Pilot Study on AI Image Analysis for Lower-Limb Reconstruction—Assessing ChatGPT-4’s Recommendations in Comparison to Board-Certified Plastic Surgeons and Resident Physicians

AI, especially ChatGPT, is impacting healthcare through applications in research, patient communication, and training. To our knowledge, this is the first study to examine ChatGPT-4’s ability to analyze images of lower leg defects and assesses its understanding of complex case reports in comparison...

Full description

Saved in:
Bibliographic Details
Main Authors: Silke Graul, Michael A. Pais, Rafael Loucas, Tobias Rohrbach, Elias Volkmer, Sebastian Leitsch, Thomas Holzbach
Format: Article
Language:English
Published: MDPI AG 2025-01-01
Series:Life
Subjects:
Online Access:https://www.mdpi.com/2075-1729/15/1/66
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832588120878481408
author Silke Graul
Michael A. Pais
Rafael Loucas
Tobias Rohrbach
Elias Volkmer
Sebastian Leitsch
Thomas Holzbach
author_facet Silke Graul
Michael A. Pais
Rafael Loucas
Tobias Rohrbach
Elias Volkmer
Sebastian Leitsch
Thomas Holzbach
author_sort Silke Graul
collection DOAJ
description AI, especially ChatGPT, is impacting healthcare through applications in research, patient communication, and training. To our knowledge, this is the first study to examine ChatGPT-4’s ability to analyze images of lower leg defects and assesses its understanding of complex case reports in comparison to the performance of board-certified surgeons and residents. We conducted a cross-sectional survey in Switzerland, Germany, and Austria, where 52 participants reviewed images depicting lower leg defects within fictitious patient profiles and selected the optimal reconstruction techniques. The questionnaire included cases with varied difficulty, and answer options did not always include the most obvious choices. Findings highlight that ChatGPT-4 successfully evaluated various reconstruction methods but struggled to determine the optimal solution based on the available information in visual and written forms. A chi-squared test of independence was performed to investigate the overall association between answer options (A, B, C, and D) and rater group (board-certified surgeons, ChatGPT-4, and resident). Inter-group rater associations showed significant overall test results (<i>p</i> < 0.001), with high agreement among board-certified surgeons. Our results suggest that board-certified plastic surgeons remain essential for patient-specific treatment planning, while AI can support decision-making. This reaffirms the role of AI as a supportive tool, rather than a replacement, in reconstructive surgery.
format Article
id doaj-art-35d1882e651e480dad5572890bfc1472
institution Kabale University
issn 2075-1729
language English
publishDate 2025-01-01
publisher MDPI AG
record_format Article
series Life
spelling doaj-art-35d1882e651e480dad5572890bfc14722025-01-24T13:38:38ZengMDPI AGLife2075-17292025-01-011516610.3390/life15010066Pilot Study on AI Image Analysis for Lower-Limb Reconstruction—Assessing ChatGPT-4’s Recommendations in Comparison to Board-Certified Plastic Surgeons and Resident PhysiciansSilke Graul0Michael A. Pais1Rafael Loucas2Tobias Rohrbach3Elias Volkmer4Sebastian Leitsch5Thomas Holzbach6Department of Hand and Plastic Surgery, Thurgau Hospital Group, 8501 Frauenfeld, SwitzerlandDepartment of Hand and Plastic Surgery, Thurgau Hospital Group, 8501 Frauenfeld, SwitzerlandDepartment of Plastic, Hand and Reconstructive Surgery, University Hospital Regensburg, 93053 Regensburg, GermanyAustralian Centre of Health Engagement, Evidence and Values (ACHEEV), University of Wollongong, Wollongong 2500, AustraliaDepartment of Hand Surgery, Helios Klinikum Munich West, 81241 Munich, GermanyDepartment of Hand and Plastic Surgery, Thurgau Hospital Group, 8501 Frauenfeld, SwitzerlandDepartment of Hand and Plastic Surgery, Thurgau Hospital Group, 8501 Frauenfeld, SwitzerlandAI, especially ChatGPT, is impacting healthcare through applications in research, patient communication, and training. To our knowledge, this is the first study to examine ChatGPT-4’s ability to analyze images of lower leg defects