EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Performance of large language models in addressing patient queries on colorectal cancer screening in different languages: An international study across 28 countries

Maida M, Papaefthymiou A, Gupta S, Voiosu T, Lau Lhs, Baraldo S, Pal P, Mwachiro M, Zuchelli T, Uchima H, Aguila Ejt, Bouberra D und 13 weitere

Digestive and Liver Disease · 2026

DOI: 10.1016/j.dld.2025.11.026 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Digestive and Liver Disease, 2026. Verfasst von Maida M und 24 weiteren Autor:innen. Beteiligte Einrichtung: Department of Medicine and Surgery, University of Enna `Kore', Enna, Italy; Gastroenterology Unit, Umberto I Hospital, Enna, Italy. Electronic addres…. Hauptthemen laut MEDLINE: Colorectal Neoplasms, Early Detection of Cancer, Language. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 12 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: Colorectal cancer (CRC) screening reduces incidence and mortality, yet patient adherence remains suboptimal. Large language models may improve participation by addressing patient questions in native languages, but their multilingual performance has not been systematically assessed. METHODS: From April to June 2025, we conducted a cross-continental study involving 28 countries and 23 languages. A standardized set of 15 CRC screening-related questions was translated into each language and submitted to ChatGPT (GPT-4o). Responses were independently evaluated by 140 gastroenterologists (five per country) for accuracy, completeness, and comprehensibility on a 5-point Likert scale. Statistical analyses included t-test, Chi-square, and two-way ANOVA. RESULTS: The study included experts and data from Europe, Asia, Africa, America, and Oceania. Mean scores (±SD) for accuracy, completeness, and comprehensibility were 4.1 ± 1.0, 4.1 ± 1.0, and 4.2 ± 0.9, respectively. Most languages achieved high ratings, with 73.9%, 86.9%, and 82.6% scoring ≥4 for accuracy, completeness, and comprehensibility. However, lower scores were observed in Chinese, Dutch, and Greek. Variability was also noted between countries sharing the same language, highlighting language- and context-dependent performance. DISCUSSION: ChatGPT showed strong ability to answer CRC screening questions across multiple languages, supporting its promise as a multilingual patient education tool. Nonetheless, regional variability requires careful validation before clinical integration.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Colorectal NeoplasmsEarly Detection of CancerLanguageHumansComprehensionSurveys and QuestionnairesAsiaMultilingualismEuropeMaleFemaleMass ScreeningAfricaLarge Language Models

Stichwörter der Autor:innen

Artificial IntelligenceChatGPTColorectal CancerLanguagesScreening

Autor:innen und Institutionen

  • Department of Medicine and Surgery, University of Enna `Kore', Enna, Italy; Gastroenterology Unit, Umberto I Hospital, Enna, Italy. Electronic address: marcello.maida@unikore.it.
  • Department of Gastroenterology, General University Hospital of Larissa, Larissa, Greece.
  • Department of Gastroenterology and Hepatology, Westmead Hospital, Sydney, Australia; Clinical School of Medicine, University of Sydney, Sydney, Australia; The Center for Advanced Therapeutic Endoscopy and Endoscopic Onc…
  • Gastroenterology Department, Colentina Clinical Hospital, Carol Davila Faculty of Medicine, Bucharest, Romania.
  • Department of Medicine and Therapeutics, Faculty of Medicine, The Chinese University of Hong Kong, China; Li Ka Shing Institute of Health Sciences, The Chinese University of Hong Kong, China; Institute of Digestive Dise…
  • Department of Endoscopy, Barretos Cancer Hospital, Barretos, Brazil.

Zitieren

APA

M, M., A, P., S, G., T, V., Lhs, L., S, B., P, P., M, M., T, Z., H, U., Ejt, A., D, B., H, D., T, D., A, G., T, K., S, L., B, L., H, M., …, & World Endoscopy Organization (WEO) Emerging Stars Program (2026). Performance of large language models in addressing patient queries on colorectal cancer screening in different languages: An international study across 28 countries. Digestive and Liver Disease. https://doi.org/10.1016/j.dld.2025.11.026

Vancouver

M M, A P, S G, T V, Lhs L, S B, et al. Performance of large language models in addressing patient queries on colorectal cancer screening in different languages: An international study across 28 countries. Digestive and Liver Disease. 2026. doi:10.1016/j.dld.2025.11.026

BibTeX
@article{M2026,
  author = {M, Maida and A, Papaefthymiou and S, Gupta and T, Voiosu and Lhs, Lau and S, Baraldo and P, Pal and M, Mwachiro and T, Zuchelli and H, Uchima and Ejt, Aguila and D, Bouberra and H, Degroote and T, Düzenli and A, Gameel and T, Khurelbaatar and S, Lakkasani and B, Luvsandagva and H, Maulahela and R, Nobre and Y, Okubo and A, Rimondi and A, Taiymi and I, Mostafa and World Endoscopy Organization (WEO) Emerging Stars Program, World Endoscopy Organization (WEO) Emerging Stars Program},
  title = {Performance of large language models in addressing patient queries on colorectal cancer screening in different languages: An international study across 28 countries},
  journal = {Digestive and Liver Disease},
  year = {2026},
  doi = {10.1016/j.dld.2025.11.026}
}
Kostenlos starten →