano (VerfasserIn) , Veccia, Alessandro (VerfasserIn) , Piazza, Pietro (VerfasserIn) , Baekelandt, Loïc (VerfasserIn) , Kowalewski, Karl-Friedrich (VerfasserIn) , Rivas, Juan Gómez (VerfasserIn) , Fankhauser, Christian D. (VerfasserIn) , Moschini, Marco (VerfasserIn) , Gandaglia, Giorgio (VerfasserIn) , Campi, Riccardo (VerfasserIn) , Abreu, Andre De Castro (VerfasserIn) , Russo, Giorgio I. (VerfasserIn) , Cocci, Andrea (VerfasserIn) , Maruccia, Serena (VerfasserIn) , Cacciamani, Giovanni E. (VerfasserIn)
Dokumenttyp: Article (Journal)
Sprache:Englisch
Veröffentlicht: June 4, 2025
In: PLOS ONE
Year: 2025, Jahrgang: 20, Heft: 6, Pages: 1-14
ISSN:1932-6203
DOI:10.1371/journal.pone.0324175
Online-Zugang:Verlag, kostenfrei, Volltext: https://doi.org/10.1371/journal.pone.0324175
Verlag, kostenfrei, Volltext: http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0324175
Volltext
Verfasserangaben:Severin Rodler, Francesco Cei, Conner Ganjavi, Enrico Checcucci, Pieter De Backer, Ines Rivero Belenchon, Mark Taratkin, Stefano Puliatti, Alessandro Veccia, Pietro Piazza, Loïc Baekelandt, Karl-Friedrich Kowalewski, Juan Gómez Rivas, Christian D. Fankhauser, Marco Moschini, Giorgio Gandaglia, Riccardo Campi, Andre De Castro Abreu, Giorgio I. Russo, Andrea Cocci, Serena Maruccia, Giovanni E. Cacciamani, YAU Collaborators

MARC

LEADER 00000naa a2200000 c 4500
001 1932991123
003 DE-627
005 20250812102305.0
007 cr uuu---uuuuu
008 250812s2025 xx |||||o 00| ||eng c
024 7 |a 10.1371/journal.pone.0324175  |2 doi 
035 |a (DE-627)1932991123 
035 |a (DE-599)KXP1932991123 
040 |a DE-627  |b ger  |c DE-627  |e rda 
041 |a eng 
084 |a 11  |2 sdnb 
100 1 |a Rodler, Severin  |d 1993-  |e VerfasserIn  |0 (DE-588)1202854095  |0 (DE-627)1687408505  |4 aut 
245 1 0 |a GPT-4 generates accurate and readable patient education materials aligned with current oncological guidelines  |b a randomized assessment  |c Severin Rodler, Francesco Cei, Conner Ganjavi, Enrico Checcucci, Pieter De Backer, Ines Rivero Belenchon, Mark Taratkin, Stefano Puliatti, Alessandro Veccia, Pietro Piazza, Loïc Baekelandt, Karl-Friedrich Kowalewski, Juan Gómez Rivas, Christian D. Fankhauser, Marco Moschini, Giorgio Gandaglia, Riccardo Campi, Andre De Castro Abreu, Giorgio I. Russo, Andrea Cocci, Serena Maruccia, Giovanni E. Cacciamani, YAU Collaborators 
264 1 |c June 4, 2025 
300 |b Diagramme 
300 |a 14 
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 12.08.2025 
520 |a Introduction and aim Guideline-based patient educational materials (PEMs) empower patients and reduce misinformation, but require frequent updates and must be adapted to the readability level of patients. The aim is to assess whether generative artificial intelligence (GenAI) can provide readable, accurate, and up-to-date PEMs that can be subsequently translated into multiple languages for broad dissemination. Study design and methods The European Association of Urology (EAU) guidelines for prostate, bladder, kidney, and testicular cancer were used as the knowledge base for GPT-4 to generate PEMs. Additionally, the PEMs were translated into five commonly spoken languages within the European Union (EU). The