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

Abstract

Background

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.

Methods

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.

Results

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.

Conclusion

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.

Keywords

AI - ChatGPT - LLMs - DFU - ALT - microsurgery

Data Availability Statement

The data that support the findings of this study are available from the corresponding author upon reasonable request and with permission from MedStar Health.

Ethical Approval

This study was conducted in accordance with the ethical standards of the Declaration of Helsinki and was approved by the Department of Plastic and Reconstructive Surgery at MedStar Georgetown University Hospital.

Note

This research was presented at the American Society for Reconstructive Microsurgery (ASRM) Annual Meeting 2025 in Kona, Hawaii, United States.

Supplementary Material is available at https://doi.org/10.1055/a-2737-5287

Publication History

Received: 03 July 2025

Accepted: 03 November 2025

Accepted Manuscript online:
05 November 2025

Article published online:
21 November 2025

• References

• 1 Li AW, Adelstein JM, Li LT, Sinkler MA, Mistovich RJ. Assessing ChatGPT responses to frequently asked questions regarding pediatric supracondylar humerus fractures. J Pediatr Orthop 2025; 45 (06) 327-331
• 2 Lieu B, Crawford E, Laubach L. et al. Patient education strategies in pediatric orthopaedics: using ChatGPT to answer frequently asked questions on scoliosis. Spine Deform 2025; 13 (05) 1377-1389
• 3 Snee I, Lava CX, Li KR, Corral GD. The utility of ChatGPT in gender-affirming mastectomy education. J Plast Reconstr Aesthet Surg 2024; 99: 432-435
• 4 Kung TH, Cheatham M, Medenilla A. et al. Performance of ChatGPT on USMLE: potential for AI-assisted medical education using large language models. PLOS Digit Health 2023; 2 (02) e0000198
• 5 Pan A, Musheyev D, Bockelman D, Loeb S, Kabarriti AE. Assessment of artificial intelligence chatbot responses to top searched queries about cancer. JAMA Oncol 2023; 9 (10) 1437-1440
• 6 Armstrong DG, Tan TW, Boulton AJM, Bus SA. Diabetic foot ulcers: a review. JAMA 2023; 330 (01) 62-75
• 7 Zhang P, Lu J, Jing Y, Tang S, Zhu D, Bi Y. Global epidemiology of diabetic foot ulceration: a systematic review and meta-analysis^† . Ann Med 2017; 49 (02) 106-116
• 8 Lazzarini PA, Cramb SM, Golledge J, Morton JI, Magliano DJ, Van Netten JJ. Global trends in the incidence of hospital admissions for diabetes-related foot disease and amputations: a review of national rates in the 21st century. Diabetologia 2023; 66 (02) 267-287
• 9 Sing QY, Borg TM, Yousif YF, Chin KJ, Devetzis K, Sousi S. Free tissue transfer for the management of diabetic lower limb ulcers: a systematic review and meta-analysis. Microsurgery 2025; 45 (06) e70093
• 10 Hong JP. Reconstruction of the diabetic foot using the anterolateral thigh perforator flap. Plast Reconstr Surg 2006; 117 (05) 1599-1608
• 11 Tan CH, Wu Y, Satkunanantham M. Flaps for lower limb diabetic wound reconstruction: a systematic review and meta-analysis. J Plast Reconstr Aesthet Surg 2023; 79: 74-86
• 12 Akkus G, Sert M. Diabetic foot ulcers: a devastating complication of diabetes mellitus continues non-stop in spite of new medical treatment modalities. World J Diabetes 2022; 13 (12) 1106-1121
• 13 Reed AJM, Lim NTY, Yip SWL. et al. Outcomes of flap reconstruction for diabetic foot ulcers: a systematic review and meta-analysis of clinical studies. Plast Reconstr Surg 2024; 154 (05) 1118-1130
• 14 McDermott K, Fang M, Boulton AJM, Selvin E, Hicks CW. Etiology, epidemiology, and disparities in the burden of diabetic foot ulcers. Diabetes Care 2023; 46 (01) 209-221
• 15 Ojo O, Boateng J, Pacella R, Hanrahan A, Essex R, Dibley L. Factors influencing the care and management of diabetic foot ulcers: a scoping review. Endocr Pract 2025; 31 (03) 380-389
