EUVIMEDEUVIMED entdecken
Crossref

The Use of Artificial Intelligence in Responding to Patient Questions About Anterolateral Thigh Flap Surgery for Diabetic Foot Ulcers

Einsatz von künstlicher Intelligenz bei Patientenfragen zur Anterolateral-Oberschenkel-Lappenoperation bei diabetischen Fußulzera

Luke J Llaurado, Kishan S Shah, Isabel A Snee, Rachel N Rohrich, Ryan J Bender, Nicole C Episalla, Richard C Youn, Karen K Evans

Journal of Reconstructive Microsurgery · 01.11.2026 · 42 (09) · 810-817

DOI: 10.1055/a-2737-5287 ↗

Auf einen Blick

ChatGPT 3.5 beantwortete 10 häufige Fragen zu ALT-Flap-Operationen bei diabetischen Fußulzera mit hoher Genauigkeit und guter Vollständigkeit, aber mit Lücken bei der postoperativen Pflege.

Fragestellung

Wie brauchbar sind ChatGPT-Antworten als Informationsquelle für Patient:innen mit ALT-Flap-Operation bei diabetischen Fußulzera?

Methode

10 FAQs zu DFU- und ALT-Flap-Versorgung wurden ChatGPT 3.5 im Juni 2024 vorgelegt. 4 plastische Chirurg:innen bewerteten Genauigkeit, Vollständigkeit und Gefahr auf einer 10-Punkte-Likert-Skala.

Ergebnisse

Mittelwerte: Genauigkeit 9,1 ± 1,2; Vollständigkeit 8,2 ± 1,5; Gefahr 2,0 ± 1,0. Lesbarkeit: mittlere Lesestufe 19,8 ± 20,1. 1 Antwort enthielt klar falsche präoperative Angaben; 6/10 ließen wichtige postoperative Infos weg.

Schlussfolgerung der Autor:innen

ChatGPT liefert laut Autor:innen genaue und umfassende Antworten zu FAQs bei ALT-Flap-Operationen für DFU. Für eine vollständige Information der Patient:innen ist aber eine weitere Verbesserung nötig.

Kernaussagen

  • Genauigkeit: 9,1 ± 1,2
  • Wichtige postoperative Angaben fehlten in 6/10 Antworten
  • Lesbarkeit im Mittel auf Niveau 19,8 ± 20,1

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

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Reconstructive Microsurgery, erschienen am 01.11.2026. Verfasst von Luke J Llaurado und 7 weiteren Autor:innen. Beteiligte Einrichtung: Georgetown University School of Medicine, Washington, District of Columbia, United States. Hauptthemen laut MEDLINE: Diabetic Foot, Plastic Surgery Procedures, Artificial Intelligence, Surgical Flaps. Die Arbeit nennt 34 Literaturangaben.

Auf einen BlickAbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Diabetic foot ulcer (DFU) care represents a significant challenge in plastic and reconstructive surgery. Oftentimes, patients encounter complex articles and websites to answer questions about their surgeries, including anterolateral thigh (ALT) flaps. Artificial intelligence (AI) represents a new and simplified resource for DFU patients seeking information regarding their care. To assess ChatGPT's utility as a patient resource, we evaluated the accuracy, comprehensiveness, and safety of AI-generated responses to frequently asked questions (FAQs) related to ALT flap surgery for DFU. Ten DFU and ALT flap care FAQs were posed to ChatGPT Model 3.5 in June 2024. Four plastic surgeons evaluated responses using a 10-point Likert scale for accuracy, comprehensiveness, and danger of ChatGPT's answers. Surgeons also provided qualitative feedback. Response readability was assessed using 10 readability indexes, averaged to produce a reading grade level for each response. Overall, ChatGPT answered patient questions with a mean accuracy of 9.1 ± 1.2, comprehensiveness of 8.2 ± 1.5, and danger of 2.0 ± 1.0. ChatGPT answered at a mean grade level of 19.8 ± 20.1. Qualitatively, physician reviewers complimented the organizational clarity of the responses (n = 4/10) and the AI's ability to provide information on possible surgical complications (n = 4/10). While one response was noted to present explicitly incorrect information about preoperative preparation protocols and when they should be initiated, the majority of responses (n = 6/10) left out key postoperative information, notably dangle protocols and compression. ChatGPT provides accurate and comprehensive responses to FAQs related to patients undergoing ALT flap surgery for the treatment of DFUs. The AI-generated responses were praised for organizational clarity and informative content regarding surgical complications, but lacked essential postoperative care details. Therefore, while ChatGPT is a valuable informational tool, further refinement is necessary to ensure that fully comprehensive information is provided to DFU patients.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Diabetic FootPlastic Surgery ProceduresArtificial IntelligenceSurgical FlapsPatient Education as TopicHumansThighMaleFemaleGenerative Artificial IntelligenceSurveys and Questionnaires

Autor:innen und Institutionen

  • Georgetown University School of Medicine, Washington, District of Columbia, United States.
  • Department of Plastic and Reconstructive Surgery, MedStar Georgetown University Hospital, Washington, District of Columbia, United States.

Zitieren

APA

Llaurado, L. J., Shah, K. S., Snee, I. A., Rohrich, R. N., Bender, R. J., Episalla, N. C., Youn, R. C., & Evans, K. K. (2026). The Use of Artificial Intelligence in Responding to Patient Questions About Anterolateral Thigh Flap Surgery for Diabetic Foot Ulcers. Journal of Reconstructive Microsurgery, 42(09), 810-817. https://doi.org/10.1055/a-2737-5287

Vancouver

Llaurado LJ, Shah KS, Snee IA, Rohrich RN, Bender RJ, Episalla NC, et al. The Use of Artificial Intelligence in Responding to Patient Questions About Anterolateral Thigh Flap Surgery for Diabetic Foot Ulcers. Journal of Reconstructive Microsurgery. 2026;42(09):810-817. doi:10.1055/a-2737-5287

BibTeX
@article{Llaurado2026,
  author = {Llaurado, Luke J and Shah, Kishan S and Snee, Isabel A and Rohrich, Rachel N and Bender, Ryan J and Episalla, Nicole C and Youn, Richard C and Evans, Karen K},
  title = {The Use of Artificial Intelligence in Responding to Patient Questions About Anterolateral Thigh Flap Surgery for Diabetic Foot Ulcers},
  journal = {Journal of Reconstructive Microsurgery},
  year = {2026},
  volume = {42},
  number = {09},
  pages = {810--817},
  doi = {10.1055/a-2737-5287}
}
Kostenlos starten →