study was conducted through a single-blinded, online randomized assessment survey. After an initial pilot assessment of the GenAI-generated PEMs, thirty-two members of the Young Academic Urologists (YAU) groups evaluated the accuracy, completeness, and clarity of the original versus GPT-generated PEMs. The translation assessment involved two native speakers from different YAU groups for each language: Dutch, French, German, Italian, and Spanish. The primary outcomes were readability, accuracy, completeness, faithfulness, and clarity. Readability was measured using Flesch Kincaid Reading Ease (FKRE), Flesch Kincaid Grade Level (FKGL), Gunning Fog (GFS) scores and Smog (SI), Coleman Liau (CLI), Automated Readability (ARI) indexes. Accuracy, completeness, faithfulness, and clarity were rated on a 5-item Likert scale. Results The mean time to create layperson PEMs based on the latest guideline by GPT-4 was 52.1 seconds. The readability scores for the 8 original PEMs were lower than for the 8 GPT-4-generated PEMs (Mean FKRE: 43.5 vs. 70.8; p < .001). The required reading education levels were higher for original PEMs compared to GPT-4 generated PEMs (Mean FKGL: 11.6 vs. 6.1; p < .001). For all urological localized cancers, the original PEMs were not significantly different from the GPT-4 generated PEMs in accuracy, completeness, and clarity. Similarly, no differences were observed for metastatic cancers. Translations of GPT-generated PEMs were rated as faithful in 77.5% of cases and clear in 67.5% of cases. Conclusions and relevance GPT-4 generated PEMs have better readability levels compared to original PEMs while maintaining similar accuracy, completeness, and clarity. The use of GenAI’s information extraction and language capabilities, integrated with human oversight, can significantly reduce the workload and ensure up-to-date and accurate PEMs. Patient summary Some cancer facts made for patients can be hard to read or not in the right words for those with prostate, bladder, kidney, or testicular cancer. This study used AI to quickly make short and easy-to-read content from trusted facts. Doctors checked the AI content and found that they were just as accurate, complete, and clear as the original text made for patients. They also worked well in many languages. This AI tool can assist providers in making it easier for patients to understand their cancer and the best care they can get. 
650 4 |a Bladder cancer 
650 4 |a European Union 
650 4 |a Internet 
650 4 |a Patients 
650 4 |a Prostate cancer 
650 4 |a Renal cell carcinoma 
650 4 |a Testicular cancer 
650 4 |a Urology 
700 1 |a Cei, Francesco  |e VerfasserIn  |4 aut 
700 1 |a Ganjavi, Conner  |e VerfasserIn  |4 aut 
700 1 |a Checcucci, Enrico  |e VerfasserIn  |4 aut 
700 1 |a Backer, Pieter De  |e VerfasserIn  |4 aut 
700 1 |a Belenchon, Ines Rivero  |e VerfasserIn  |4 aut 
700 1 |a Taratkin, Mark  |e VerfasserIn  |4 aut 
700 1 |a Puliatti, Stefano  |e VerfasserIn  |4 aut 
700 1 |a Veccia, Alessandro  |e VerfasserIn  |4 aut 
700 1 |a Piazza, Pietro  |e VerfasserIn  |4 aut 
700 1 |a Baekelandt, Loïc  |e VerfasserIn  |4 aut 
