Melanoma remains the most lethal form of skin cancer, responsible for the majority of skin cancer-related fatalities despite its relatively low incidence. Melanoma can spread to different parts of the body if it is not identified and treated in its early stages. In previous work on melanoma classification, the VGG16 architecture of the CNN performed better on the cancer dataset than any other popular network. The early detection of melanoma by analyzing skin lesion images aims to enhance early diagnosis and accessibility. However, a significant challenge arises when incorporating demographic factors as biases in training data, as they can lead to disparities in model performance across different populations. These biases often stem from the underrepresentation of certain demographic groups in medical datasets, leading to lower accuracy for underserved communities. Such disparities can have serious consequences, including delayed diagnoses and inadequate treatment recommendations, further increasing healthcare inequities. Therefore, this study examines the effects of demographic factors such as age, gender, and data scalability on the early detection of melanoma. It also evaluates and compares two distinct deep learning approaches for classifying melanoma from dermoscopic images and associated patient metadata. The first experiment establishes a baseline using a VGG-16 convolutional neural network (CNN) trained via transfer learning. The second, expanded experiment introduces a novel multimodal ensemble model that synergistically combines an EfficientNetB0 CNN with a Multi-Layer Perceptron (MLP) to process both image and tabular data concurrently.
- Open Access
- Article
Unraveling the Effect of Demographic Factors on the Performance of Melanoma Classification
- Arav Kumar,
- Savya Vats,
- Anvi Kumar,
- Arjun Sriram,
- Avimanyou Vatsa *
Author Information
Received: 22 May 2026 | Revised: 16 Jun 2026 | Accepted: 18 Jun 2026 | Published: 30 Jun 2026
Abstract
Keywords
skin cancer | melanoma | classification | CNN | VGG16 | ensemble | performance analysis
References
- 1.
O’shea, K.; Nash, R. An Introduction to Convolutional Neural Networks. arXiv 2015, https://doi.org/10.48550/arXiv.1511.08458.
- 2.
Kosary, C.L.; Altekruse, S.F.; Ruhl, J.; et al. Clinical and prognostic factors for melanoma of the skin using SEER registries: Collaborative stage data collection system, version 1 and version 2. Cancer 2014, 120 (Suppl. 23), 3807–3814. https://doi.org/10.1002/cncr.29050.
- 3.
Melanoma Skin Cancer. Available online: https://www.cancer.org/cancer/melanoma-skin-cancer.html (accessed on 15 January 2024).
- 4.
Han, S.S.; Park, I.; Eun Chang, S.; et al. Augmented Intelligence Dermatology: Deep Neural Networks Empower Medical Professionals in Diagnosing Skin Cancer and Predicting Treatment Options for 134 Skin Disorders. J. Investig. Dermatol. 2020, 140, 1753–1761. https://doi.org/10.1016/j.jid.2020.01.019.
- 5.
Milton, M.A.A. Automated skin lesion classification using ensemble of deep neural networks in ISIC 2018: Skin lesion analysis towards melanoma detection challenge. arXiv 2019, arXiv:1901.10802.
- 6.
Edis, D.; Hayman, T.; Vatsa, A. Understanding Complex Malware. In Proceedings of the 2021 IEEE Integrated STEM Education Conference (ISEC), Princeton, NJ, USA, 13 March 2021. https://doi.org/10.1109/ISEC52395.2021.9763932.
- 7.
Kumar, A.; Vatsa, A. Influence of GFP GAN on Melanoma Classification. In Proceedings of the 2022 IEEE Integrated STEM Education Conference (ISEC), Princeton, NJ, USA, 26 March 2022. https://doi.org/10.1109/ISEC54952.2022.10025075.
- 8.
Miller, A.; Jan, T.R.; Small, Q.; et al. GAN Assistance in Diagnosis of Melanoma. In Proceedings of the 2022 IEEE Integrated STEM Education Conference (ISEC), Princeton, NJ, USA, 26 March 2022. https://doi.org/10.1109/ISEC54952.2022.10025328.
- 9.
Jan, T.R.; Miller, A.; Small, Q.; et al. Effect of Cycle GAN inMelanoma Classification. In Proceedings of the 2022 IEEE Integrated STEMEducation Conference (ISEC), Princeton, NJ, USA, 26March 2022. https://doi.org/10.1109/ISEC54952.2022.10025273.
