ChatGPT provides accurate and safe responses to patient questions on hip arthroscopy, while completeness remains variable: A systematic review and single‐arm meta‐analysis
ChatGPT liefert genaue und sichere Antworten auf Patientenfragen zur Hüftarthroskopie, während die Vollständigkeit variabel bleibt: systematische Übersicht und Single-Arm-Metaanalyse
Knee Surgery, Sports Traumatology, Arthroscopy · 2026-06 · 34 (6) · 2236-2246
DOI: 10.1002/ksa.70396 ↗Auf einen Blick
Acht Studien zeigen für ChatGPT bei Patientenfragen zur Hüftarthroskopie hohe Genauigkeit sowie hohe Relevanz, Sicherheit, Lesbarkeit und Klarheit. Die Vollständigkeit war geringer und variabler.
Fragestellung
Wie gut beantwortet ChatGPT Patientenfragen zur Hüftarthroskopie bzw. zum femoroacetabulären Impingement hinsichtlich Genauigkeit, Vollständigkeit und Sicherheit?
Methode
Systematische Übersicht und Single-Arm-Metaanalyse; Suche in PubMed, Embase, Scopus, CINAHL und Epistemonikos bis 10. Februar 2026; Bewertung mit QUADAS-2 und ROBINS-I.
Ergebnisse
8 Studien. Gepoolte Genauigkeit 88,6 %; Relevanz, Sicherheit, Lesbarkeit und Klarheit jeweils 100 % mit geringer Heterogenität. Vollständigkeit 83,8 % mit moderater Heterogenität.
Einschränkungen
Hohes oder mittleres Verzerrungsrisiko, vor allem durch nicht systematische Fragenauswahl und heterogene Bewertungsinstrumente. Kleine Zahl an Studien schränkte die Funnel-Plot-Interpretation ein.
Schlussfolgerung der Autor:innen
ChatGPT liefert genaue, relevante, sichere und klare Antworten zu Patientenfragen zur Hüftarthroskopie; die Vollständigkeit variiert moderat. Die Autor:innen betonen den Bedarf an klinischer Beratung und standardisierter Bewertung.
Kernaussagen
- Genauigkeit gepoolt 88,6 %
- Vollständigkeit geringer: 83,8 %
- Spätere Modelle schnitten besser ab als GPT-3.5
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
Kurz gefasst
Systematische Übersicht in der Zeitschrift Knee Surgery, Sports Traumatology, Arthroscopy, online erschienen am 14.04.2026. Verfasst von Nikolai Ramadanov und 8 weiteren Autor:innen. Beteiligte Einrichtung: Center of Orthopaedics and Traumatology, Brandenburg Medical School, University Hospital Brandenburg an der Havel, Brandenburg an der Havel, Germany. Hauptthemen laut MEDLINE: Arthroscopy, Patient Education as Topic, Femoracetabular Impingement, Hip Joint. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Purpose
Large language models, such as ChatGPT, are increasingly used by patients seeking information on hip arthroscopy (HAS) and femoroacetabular impingement (FAI). Despite their linguistic fluency, the accuracy, completeness and safety of procedure‐specific patient information remain unclear. Although orthopaedic studies report variable performance across subspecialties, no systematic evaluation has specifically addressed HAS.
Methods
PubMed, Embase, Scopus, CINAHL and Epistemonikos were searched to 10 February 2026 for studies evaluating ChatGPT responses to patient‐oriented HAS or FAI questions. Randomized and non‐randomized studies, observational cohorts and case series were eligible. Data on question sources, model versions, rating systems and performance domains (accuracy, relevance, completeness, safety, readability and clarity) were extracted. Heterogeneous rating scales were dichotomized into high‐ versus low‐quality responses. Risk of bias was assessed using QUADAS‐2 and ROBINS‐I. Random‐effects single‐arm meta‐analyses (REML) were conducted for each domain.
Results
Eight studies met eligibility criteria. Accuracy was high (pooled 88.6%). Relevance, safety, readability and clarity reached pooled values of 100% with low heterogeneity. Completeness was lower (83.8%) with moderate heterogeneity, mainly driven by early GPT‐3.5 studies. Funnel plots showed no clear small‐study effects, although interpretation was limited by the small number of studies. Risk of bias was predominantly high or moderate, largely due to non‐systematic question selection and heterogeneous rating tools. Later models (GPT‐4/4o and beyond) demonstrated higher performance compared with GPT‐3.5.
Conclusion
ChatGPT provides accurate, relevant, safe and clear responses to patient questions about HAS, while completeness shows moderate variability. Although LLMs appear promising as adjuncts to patient education, methodological limitations in the current evidence base underscore the need for expert clinical counselling and more rigorous, standardized evaluation frameworks. Level of Evidence Level III systematic review and meta‐analysis of non‐randomized studies.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Center of Orthopaedics and Traumatology, Brandenburg Medical School, University Hospital Brandenburg an der Havel, Brandenburg an der Havel, Germany.
- Faculty of Health Science Brandenburg, Brandenburg Medical School Theodor Fontane, Brandenburg an der Havel, Germany.
- Faculty of Medicine, Medical University of Plovdiv, Plovdiv, Bulgaria.
- Clinic of Orthopaedics and Sports Orthopaedics, School of Medicine and Health, TUM University Hospital, Technical University of Munich, Munich, Germany.
- AGA-Society for Arthroscopy and Joint-Surgery, Hip Committee, c/o Walder Wyss Ltd., Zürich, Switzerland.
ORCID-Profile: Nikolai Ramadanov
Zitieren
APA
Ramadanov, N., Penchev, P., Voss, M., Heinz, M., Prill, R., Salzmann, M., Becker, R., Osterberger, T., & Banke, I. J. (2026). ChatGPT provides accurate and safe responses to patient questions on hip arthroscopy, while completeness remains variable: A systematic review and single‐arm meta‐analysis. Knee Surgery, Sports Traumatology, Arthroscopy, 34(6), 2236-2246. https://doi.org/10.1002/ksa.70396
Vancouver
Ramadanov N, Penchev P, Voss M, Heinz M, Prill R, Salzmann M, et al. ChatGPT provides accurate and safe responses to patient questions on hip arthroscopy, while completeness remains variable: A systematic review and single‐arm meta‐analysis. Knee Surgery, Sports Traumatology, Arthroscopy. 2026;34(6):2236-2246. doi:10.1002/ksa.70396
BibTeX
@article{Ramadanov2026,
author = {Ramadanov, Nikolai and Penchev, Plamen and Voss, Maximilian and Heinz, Maximilian and Prill, Robert and Salzmann, Mikhail and Becker, Roland and Osterberger, Timoty and Banke, Ingo J},
title = {ChatGPT provides accurate and safe responses to patient questions on hip arthroscopy, while completeness remains variable: A systematic review and single‐arm meta‐analysis},
journal = {Knee Surgery, Sports Traumatology, Arthroscopy},
year = {2026},
volume = {34},
number = {6},
pages = {2236--2246},
doi = {10.1002/ksa.70396}
}
EUVIMED