• 16 Gravely SS, Hensley BK, Hagood-Thompson C. Comparison of three types of diabetic foot ulcer education plans to determine patient recall of education. J Vasc Nurs 2011; 29 (03) 113-119
• 17 Berry CE, Fazilat AZ, Lavin C. et al. Both patients and plastic surgeons prefer artificial intelligence-generated microsurgical information. J Reconstr Microsurg 2024; 40 (09) 657-664
• 18 Raquepo TM, Tobin M, Puducheri S. et al. Artificial intelligence in microsurgical education: a systematic review of its role in training surgeons. J Reconstr Microsurg 2025
• 19 A technique for the measurement of attitudes - National Library of Medicine Institution. Accessed October 12, 2025 at: https://catalog.nlm.nih.gov/discovery/fulldisplay/alma9916816193406676/01NLM_INST:01NLM_INST
• 20 Westland JC. Information loss and bias in Likert survey responses. PLoS One 2022; 17 (07) e0271949
• 21 O'Neill TA. An overview of interrater agreement on Likert scales for researchers and practitioners. Front Psychol 2017; 8: 777
• 22 Jebb AT, Ng V, Tay L. A review of key Likert scale development advances: 1995-2019. Front Psychol 2021; 12: 637547
• 23 Norman G. Likert scales, levels of measurement and the “laws” of statistics. Adv Health Sci Educ Theory Pract 2010; 15 (05) 625-632
• 24 Huang AS, Hirabayashi K, Barna L, Parikh D, Pasquale LR. Assessment of a large language model's responses to questions and cases about glaucoma and retina management. JAMA Ophthalmol 2024; 142 (04) 371-375
• 25 Ley P, Florio T. The use of readability formulas in health care. Psychol Health Med 1996; 1 (01) 7-28
• 26 Kincaid JP, Braby R, Mears JE. Electronic authoring and delivery of technical information. J Instr Dev 1988; 11 (02) 8-13
• 27 Kincaid JP, Fishburne J, Rogers RL, Chissom BS. Derivation of New Readability Formulas (Automated Readability Index, Fog Count and Flesch Reading Ease Formula) for Navy Enlisted Personnel. Published online February 1, 1975. Accessed October 12, 2025 at: https://apps.dtic.mil/sti/html/tr/ADA006655/
• 28 Gunning R. The Technique of Clear Writing. McGraw-Hill; 1952
• 29 Mc Laughlin GH. SMOG grading-a new readability formula. J Read 1969; 12 (08) 639-646
• 30 Smith EA, Senter RJ. Automated readability index. AMRL-TR (6570th Aerosp Med Res Lab) 1967; 1-14
• 31 Coleman M, Liau TL. A computer readability formula designed for machine scoring. J Appl Psychol 1975; 60 (02) 283-284
• 32 Caylor JS, Others A. Methodologies for Determining Reading Requirements of Military Occupational Specialties. 1973 . Accessed October 12, 2025 at: https://eric.ed.gov/?id=ED074343
• 33 Dale E, Chall JS. A formula for predicting readability. Educ Res Bull 1948; 27 (01) 11-28
• 34 Collins CE, Giammanco PA, Guirgus M. et al. Evaluating the quality and readability of generative artificial intelligence (AI) chatbot responses in the management of Achilles tendon rupture. Cureus 2025; 17 (01) e78313
• 35 Abou-Abdallah M, Dar T, Mahmudzade Y, Michaels J, Talwar R, Tornari C. The quality and readability of patient information provided by ChatGPT: can AI reliably explain common ENT operations?. Eur Arch Otorhinolaryngol 2024; 281 (11) 6147-6153
• 36 The Powers Sumner Kearl Readability Formula. Readable. . Accessed April 6, 2025 at: https://readable.com/readability/powers-sumner-kearl-readability-formula/
• 37 Abi-Rafeh J, Bassiri-Tehrani B, Kazan R, Hanna SA, Kanevsky J, Nahai F. Comparative performance of current patient-accessible artificial intelligence large language models in the preoperative education of patients in facial aesthetic surgery. Aesthet Surg J Open Forum 2024; 6: ojae058
• 38 Roster K, Kann RB, Farabi B, Gronbeck C, Brownstone N, Lipner SR. Readability and health literacy scores for ChatGPT-generated dermatology public education materials: cross-sectional analysis of sunscreen and melanoma questions. JMIR Dermatol 2024; 7: e50163
• 39 Sina EM, Campbell DJ, Duffy A. et al. Evaluating ChatGPT as a patient education tool for COVID-19-induced olfactory dysfunction. OTO Open 2024; 8 (03) e70011