Evaluating Sex and Age Biases in Multimodal Large Language Models for Skin Disease Identification from Dermatoscopic Images

Background: Multimodal large language models (LLMs) have shown potential in various health-related fields. However, many healthcare studies have raised concerns about the reliability and biases of LLMs in healthcare applications. Methods: To explore the practical application of multimodal LLMs in sk...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhiyu Wan, Yuhang Guo, Shunxing Bao, Qian Wang, Bradley A. Malin
Format: Article
Language:English
Published: American Association for the Advancement of Science (AAAS) 2025-01-01
Series:Health Data Science
Online Access:https://spj.science.org/doi/10.34133/hds.0256
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849739640876040192
author Zhiyu Wan
Yuhang Guo
Shunxing Bao
Qian Wang
Bradley A. Malin
author_facet Zhiyu Wan
Yuhang Guo
Shunxing Bao
Qian Wang
Bradley A. Malin
author_sort Zhiyu Wan
collection DOAJ
description Background: Multimodal large language models (LLMs) have shown potential in various health-related fields. However, many healthcare studies have raised concerns about the reliability and biases of LLMs in healthcare applications. Methods: To explore the practical application of multimodal LLMs in skin disease identification, and to evaluate sex and age biases, we tested the performance of 2 popular multimodal LLMs, ChatGPT-4 and LLaVA-1.6, across diverse sex and age groups using a subset of a large dermatoscopic dataset containing around 10,000 images and 3 skin diseases (melanoma, melanocytic nevi, and benign keratosis-like lesions). Results: In comparison to 3 deep learning models (VGG16, ResNet50, and Model Derm) based on convolutional neural network (CNN), one vision transformer model (Swin-B), we found that ChatGPT-4 and LLaVA-1.6 demonstrated overall accuracies that were 3% and 23% higher (and F1-scores that were 4% and 34% higher), respectively, than the best performing CNN-based baseline while maintaining accuracies that were 38% and 26% lower (and F1-scores that were 38% and 19% lower), respectively, than Swin-B. Meanwhile, ChatGPT-4 is generally unbiased in identifying these skin diseases across sex and age groups, while LLaVA-1.6 is generally unbiased across age groups, in contrast to Swin-B, which is biased in identifying melanocytic nevi. Conclusions: This study suggests the usefulness and fairness of LLMs in dermatological applications, aiding physicians and practitioners with diagnostic recommendations and patient screening. To further verify and evaluate the reliability and fairness of LLMs in healthcare, experiments using larger and more diverse datasets need to be performed in the future.
format Article
id doaj-art-e9e6f30fa59840ad9a06a6506d8a0760
institution DOAJ
issn 2765-8783
language English
publishDate 2025-01-01
publisher American Association for the Advancement of Science (AAAS)
record_format Article
series Health Data Science
spelling doaj-art-e9e6f30fa59840ad9a06a6506d8a07602025-08-20T03:06:13ZengAmerican Association for the Advancement of Science (AAAS)Health Data Science2765-87832025-01-01510.34133/hds.0256Evaluating Sex and Age Biases in Multimodal Large Language Models for Skin Disease Identification from Dermatoscopic ImagesZhiyu Wan0Yuhang Guo1Shunxing Bao2Qian Wang3Bradley A. Malin4Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, TN, USA.School of Biomedical Engineering, ShanghaiTech University, Shanghai, China.Department of Electrical and Computer Engineering, Vanderbilt University, Nashville, TN, USA.School of Biomedical Engineering, ShanghaiTech University, Shanghai, China.Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, TN, USA.Background: Multimodal large language models (LLMs) have shown potential in various health-related fields. However, many healthcare studies have raised concerns about the reliability and biases of LLMs in healthcare applications. Methods: To explore the practical application of multimodal LLMs in skin disease identification, and to evaluate sex and age biases, we tested the performance of 2 popular multimodal LLMs, ChatGPT-4 and LLaVA-1.6, across diverse sex and age groups using a subset of a large dermatoscopic dataset containing around 10,000 images and 3 skin diseases (melanoma, melanocytic nevi, and benign keratosis-like lesions). Results: In comparison to 3 deep learning models (VGG16, ResNet50, and Model Derm) based on convolutional neural network (CNN), one vision transformer model (Swin-B), we found that ChatGPT-4 and LLaVA-1.6 demonstrated overall accuracies that were 3% and 23% higher (and F1-scores that were 4% and 34% higher), respectively, than the best performing CNN-based baseline while maintaining accuracies that were 38% and 26% lower (and F1-scores that were 38% and 19% lower), respectively, than Swin-B. Meanwhile, ChatGPT-4 is generally unbiased in identifying these skin diseases across sex and age groups, while LLaVA-1.6 is generally unbiased across age groups, in contrast to Swin-B, which is biased in identifying melanocytic nevi. Conclusions: This study suggests the usefulness and fairness of LLMs in dermatological applications, aiding physicians and practitioners with diagnostic recommendations and patient screening. To further verify and evaluate the reliability and fairness of LLMs in healthcare, experiments using larger and more diverse datasets need to be performed in the future.https://spj.science.org/doi/10.34133/hds.0256
spellingShingle Zhiyu Wan
Yuhang Guo
Shunxing Bao
Qian Wang
Bradley A. Malin
Evaluating Sex and Age Biases in Multimodal Large Language Models for Skin Disease Identification from Dermatoscopic Images
Health Data Science
title Evaluating Sex and Age Biases in Multimodal Large Language Models for Skin Disease Identification from Dermatoscopic Images
title_full Evaluating Sex and Age Biases in Multimodal Large Language Models for Skin Disease Identification from Dermatoscopic Images
title_fullStr Evaluating Sex and Age Biases in Multimodal Large Language Models for Skin Disease Identification from Dermatoscopic Images
title_full_unstemmed Evaluating Sex and Age Biases in Multimodal Large Language Models for Skin Disease Identification from Dermatoscopic Images
title_short Evaluating Sex and Age Biases in Multimodal Large Language Models for Skin Disease Identification from Dermatoscopic Images
title_sort evaluating sex and age biases in multimodal large language models for skin disease identification from dermatoscopic images
url https://spj.science.org/doi/10.34133/hds.0256
work_keys_str_mv AT zhiyuwan evaluatingsexandagebiasesinmultimodallargelanguagemodelsforskindiseaseidentificationfromdermatoscopicimages
AT yuhangguo evaluatingsexandagebiasesinmultimodallargelanguagemodelsforskindiseaseidentificationfromdermatoscopicimages
AT shunxingbao evaluatingsexandagebiasesinmultimodallargelanguagemodelsforskindiseaseidentificationfromdermatoscopicimages
AT qianwang evaluatingsexandagebiasesinmultimodallargelanguagemodelsforskindiseaseidentificationfromdermatoscopicimages
AT bradleyamalin evaluatingsexandagebiasesinmultimodallargelanguagemodelsforskindiseaseidentificationfromdermatoscopicimages