EUVIMEDEUVIMED entdecken
VergleichsstudieQuerschnittstudie

ChatGPT vs rheumatologists: cross-sectional study on accuracy and patient perception of AI-generated information for psoriatic arthritis

Giulio Forte, Daniele Mauro, Maura Raimondi, Ilenia Pantano, Saviana Gandolfo, Alberto Cauli, Giuliana Guggino, Ennio Lubrano, Serena Guiducci, Maria Sole Chimenti, Giusy Peluso, Maria Antonietta D'Agostino und 9 weitere

Annals of the Rheumatic Diseases · 2026-07 · 85 (7) · 1290-1299

DOI: 10.1016/j.ard.2025.11.012 ↗

Kurz gefasst

Vergleichsstudie in der Zeitschrift Annals of the Rheumatic Diseases, 2026-07. Verfasst von Giulio Forte und 20 weiteren Autor:innen. Beteiligte Einrichtung: Department of Precision Medicine, University of Campania "Luigi Vanvitelli", Naples, Italy. Hauptthemen laut MEDLINE: Arthritis, Psoriatic, Patient Education as Topic, Rheumatologists. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 25 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

OBJECTIVES: Patients with rheumatic diseases frequently turn to online sources for medical information. Large language models, such as ChatGPT, may offer an accessible alternative to conventional patient‑education resources; however, their reliability remains poorly explored. We conducted an exploratory, descriptive comparison to examine whether ChatGPT-4 might provide responses comparable to those of experts. METHODS: Seventy-six psoriatic arthritis (PsA) patients generated 32 questions (296 selections) grouped into 6 themes. Each question was answered by ChatGPT-4 and by 12 Italian PsA specialists (each drafted 2-3 answers). Fourteen clinicians, The 14 clinicians scored the accuracy and completeness of AI and human-generated answers, rated accuracy (1-5 Likert scale) and completeness (1-3). Interrater reliability was calculated, and mixed-effects ordinal logistic models were used to compare sources. In a separate arm, 67 PsA patients reviewed 16 randomly selected answer pairs and indicated their preference. Readability was assessed. No formal sample size calculation was performed; P values were descriptive and interpreted alongside effect sizes and 95% CIs. RESULTS: Patients most frequently sought information on prognosis/comorbidities (54/76, 71.1%), therapy strategy (48/76, 63.2%), and treatment risks (38/76, 50.0%). Accuracy appeared comparable between ChatGPT and experts, but ChatGPT scored lower in completeness. Accuracy was lower for pregnancy/fertility, with no clear relevant differences in other domains. ChatGPT answers were chosen 491/998 times (49.2%), clinician answers 343/998 times (34.4%), and no preference 164/998 times (16.4%, P < .001), with a relative preference for ChatGPT responses in prognosis and therapy. ChatGPT responses were, on average, more readable across indices. CONCLUSIONS: In this exploratory study, ChatGPT-4 appeared able to generate accurate and readable responses to PsA-related questions and was often preferred by patients.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Arthritis, PsoriaticPatient Education as TopicRheumatologistsHumansCross-Sectional StudiesFemaleMaleMiddle AgedGenerative Artificial IntelligenceLarge Language ModelsAdultReproducibility of ResultsAgedSurveys and Questionnaires

Autor:innen und Institutionen

  • Department of Precision Medicine, University of Campania "Luigi Vanvitelli", Naples, Italy.
  • Rheumatology Unit, Ospedale del Mare, ASL Napoli 1 Centro, Naples, Italy.
  • Rheumatology Unit, Department of Medical Sciences and Public Health, University of Cagliari, Cagliari, Italy.
  • Department of Health Promotion, Mother and Child Care, Internal Medicine and Medical Specialties, Rheumatology Section-"P. Giaccone", University of Palermo, Palermo, Italy.
  • Rheumatology and Internal Medicine Department, Molise University, Campobasso, Italy.
  • Rheumatology Unit, Department of Experimental and Clinical Medicine, University of Florence, Florence, Italy.

Zitieren

APA

Forte, G., Mauro, D., Raimondi, M., Pantano, I., Gandolfo, S., Cauli, A., Guggino, G., Lubrano, E., Guiducci, S., Chimenti, M. S., Peluso, G., D'Agostino, M. A., Ramonda, R., Caso, F., Costa, L., Ruscitti, P., Maioli, G., Lopalco, G., Tirri, E., …, & Ciccia, F. (2026). ChatGPT vs rheumatologists: cross-sectional study on accuracy and patient perception of AI-generated information for psoriatic arthritis. Annals of the Rheumatic Diseases, 85(7), 1290-1299. https://doi.org/10.1016/j.ard.2025.11.012

Vancouver

Forte G, Mauro D, Raimondi M, Pantano I, Gandolfo S, Cauli A, et al. ChatGPT vs rheumatologists: cross-sectional study on accuracy and patient perception of AI-generated information for psoriatic arthritis. Annals of the Rheumatic Diseases. 2026;85(7):1290-1299. doi:10.1016/j.ard.2025.11.012

BibTeX
@article{Forte2026,
  author = {Forte, Giulio and Mauro, Daniele and Raimondi, Maura and Pantano, Ilenia and Gandolfo, Saviana and Cauli, Alberto and Guggino, Giuliana and Lubrano, Ennio and Guiducci, Serena and Chimenti, Maria Sole and Peluso, Giusy and D'Agostino, Maria Antonietta and Ramonda, Roberta and Caso, Francesco and Costa, Luisa and Ruscitti, Piero and Maioli, Gabriella and Lopalco, Giuseppe and Tirri, Enrico and Caporali, Roberto and Ciccia, Francesco},
  title = {ChatGPT vs rheumatologists: cross-sectional study on accuracy and patient perception of AI-generated information for psoriatic arthritis},
  journal = {Annals of the Rheumatic Diseases},
  year = {2026},
  volume = {85},
  number = {7},
  pages = {1290--1299},
  doi = {10.1016/j.ard.2025.11.012}
}
Kostenlos starten →