- 10.
Small, Q.; Vatsa, A.K.; Jan, T.R.; et al. Unsupervised GAN for Melanoma. In Proceedings of the 2022 IEEE Integrated STEM Education Conference (ISEC), Princeton, NJ, USA, 26 March 2022. https://doi.org/10.1109/ISEC54952.2022.10025272.
- 11.
Chang, H. Skin cancer reorganization and classification with deep neural network. arXiv 2017, arXiv:1703.00534.
- 12.
Hearne, L.B.; Kelly, D.; Vatsa, A.; et al. Statistical Linkage across High Dimensional Observational Domains. In Proceedings of the ITI 2013 35th International Conference on Information Technology Interfaces, Cavtat, Croatia, 24–27 June 2013; pp. 239–244. https://doi.org/10.2498/iti.2013.0554.
- 13.
Vatsa, A. SDFS: A Standardization Technique for Nonparametric Analysis. Int. J. Eng. Sci. Technol. 2021, 3, 30–43. Available online: https://ijonest.net/index.php/ijonest/article/view/31 (accessed on 15 January 2024).
- 14.
Kumar, A.; Vatsa, A. Untangling Classification Methods for Melanoma Skin Cancer. Front. Big Data Data Min. Manag. 2022, 5, 848614. https://doi.org/10.3389/fdata.2022.848614.
- 15.
Vieira, J.; Mendonca, F.; Morgado-Dias, F. Deep Learning Approaches for Skin Lesion Detection. Electronics 2025, 14, 2785. https://doi.org/10.3390/electronics14142785.
- 16.
Dietterich, T.G. Ensemble Methods in Machine Learning. In Proceedings of the Multiple Classifier Systems (MCS 2000), Cagliari, Italy, 21–23 June 2020; Lecture Notes in Computer Science; Springer: Berlin, Heidelberg, 2020; Volume 1857. https://doi.org/10.1007/3-540-45014-9 1.
- 17.
Fort, S.; Hu, C.H.; Lakshminarayanan, B. Deep Ensembles: A Loss Landscape Perspective. Available online: https://openreview.net/forum?id=r1xZAkrFPr (accessed on 15 January 2024).
- 18.
Huang, G.; Li, Y.; Pleiss, G.; et al. Snapshot Ensembles: Train 1, get M for free. arXiv 2017, arXiv.1704.00109.
- 19.
Ali, R.; Hardie, R.C.; Narayanan Narayanan, B.; et al. Deep Learning Ensemble Methods for Skin Lesion Analysis towards Melanoma Detection. In Proceedings of the 2019 IEEE National Aerospace and Electronics Conference (NAECON), Dayton, OH, USA , 15–19 July 2019; pp. 311–316. https://doi.org/10.1109/NAECON46414.2019.9058245.
- 20.
Guo, Y.; Ashour, A. Multiple Convolutional Neural Network for Skin Dermoscopic Image Classification. In Proceedings of the 2018 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT), Louisville, KY, USA, 6–8 December 2018. https://doi.org/10.48550/arXiv.1807.08114.
- 21.
Kelly, D.; Vatsa, A.; Mayham, W.; et al. An opinion on imaging challenges in phenotyping field crops. Mach. Vision Appl. 2016, 27, 681–694. https://doi.org/10.1007/s00138-015-0728-4.
- 22.
Kelly, D.; Vatsa, A.; Mayham, W.; et al. Extracting complex lesion phenotypes in Zea mays. Mach. Vis. Appl. 2016, 27, 145–156. https://doi.org/10.1007/s00138-015-0718-6.
- 23.
Kumar, A.; Kapelyan, A.; Vatsa, A. Classification of Skin Phenotype: Melanoma Skin Cancer. In Proceedings of the 2021 IEEE Integrated STEM Education Conference (ISEC), Princeton, NJ, USA, 13 March 2021. https://doi.org/10.1109/ISEC52395.2021.9763999.
- 24.
Vatsa, A. Characterizing Low-Dimensional Phenotypes by Clustering. Master’s Thesis, University of Missouri, Columbia, MO, USA, 2015.
- 25.
Vatsa, A. An Approach to Clustering Biological Phenotypes. Ph.D. Thesis, University of Missouri, Columbia, MO, USA, 2017.
- 26.
