Skip to main content
Key Specialties
Anesthesiology Cardiology Dermatology Diabetology Endocrinology Gastroenterology General Medicine Geriatrics Hematology Infectious Diseases Internal Medicine Nephrology Neurology Obstetrics and Gynecology Oncology Pediatrics Psychiatry Radiology Respiratory Medicine Rheumatology Surgery Urology
Congress Coverage
2024 ESMO Congress 2024 ERS Congress 2024 EASD Congress 2024 ESC Congress 2024 EAN Congress 2024 ASCO Annual Meeting 2024 ACC Congress
Clinical Collections
Advances in Alzheimer’s

Keynote webinar | Spotlight on modern management of frailty

LIVE: Thursday 17th October 2024, 18:00-19:30 (CEST)

Frailty has a significant impact on health and wellbeing, especially in older adults. Join our experts to understand the factors that contribute to the development of frailty and find out how to manage the condition and reduce the risk of disability, dependency, and mortality.
ADVANCED SEARCH
Log in
Top
Aesthetic Plastic Surgery

25-09-2024 | Keloid | Original Articles

The Potential of Chat-Based Artificial Intelligence Models in Differentiating Between Keloid and Hypertrophic Scars: A Pilot Study

Authors: Makoto Shiraishi, Shimpei Miyamoto, Hakuba Takeishi, Daichi Kurita, Kiichi Furuse, Jun Ohba, Yuta Moriwaki, Kou Fujisawa, Mutsumi Okazaki

Published in: Aesthetic Plastic Surgery

Login to get access

Abstract

Background

Lasting scars such as keloids and hypertrophic scars adversely affect a patient’s quality of life. However, these scars are frequently underdiagnosed because of the complexity of the current diagnostic criteria and classification systems. This study aimed to explore the application of Large Language Models (LLMs) such as ChatGPT in diagnosing scar conditions and to propose a more accessible and straightforward diagnostic approach.

Methods

In this study, five artificial intelligence (AI) chatbots, including ChatGPT-4 (GPT-4), Bing Chat (Precise, Balanced, and Creative modes), and Bard, were evaluated for their ability to interpret clinical scar images using a standardized set of prompts. Thirty mock images of various scar types were analyzed, and each chatbot was queried five times to assess the diagnostic accuracy.

Results

GPT-4 had a significantly higher accuracy rate in diagnosing scars than Bing Chat. The overall accuracy rates of GPT-4 and Bing Chat were 36.0% and 22.0%, respectively (P = 0.027), with GPT-4 showing better performance in terms of specificity for keloids (0.6 vs. 0.006) and hypertrophic scars (0.72 vs. 0.0) than Bing Chat.

Conclusions

Although currently available LLMs show potential for use in scar diagnostics, the current technology is still under development and is not yet sufficient for clinical application standards, highlighting the need for further advancements in AI for more accurate medical diagnostics.