700 1 |a Kowalewski, Karl-Friedrich  |d 1989-  |e VerfasserIn  |0 (DE-588)1100724192  |0 (DE-627)859518825  |0 (DE-576)469770740  |4 aut 
700 1 |a Rivas, Juan Gómez  |e VerfasserIn  |4 aut 
700 1 |a Fankhauser, Christian D.  |e VerfasserIn  |4 aut 
700 1 |a Moschini, Marco  |e VerfasserIn  |4 aut 
700 1 |a Gandaglia, Giorgio  |e VerfasserIn  |4 aut 
700 1 |a Campi, Riccardo  |e VerfasserIn  |4 aut 
700 1 |a Abreu, Andre De Castro  |e VerfasserIn  |4 aut 
700 1 |a Russo, Giorgio I.  |e VerfasserIn  |4 aut 
700 1 |a Cocci, Andrea  |e VerfasserIn  |4 aut 
700 1 |a Maruccia, Serena  |e VerfasserIn  |4 aut 
700 1 |a Cacciamani, Giovanni E.  |e VerfasserIn  |4 aut 
773 0 8 |i Enthalten in  |t PLOS ONE  |d San Francisco, California, US : PLOS, 2006  |g 20(2025), 6, Artikel-ID e0324175, Seite 1-14  |h Online-Ressource  |w (DE-627)523574592  |w (DE-600)2267670-3  |w (DE-576)281331979  |x 1932-6203  |7 nnas  |a GPT-4 generates accurate and readable patient education materials aligned with current oncological guidelines a randomized assessment 
773 1 8 |g volume:20  |g year:2025  |g number:6  |g elocationid:e0324175  |g pages:1-14  |g extent:14  |a GPT-4 generates accurate and readable patient education materials aligned with current oncological guidelines a randomized assessment 
856 4 0 |u https://doi.org/10.1371/journal.pone.0324175  |x Verlag  |x Resolving-System  |z kostenfrei  |3 Volltext 
856 4 0 |u http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0324175  |x Verlag  |z kostenfrei  |3 Volltext 
951 |a AR 
992 |a 20250812 
993 |a Article 
994 |a 2025 
998 |g 1100724192  |a Kowalewski, Karl-Friedrich  |m 1100724192:Kowalewski, Karl-Friedrich  |d 60000  |d 63100  |e 60000PK1100724192  |e 63100PK1100724192  |k 0/60000/  |k 1/60000/63100/  |p 12 
999 |a KXP-PPN1932991123  |e 4756436455 
BIB |a Y 
SER |a journal 
JSO |a {"recId":"1932991123","language":["eng"],"note":["Gesehen am 12.08.2025"],"type":{"bibl":"article-journal","media":"Online-Ressource"},"title":[{"subtitle":"a randomized assessment","title":"GPT-4 generates accurate and readable patient education materials aligned with current oncological guidelines","title_sort":"GPT-4 generates accurate and readable patient education materials aligned with current oncological guidelines"}],"person":[{"given":"Severin","family":"Rodler","role":"aut","display":"Rodler, Severin","roleDisplay":"VerfasserIn"},{"roleDisplay":"VerfasserIn","display":"Cei, Francesco","role":"aut","family":"Cei","given":"Francesco"},{"given":"Conner","family":"Ganjavi","role":"aut","roleDisplay":"VerfasserIn","display":"Ganjavi, Conner"},{"given":"Enrico","family":"Checcucci","role":"aut","roleDisplay":"VerfasserIn","display":"Checcucci, Enrico"},{"given":"Pieter De","family":"Backer","role":"aut","roleDisplay":"VerfasserIn","display":"Backer, Pieter De"},{"family":"Belenchon","given":"Ines Rivero","display":"Belenchon, Ines