EUVIMEDEUVIMED entdecken
Randomisierte kontrollierte StudieVergleichsstudie

Comparative Efficacy of ChatGPT and Gemini in Addressing Patient Queries on Gonarthrosis and Total Knee Arthroplasty: A Randomized Controlled Trial

Vergleichende Wirksamkeit von ChatGPT und Gemini bei Patientenfragen zu Gonarthrose und totaler Knieendoprothese: randomisierte kontrollierte Studie

Serhat Gurbuz, Bulent Karslioglu, Ahmet Keskin, Niyazi Igde, Mustafa Bugra Ayaz, Yunus Imren

The Journal of Knee Surgery · 01.02.2026 · 39 (03) · 123-126

DOI: 10.1055/a-2693-0756 ↗

Auf einen Blick

In einer randomisierten Studie mit 100 Patient:innen waren ChatGPT-Antworten zu Gonarthrose und TKA genauer und wurden besser bewertet als Gemini-Antworten.

Fragestellung

Sind ChatGPT und Gemini bei der Beantwortung von Patientenfragen zu Gonarthrose und totaler Knieendoprothese unterschiedlich wirksam?

Methode

Prospektive, randomisierte kontrollierte Studie mit 100 Patient:innen; 5 Fragen zu Operation und Rehabilitation an ChatGPT und Gemini; Bewertung durch 2 verblindete orthopädische Spezialisten und Patient:innen auf einer 10-Punkte-Skala.

Ergebnisse

ChatGPT erzielte höhere Genauigkeitswerte als Gemini (8,7 ± 0,9 vs. 7,2 ± 1,1; p < 0,001). Auch die Patientenzufriedenheit war höher (8,9 ± 0,8 vs. 7,5 ± 1,2; p < 0,001).

Schlussfolgerung der Autor:innen

ChatGPT lieferte genauere und zufriedenstellendere Antworten auf Patientenfragen zu Gonarthrose und TKA als Gemini.

Kernaussagen

  • Genauigkeit: 8,7 ± 0,9 mit ChatGPT vs. 7,2 ± 1,1 mit Gemini
  • Patientenzufriedenheit: 8,9 ± 0,8 vs. 7,5 ± 1,2
  • ChatGPT erzielte höhere Werte zu OP-Erklärung und Nachsorge

Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.

Kurz gefasst

Randomisierte kontrollierte Studie in der Zeitschrift The Journal of Knee Surgery, erschienen am 01.02.2026. Verfasst von Serhat Gurbuz und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Orthopedics and Traumatology, Health Sciences University Turkey, Metin Sabancı Baltalimanı Bone Diseases Training and Research Center, …. Hauptthemen laut MEDLINE: Arthroplasty, Replacement, Knee, Osteoarthritis, Knee, Patient Education as Topic, Artificial Intelligence. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 15 Literaturangaben.

Auf einen BlickAbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The emergence of artificial intelligence (AI) in health care has created novel opportunities for enhancing patient education and alleviating anxiety. This study seeks to evaluate the effectiveness of two leading AI platforms, ChatGPT and Gemini, in delivering accurate and satisfactory responses to patients with gonarthrosis, considering total knee arthroplasty (TKA). A prospective, randomized controlled trial was conducted involving 100 patients diagnosed with gonarthrosis and indicated for TKA. Each patient posed five questions regarding the surgery and postoperative rehabilitation to both ChatGPT and Gemini. Responses were evaluated by two blinded orthopaedic specialists on a 10-point scale for accuracy and patient satisfaction. Patients additionally evaluated their satisfaction with each response using a 10-point scale. The main outcome measures consisted of the average accuracy scores assessed by specialists and the average satisfaction scores reported by patients. Statistical analysis revealed significant differences between ChatGPT and Gemini in both accuracy and patient satisfaction (p < 0.001). ChatGPT demonstrated better performance with a mean accuracy score of 8.7 ± 0.9 compared with Gemini's 7.2 ± 1.1. Patient satisfaction scores aligned with expert evaluations, with ChatGPT achieving a mean satisfaction score of 8.9 ± 0.8 versus Gemini's 7.5 ± 1.2. Notably, ChatGPT excelled in providing comprehensive explanations of surgical procedures (mean score: 9.2 ± 0.7) and postoperative care (9.1 ± 0.8), whereas Gemini performed better in offering concise summaries of recovery timelines (8.4 ± 0.9). This study demonstrates that ChatGPT offers more accurate and satisfactory responses to patient queries regarding gonarthrosis and TKA compared with Gemini. The findings suggest that AI platforms, particularly ChatGPT, can serve as valuable tools in augmenting patient education and potentially reducing preoperative anxiety. Future studies should investigate the incorporation of AI-assisted information delivery into clinical practice and its long-term effects on patient outcomes.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Arthroplasty, Replacement, KneeOsteoarthritis, KneePatient Education as TopicArtificial IntelligenceHumansPatient SatisfactionFemaleMaleMiddle AgedProspective StudiesAgedGenerative Artificial Intelligence

Autor:innen und Institutionen

  • Department of Orthopedics and Traumatology, Health Sciences University Turkey, Metin Sabancı Baltalimanı Bone Diseases Training and Research Center, İstanbul, Turkey.
  • Department of Orthopedics and Traumatology, Istinye University Turkey, Liv Hospital Vadistanbul, İstanbul, Turkey.

Zitieren

APA

Gurbuz, S., Karslioglu, B., Keskin, A., Igde, N., Ayaz, M. B., & Imren, Y. (2026). Comparative Efficacy of ChatGPT and Gemini in Addressing Patient Queries on Gonarthrosis and Total Knee Arthroplasty: A Randomized Controlled Trial. The Journal of Knee Surgery, 39(03), 123-126. https://doi.org/10.1055/a-2693-0756

Vancouver

Gurbuz S, Karslioglu B, Keskin A, Igde N, Ayaz MB, Imren Y. Comparative Efficacy of ChatGPT and Gemini in Addressing Patient Queries on Gonarthrosis and Total Knee Arthroplasty: A Randomized Controlled Trial. The Journal of Knee Surgery. 2026;39(03):123-126. doi:10.1055/a-2693-0756

BibTeX
@article{Gurbuz2026,
  author = {Gurbuz, Serhat and Karslioglu, Bulent and Keskin, Ahmet and Igde, Niyazi and Ayaz, Mustafa Bugra and Imren, Yunus},
  title = {Comparative Efficacy of ChatGPT and Gemini in Addressing Patient Queries on Gonarthrosis and Total Knee Arthroplasty: A Randomized Controlled Trial},
  journal = {The Journal of Knee Surgery},
  year = {2026},
  volume = {39},
  number = {03},
  pages = {123--126},
  doi = {10.1055/a-2693-0756}
}
Kostenlos starten →