EUVIMEDEUVIMED entdecken
Systematische ÜbersichtMetaanalyse

Assessment of the Utility of Artificial Intelligence-Based Chatbots in Patient Education: A Systematic Review and Meta-Analysis

Bewertung des Nutzens von KI-basierten Chatbots in der Patientenaufklärung: systematische Übersicht und Metaanalyse

Sameh Hany Emile, Nir Horesh, Zoe Garoufalia, Rachel Gefen, Marylise Boutros, Steven D Wexner iD

The American Surgeon™ · 2026-01 · 92 (1) · 258-269

DOI: 10.1177/00031348251367031 ↗

Auf einen Blick

21 Studien zeigen: Chatbot-Antworten zur Patientenaufklärung waren überwiegend angemessen und korrekt. Die Lesbarkeit lag jedoch auf Hochschulniveau.

Fragestellung

Wie angemessen und genau sind Chatbot-Antworten für die Patientenaufklärung in verschiedenen medizinischen Fachgebieten?

Methode

Systematische Übersicht und Metaanalyse nach PRISMA; Suche in PubMed und Scopus von Januar bis August 2023; Pooling mit Random-Effects-Metaanalyse.

Ergebnisse

21 Studien. Pooled rate der Angemessenheit: 89,1 % (95 %-KI 84,9–93,3). Flesch-Kincaid Grade Level 13,1 (95 %-KI 11,7–14,5), Flesch Reading Ease 38,6 (95 %-KI 29–48,2).

Einschränkungen

Die Antworten lagen auf fortgeschrittenem Lesefähigkeitsniveau.

Schlussfolgerung der Autor:innen

Chatbots liefern laut Autor:innen meist genaue und angemessene Antworten für die Patientenaufklärung. Das hohe Lesenniveau könnte die breite Nutzung als Informationsquelle einschränken.

Kernaussagen

  • Angemessenheit der Antworten: 89,1 % (95 %-KI 84,9–93,3)
  • Lesbarkeit auf Hochschulniveau: Flesch-Kincaid 13,1
  • Bessere Patientenaufklärungswerte als Google Search (87 % vs. 78 %)

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 The American Surgeon™, online erschienen am 11.08.2025. Verfasst von Sameh Hany Emile und 5 weiteren Autor:innen. Beteiligte Einrichtung: Ellen Leifer Shulman and Steven Shulman Digestive Disease Center, Cleveland Clinic Florida, Weston, FL, USA. Hauptthemen laut MEDLINE: Patient Education as Topic, Artificial Intelligence. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 38 Literaturangaben.

Auf einen BlickAbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Chatbots and large language models, particularly ChatGPT, have led to an increasing number of studies on the potential for chatbots in patient education. In this systematic review, we aimed to provide a pooled assessment of the appropriateness and accuracy of chatbot responses in patient education across various medical disciplines.

Methods

This was a PRISMA-compliant systematic review and meta-analysis. PubMed and Scopus were searched from January-August 2023. Eligible studies that assessed the utility of chatbots in patient education were included. Primary outcomes were the appropriateness and quality of chatbot responses. Secondary outcomes included readability and concordance with published guidelines and Google searches. A random-effect proportional meta-analysis was used for pooling data.

Results

Following initial screening, 21 studies were included. The pooled rate of appropriateness of chatbot answers was 89.1% (95%CI: 84.9%–93.3%). ChatGPT was the most assessed chatbot. Responses, while accurate, were found to be at a college reading level as the weighted mean Flesh-Kincaid Grade Level was 13.1 (95%CI: 11.7-14.5) and the weighted mean Flesch Reading Ease Score was 38.6 (95%CI: 29- 48.2). Answers of chatbots to questions relevant to patient education had 78.6%–95% concordance with published guidelines in colorectal surgery and urology. Chatbots had higher patient education scores (87% vs 78%) than Google Search.

Conclusions

Chatbots provide largely accurate and appropriate answers for patient education. The advanced reading level of chatbot responses might be a limitation to their wide adoption as a source for patient education. However, they outperform traditional search engines and align well with professional guidelines, showcasing their potential in patient education.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Patient Education as TopicArtificial IntelligenceHumansComprehensionGenerative Artificial Intelligence

Stichwörter der Autor:innen

artificial intelligencechatbotsmeta-analysispatient educationsystematic review

Autor:innen und Institutionen

  • Ellen Leifer Shulman and Steven Shulman Digestive Disease Center, Cleveland Clinic Florida, Weston, FL, USA.
  • Colorectal Surgery Unit, General Surgery Department, Mansoura University Hospitals, Mansoura, Egypt.
  • Department of Surgery and Transplantation, Sheba Medical Center, Ramat-Gan, Israel.
  • Department of General Surgery, Hadassah Medical Organization and Faculty of Medicine, Hebrew University of Jerusalem, Israel.

ORCID-Profile: Steven D Wexner

Zitieren

APA

Emile, S. H., Horesh, N., Garoufalia, Z., Gefen, R., Boutros, M., & Wexner, S. D. (2026). Assessment of the Utility of Artificial Intelligence-Based Chatbots in Patient Education: A Systematic Review and Meta-Analysis. The American Surgeon™, 92(1), 258-269. https://doi.org/10.1177/00031348251367031

Vancouver

Emile SH, Horesh N, Garoufalia Z, Gefen R, Boutros M, Wexner SD. Assessment of the Utility of Artificial Intelligence-Based Chatbots in Patient Education: A Systematic Review and Meta-Analysis. The American Surgeon™. 2026;92(1):258-269. doi:10.1177/00031348251367031

BibTeX
@article{Emile2026,
  author = {Emile, Sameh Hany and Horesh, Nir and Garoufalia, Zoe and Gefen, Rachel and Boutros, Marylise and Wexner, Steven D},
  title = {Assessment of the Utility of Artificial Intelligence-Based Chatbots in Patient Education: A Systematic Review and Meta-Analysis},
  journal = {The American Surgeon™},
  year = {2026},
  volume = {92},
  number = {1},
  pages = {258--269},
  doi = {10.1177/00031348251367031}
}
Kostenlos starten →