Rivero","roleDisplay":"VerfasserIn","role":"aut"},{"family":"Taratkin","given":"Mark","display":"Taratkin, Mark","roleDisplay":"VerfasserIn","role":"aut"},{"family":"Puliatti","given":"Stefano","display":"Puliatti, Stefano","roleDisplay":"VerfasserIn","role":"aut"},{"given":"Alessandro","family":"Veccia","role":"aut","display":"Veccia, Alessandro","roleDisplay":"VerfasserIn"},{"display":"Piazza, Pietro","roleDisplay":"VerfasserIn","role":"aut","family":"Piazza","given":"Pietro"},{"display":"Baekelandt, Loïc","roleDisplay":"VerfasserIn","role":"aut","family":"Baekelandt","given":"Loïc"},{"role":"aut","display":"Kowalewski, Karl-Friedrich","roleDisplay":"VerfasserIn","given":"Karl-Friedrich","family":"Kowalewski"},{"given":"Juan Gómez","family":"Rivas","role":"aut","roleDisplay":"VerfasserIn","display":"Rivas, Juan Gómez"},{"display":"Fankhauser, Christian D.","roleDisplay":"VerfasserIn","role":"aut","family":"Fankhauser","given":"Christian D."},{"display":"Moschini, Marco","roleDisplay":"VerfasserIn","role":"aut","family":"Moschini","given":"Marco"},{"given":"Giorgio","family":"Gandaglia","role":"aut","roleDisplay":"VerfasserIn","display":"Gandaglia, Giorgio"},{"family":"Campi","given":"Riccardo","display":"Campi, Riccardo","roleDisplay":"VerfasserIn","role":"aut"},{"display":"Abreu, Andre De Castro","roleDisplay":"VerfasserIn","role":"aut","family":"Abreu","given":"Andre De Castro"},{"roleDisplay":"VerfasserIn","display":"Russo, Giorgio I.","role":"aut","family":"Russo","given":"Giorgio I."},{"role":"aut","roleDisplay":"VerfasserIn","display":"Cocci, Andrea","given":"Andrea","family":"Cocci"},{"roleDisplay":"VerfasserIn","display":"Maruccia, Serena","role":"aut","family":"Maruccia","given":"Serena"},{"family":"Cacciamani","given":"Giovanni E.","display":"Cacciamani, Giovanni E.","roleDisplay":"VerfasserIn","role":"aut"}],"relHost":[{"type":{"bibl":"periodical","media":"Online-Ressource"},"disp":"GPT-4 generates accurate and readable patient education materials aligned with current oncological guidelines a randomized assessmentPLOS ONE","note":["Schreibweise des Titels bis 2012: PLoS ONE","Gesehen am 20.03.19"],"recId":"523574592","corporate":[{"roleDisplay":"Herausgebendes Organ","display":"Public Library of Science","role":"isb"}],"language":["eng"],"pubHistory":["1.2006 -"],"part":{"extent":"14","volume":"20","text":"20(2025), 6, Artikel-ID e0324175, Seite 1-14","issue":"6","pages":"1-14","year":"2025"},"title":[{"title":"PLOS ONE","title_sort":"PLOS ONE"}],"physDesc":[{"extent":"Online-Ressource"}],"name":{"displayForm":["Public Library of Science"]},"origin":[{"publisher":"PLOS ; PLoS","dateIssuedKey":"2006","dateIssuedDisp":"2006-","publisherPlace":"San Francisco, California, US ; Lawrence, Kan."}],"id":{"issn":["1932-6203"],"zdb":["2267670-3"],"eki":["523574592"]}}],"physDesc":[{"noteIll":"Diagramme","extent":"14 S."}],"id":{"eki":["1932991123"],"doi":["10.1371/journal.pone.0324175"]},"origin":[{"dateIssuedDisp":"June 4, 2025","dateIssuedKey":"2025"}],"name":{"displayForm":["Severin Rodler, Francesco Cei, Conner Ganjavi, Enrico Checcucci, Pieter De Backer, Ines Rivero Belenchon, Mark Taratkin, Stefano Puliatti, Alessandro Veccia, Pietro Piazza, Loïc Baekelandt, Karl-Friedrich Kowalewski, Juan Gómez Rivas, Christian D. Fankhauser, Marco Moschini, Giorgio Gandaglia, Riccardo Campi, Andre De Castro Abreu, Giorgio I. Russo, Andrea Cocci, Serena Maruccia, Giovanni E. Cacciamani, YAU Collaborators"]}} 
SRT |a RODLERSEVEGPT4GENERA4202