Wolmer, J.; Vatsa, A.; Weiss, D. Retrieval of Data from the Database of a BCT—Voting System. In Proceedings of the 2022 IEEE Integrated STEM Education Conference (ISEC), Princeton, NJ, USA, 26 March 2022. https://doi.org/10.1109/ISEC54952.2022.10025062.
- 27.
Vatsa, A.; Lee, D.; Sullivan, B.; et al. Enumeration of Birds using Video Segmentation for a Better Understanding of Bird Behaviors. In Proceedings of the 2023 IEEE Integrated STEM Education Conference (ISEC), Laurel, MD, USA, 11 March 2023. https://doi.org/10.1109/ISEC57711.2023.10402158.
- 28.
Breiman, L. Random Forests. Available online: https://www.stat.berkeley.edu/∼breiman/randomforest2001.pdf (accessed on 15 January 2024).
- 29.
Kumar, A.; Vats, S.; Kumar, A.; et al. Challenges and Applications of AI in Healthcare: A Review. In Proceedings of the 2023 IEEE Integrated STEM Education Conference (ISEC), Laurel, MD, USA, 11 March 2023. https://doi.org/10.1109/ISEC57711.2023.10402195.
- 30.
Vatsa, A.; Kumar, A.; Vats, S.; et al. Comparing the Performance of Classification Algorithms for Melanoma Skin Cancer. In Proceedings of the 2023 IEEE Integrated STEM Education Conference (ISEC), Laurel, MD, USA, 11 March 2023. https://doi.org/10.1109/ISEC57711.2023.10402205.
- 31.
Chen, T.; Guestrin, C. XGBoost: A Scalable Tree Boosting System. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD ’16), San Francisco, CA, USA, 13–17 August 2016; pp. 785–794. https://doi.org/10.1145/2939672.2939785.
- 32.
Kumar, P.; Singhal, N.; Asim, M.; et al. An Optimized Authentication Mechanism for Mobile Agents by Using Machine Learning. Int. J. Comput. Netw. Inf. Secur. 2023, 15, 30–39. https://doi.org/10.5815/ijcnis.2023.06.03.
- 33.
Vatsa, A.; Zhang, K.; Quinche-Dutan, K.G. Maize Phenotype Classification Using GNN: Research Perspective. In Proceedings of the 2024 IEEE Integrated STEM Education Conference (ISEC), Princeton, NJ, USA, 9 March 2024. https://doi.org/10.1109/ISEC61299.2024.10665023.
- 34.
Sriram, A.; Vatsa, A.; Kumar, A.; et al. Challenges and Opportunities in Malignant Image Reconstruction Using GAN: A Review. In Proceedings of the 2024 IEEE Integrated STEM Education Conference (ISEC), Princeton, NJ, USA, 9 March 2024. https://doi.org/10.1109/ISEC61299.2024.10664911.
- 35.
Dataset 1. Available online: https://www.kaggle.com/competitions/siim-isic-melanoma-classification/data (accessed on 15 January 2024).
- 36.
Dataset 2. Available online: https://www.kaggle.com/datasets/drscarlat/melanoma (accessed on 15 January 2024).
- 37.
Dataset 3. Available online: https://www.kaggle.com/datasets/hasnainjaved/melanoma-skin-cancer-dataset-of-10000-images (accessed on 15 January 2024).
- 38.
Dataset 4. Available online: https://www.kaggle.com/datasets/wanderdust/skin-lesion-analysis-toward-melanoma-detection?select=skin-lesions (accessed on 15 January 2024).
- 39.
Dataset 5. Available online: https://www.kaggle.com/datasets/nodoubttome/skin-cancer9-classesisic (accessed on 15 January 2024).
- 40.
Dataset 6. Available online: https://challenge.isic-archive.com/data/ (accessed on 15 January 2024).
- 41.
Yuan, T.-A.; Lu, Y.; Edwards, K.; et al. Race-, Age-, and Anatomic Site-Specific Gender Differences in Cutaneous Melanoma Suggest Differential Mechanisms of Early-and Late-Onset Melanoma. Int. J. Environ. Res. Public Health 2019, 16, 908. https://doi.org/10.3390/ijerph16060908.
This work is licensed under a Creative Commons Attribution 4.0 International License.
Suite 4002 Level 4, 447 Collins Street, Melbourne, Victoria 3000, Australia
General Inquiries: info@sciltp.com