and assesses its understanding of complex case reports in comparison to the performance of board-certified surgeons and residents. We conducted a cross-sectional survey in Switzerland, Germany, and Austria, where 52 participants reviewed images depicting lower leg defects within fictitious patient profiles and selected the optimal reconstruction techniques. The questionnaire included cases with varied difficulty, and answer options did not always include the most obvious choices. Findings highlight that ChatGPT-4 successfully evaluated various reconstruction methods but struggled to determine the optimal solution based on the available information in visual and written forms. A chi-squared test of independence was performed to investigate the overall association between answer options (A, B, C, and D) and rater group (board-certified surgeons, ChatGPT-4, and resident). Inter-group rater associations showed significant overall test results (<i>p</i> < 0.001), with high agreement among board-certified surgeons. Our results suggest that board-certified plastic surgeons remain essential for patient-specific treatment planning, while AI can support decision-making. This reaffirms the role of AI as a supportive tool, rather than a replacement, in reconstructive surgery.https://www.mdpi.com/2075-1729/15/1/66ChatGPTChatGPT-4image analysisartificial intelligenceAIsurvey
spellingShingle Silke Graul
Michael A. Pais
Rafael Loucas
Tobias Rohrbach
Elias Volkmer
Sebastian Leitsch
Thomas Holzbach
Pilot Study on AI Image Analysis for Lower-Limb Reconstruction—Assessing ChatGPT-4’s Recommendations in Comparison to Board-Certified Plastic Surgeons and Resident Physicians
Life
ChatGPT
ChatGPT-4
image analysis
artificial intelligence
AI
survey
title Pilot Study on AI Image Analysis for Lower-Limb Reconstruction—Assessing ChatGPT-4’s Recommendations in Comparison to Board-Certified Plastic Surgeons and Resident Physicians
title_full Pilot Study on AI Image Analysis for Lower-Limb Reconstruction—Assessing ChatGPT-4’s Recommendations in Comparison to Board-Certified Plastic Surgeons and Resident Physicians
title_fullStr Pilot Study on AI Image Analysis for Lower-Limb Reconstruction—Assessing ChatGPT-4’s Recommendations in Comparison to Board-Certified Plastic Surgeons and Resident Physicians
title_full_unstemmed Pilot Study on AI Image Analysis for Lower-Limb Reconstruction—Assessing ChatGPT-4’s Recommendations in Comparison to Board-Certified Plastic Surgeons and Resident Physicians
title_short Pilot Study on AI Image Analysis for Lower-Limb Reconstruction—Assessing ChatGPT-4’s Recommendations in Comparison to Board-Certified Plastic Surgeons and Resident Physicians
title_sort pilot study on ai image analysis for lower limb reconstruction assessing chatgpt 4 s recommendations in comparison to board certified plastic surgeons and resident physicians
topic ChatGPT
ChatGPT-4
image analysis
artificial intelligence
AI
survey
url https://www.mdpi.com/2075-1729/15/1/66
work_keys_str_mv AT silkegraul pilotstudyonaiimageanalysisforlowerlimbreconstructionassessingchatgpt4srecommendationsincomparisontoboardcertifiedplasticsurgeonsandresidentphysicians
AT michaelapais pilotstudyonaiimageanalysisforlowerlimbreconstructionassessingchatgpt4srecommendationsincomparisontoboardcertifiedplasticsurgeonsandresidentphysicians
AT rafaelloucas pilotstudyonaiimageanalysisforlowerlimbreconstructionassessingchatgpt4srecommendationsincomparisontoboardcertifiedplasticsurgeonsandresidentphysicians
AT tobiasrohrbach pilotstudyonaiimageanalysisforlowerlimbreconstructionassessingchatgpt4srecommendationsincomparisontoboardcertifiedplasticsurgeonsandresidentphysicians
AT eliasvolkmer pilotstudyonaiimageanalysisforlowerlimbreconstructionassessingchatgpt4srecommendationsincomparisontoboardcertifiedplasticsurgeonsandresidentphysicians
AT sebastianleitsch pilotstudyonaiimageanalysisforlowerlimbreconstructionassessingchatgpt4srecommendationsincomparisontoboardcertifiedplasticsurgeonsandresidentphysicians
AT thomasholzbach pilotstudyonaiimageanalysisforlowerlimbreconstructionassessingchatgpt4srecommendationsincomparisontoboardcertifiedplasticsurgeonsandresidentphysicians