Early Detection of Skin Diseases Across Diverse Skin Tones Using Hybrid Machine Learning and Deep Learning Models

Aquil, Akasha and Saeed, Faisal and Baowidan, Souad and Ali, Abdullah Marish and Elmitwally, Nouh (2025) Early Detection of Skin Diseases Across Diverse Skin Tones Using Hybrid Machine Learning and Deep Learning Models. Information, 16 (2). ISSN 2078-2489

Preview

Text information-16-00152.pdf - Published Version Available under License Creative Commons Attribution. Download (3MB)

Abstract

Skin diseases in melanin-rich skin often present diagnostic challenges due to the unique characteristics of darker skin tones, which can lead to misdiagnosis or delayed treatment. This disparity impacts millions within diverse communities, highlighting the need for accurate, AI-based diagnostic tools. In this paper, we investigated the performance of three machine learning methods—Support Vector Machines (SVMs), Random Forest (RF), and Decision Trees (DT)—combined with state-of-the-art (SOTA) deep learning models: EfficientNet, MobileNetV2, and DenseNet121, for predicting skin conditions using dermoscopic images from the HAM10000 dataset. Features were extracted using the deep learning models, with labels encoded numerically. To address data imbalance, SMOTE and resampling techniques were applied. Additionally, Principal Component Analysis (PCA) was used for feature reduction, and fine-tuning was performed to optimize the models. The results demonstrated that RF with DenseNet121 achieved superior accuracy of 98.32%, followed by SVM with MobileNetV2 at 98.08%, and Decision Tree with MobileNetV2 at 85.39%. The proposed methods overcome the SVM with SOTA EfficientNet model, validating the robustness of the proposed approaches. Evaluation metrics such as accuracy, precision, recall, and F1-score were used to benchmark performance, showcasing the potential of these methods in advancing skin disease diagnostics for diverse populations.

Item Type:	Article
Identification Number:	10.3390/info16020152
Dates:	Date Event 9 February 2025 Accepted 19 February 2025 Published Online
Uncontrolled Keywords:	Machine Learning, Skin Diseases, Diverse Skin Tones, dermoscopic images, Random Forest, SVM, Decision Tree
Subjects:	CAH11 - computing > CAH11-01 - computing > CAH11-01-01 - computer science
Divisions:	Faculty of Computing, Engineering and the Built Environment > College of Computing
Depositing User:	Nouh Elmitwally
Date Deposited:	11 Feb 2025 10:14
Last Modified:	03 Mar 2025 15:03
URI:	https://www.open-access.bcu.ac.uk/id/eprint/16131

Actions (login required)

View Item