Level of Evidence IV

This journal requires that authors assign a level of evidence to each article. For a full description of these Evidence-Based Medicine ratings, please refer to the Table of Contents or the online instructions to authors www.​springer.​com/​00266.
Appendix
Available only for authorised users
Literature
1.
Stokel-Walker C, Van Noorden R (2023) What ChatGPT and generative AI mean for science. Nature 614:214–216CrossRefPubMed
2.
3.
Decker H, Trang K, Ramirez J, Colley A, Pierce L, Coleman M, Li Y, Patel V, Thomas D, Wu S, Yang R (2023) Large language model-based chatbot vs surgeon-generated informed consent documentation for common procedures. JAMA Netw Open 6:e2336997CrossRefPubMedPubMedCentral
4.
Ali R, Tang OY, Connolly ID, Abdulrazeq HF, Mirza FN, Lim RK, Thorne J, Lu A, Janardhanan K (2024) Demographic representation in 3 leading artificial intelligence text-to-image generators. JAMA Surg 159:87–95CrossRefPubMed
5.
Shiraishi M, Tanigawa K, Tomioka Y, Miyakuni A, Moriwaki Y, Yang R, Okazaki M, Kanayama K (2024) Blepharoptosis consultation with artificial intelligence: aesthetic surgery advice and counseling from chat generative pre-trained transformer (ChatGPT). Aesthet Plast Surg 48:2057–2063CrossRef
6.
Shiraishi M, Tomioka Y, Miyakuni A, Ishii S, Hori A, Park H, Kanayama K (2024) Performance of ChatGPT in answering clinical questions on the practical guideline of blepharoptosis. Aesthet Plast Surg 48:2389–2398CrossRefPubMed
7.
Shiraishi M, Kanayama K, Yang R, Okazaki M (2023) Preliminary evaluation of the potential of commercially available large language models in diagnosing skin tumours. Clin Exp Dermatol 49:741–743CrossRef
8.
9.
Ziegelmayer S, Marka AW, Lenhart N, Nehls N, Reischl S, Harder F, Hummel M, Schick A, Schmidt H (2023) Evaluation of GPT-4’s chest X-ray impression generation: a reader study on performance and perception. J Med Internet Res 25:e50865CrossRefPubMedPubMedCentral
10.
11.
Bock O, Schmid-Ott G, Malewski P, Mrowietz U (2006) Quality of life of patients with keloid and hypertrophic scarring. Arch Dermatol Res 297:433–438CrossRefPubMed
12.
Esselman PC, Thombs BD, Magyar-Russell G, Fauerbach JA (2006) Burn rehabilitation: state of the science. Am J Phys Med Rehabil 85:383–413CrossRefPubMed
13.
Berman B, Viera MH, Amini S, Huo R, Jones IS (2008) Prevention and management of hypertrophic scars and keloids after burns in children. J Craniofac Surg 19:989–1006CrossRefPubMed
14.
15.
Bijlard E, Kouwenberg CA, Timman R, Hovius SE, Busschbach JJ, Mureau MA (2017) Burden of keloid disease: a cross-sectional health-related quality of life assessment. Acta Derm Venereol 97:225–229CrossRefPubMed
16.
Menashe S, Heller L (2024) Keloid and hypertrophic scars treatment. Aesthetic Plast Surg 48:2553–2560CrossRefPubMed
17.
Baryza MJ, Baryza GA (1995) The Vancouver scar scale: an administration tool and its interrater reliability. J Burn Care Rehabil 16:535–538CrossRefPubMed
18.
Sullivan T, Smith J, Kermode J, McIver E, Courtemanche DJ (1990) Rating the burn scar. J Burn Care Rehabil 11:256–260CrossRefPubMed
19.
Ogawa R, Akita S, Akaishi S, Aramaki-Hattori N, Dohi T, Hayashi T, Shibata K, Takamatsu H, Kuroyanagi Y (2019) Diagnosis and treatment of keloids and hypertrophic scars—Japan scar workshop consensus document 2018. Burns Trauma 7:39CrossRefPubMedPubMedCentral
20.
Gauglitz GG, Korting HC, Pavicic T, Ruzicka T, Jeschke MG (2011) Hypertrophic scarring and keloids: pathomechanisms and current and emerging treatment strategies. Mol Med 17:113–125CrossRefPubMed
21.
Manca G, Pandolfi P, Gregorelli C, Cadossi M, de Terlizzi F (2013) Treatment of keloids and hypertrophic scars with bleomycin and electroporation. Plast Reconstr Surg 132:621e–630eCrossRefPubMed
22.
Koike S, Akaishi S, Nagashima Y, Dohi T, Hyakusoku H, Ogawa R (2015) Nd:YAG laser treatment for keloids and hypertrophic scars: an analysis of 102 cases. Plast Reconstr Surg Glob Open 2:e272CrossRefPubMedPubMedCentral
23.
Santos-Cortez RLP, Hu Y, Sun F, Benahmed-Miniuk F, Tao J, Kanaujiya JK, Smith SD, Kiefer J, Haines L, Teshima S (2017) Identification of ASAH1 as a susceptibility gene for familial keloids. Eur J Hum Genet 25:1155–1161CrossRefPubMedPubMedCentral
24.
Liu AH, Sun XL, Liu DZ, Xu F, Feng SJ, Zhang SY, Lin R, Wang L, Xu L, Chen H (2023) Epidemiological and clinical features of hypertrophic scar and keloid in Chinese college students: a university-based cross-sectional survey. Heliyon 9:e15345CrossRefPubMedPubMedCentral
25.
Zhu CY, Wang YK, Chen HP, Gao KL, Shu C, Wang JC, Xie Y, Zhang L, Liu Y, Wu Q (2021) A deep learning based framework for diagnosing multiple skin diseases in a clinical environment. Front Med (Lausanne) 8:626369CrossRefPubMed
26.
Ito H, Nakamura Y, Takanari K, Oishi M, Matsuo K, Kanbe M, Suzuki K, Nakano S, Yamada T, Tanaka R (2022) Development of a novel scar screening system with machine learning. Plast Reconstr Surg 150:465e–472eCrossRefPubMed
27.
Chang CW, Ho CY, Lai F, Christian M, Huang SC, Chang DH, Lin Y, Chiu J, Chen Y, Lee Y (2023) Application of multiple deep learning models for automatic burn wound assessment. Burns 49:1039–1051CrossRefPubMed
28.
Kim J, Oh I, Lee YN, Lee JH, Lee YI, Kim J, Park J, Choi J, Han Y, Cho S (2023) Predicting the severity of postoperative scars using artificial intelligence based on images and clinical data. Sci Rep 13:13448CrossRefPubMedPubMedCentral
29.
Ono D, Dickson DW, Koga S (2024) Evaluating the efficacy of few-shot learning for GPT-4Vision in neurodegenerative disease histopathology: a comparative analysis with convolutional neural network model. Neuropathol Appl Neurobiol 50:e12997CrossRefPubMed
30.
Gupta R, Park JB, Herzog I, Yosufi N, Mangan A, Firouzbakht PK, Shiu R, Patel R, Singh R, Roberts T (2023) Applying GPT-4 to the plastic surgery inservice training examination. J Plast Reconstr Aesthet Surg 87:78–82CrossRefPubMed
31.
Beltrami EJ, Grant-Kels JM (2024) Consulting ChatGPT: ethical dilemmas in language model artificial intelligence. J Am Acad Dermatol 90:879–880CrossRefPubMed
32.
Metadata
Title
The Potential of Chat-Based Artificial Intelligence Models in Differentiating Between Keloid and Hypertrophic Scars: A Pilot Study
Authors
Makoto Shiraishi
Shimpei Miyamoto
Hakuba Takeishi
Daichi Kurita
Kiichi Furuse
Jun Ohba
Yuta Moriwaki
Kou Fujisawa
Mutsumi Okazaki
Publication date
25-09-2024
Publisher
Springer US
Published in
Aesthetic Plastic Surgery
Print ISSN: 0364-216X
Electronic ISSN: 1432-5241
DOI
https://doi.org/10.1007/s00266-024-04380-9