@article {10.3844/jcssp.2025.2928.2939,
article_type = {journal},
title = {A Comparative Study of Machine Learning Algorithms for Skin Cancer Detection},
author = {Victor, Vineeth and Tyagi, Amit Kumr and Tripathi, Khushboo and Rai, Kajal and Chaturvedi, Ravi Prakash and Kumar, Lalan and Siddhi, Pragya},
volume = {21},
number = {12},
year = {2026},
month = {Jan},
pages = {2928-2939},
doi = {10.3844/jcssp.2025.2928.2939},
url = {https://thescipub.com/abstract/jcssp.2025.2928.2939},
abstract = {The skin is the largest organ in the human body, covering an area of around 20 square feet. Our skin keeps us safe from germs and the environment, helps us regulate our body temperature, and gives us the ability to feel touch, heat, and cold. More than 95 percent of all skin cancers are caused by ultraviolet (UV) radiation. UV radiation is emitted by the sun, although it is unrelated to sunshine or heat, as many people believe. The key factor that causes skin cells to become cancer cells is exposure to UV radiation. Overexposure to UV radiation causes almost all skin cancers (about 99 percent of non-melanoma skin cancers and 95 percent of melanoma). Sunburn has been shown to play a significant role in the development of melanoma, the most dangerous of the three most common types of skin cancer. According to research, UV rays can alter a gene that suppresses tumours, increasing the risk of sun-damaged skin cells turning into skin cancer. Melanoma is the worst form of skin cancer and one of the most common cancers. Melanoma rates are quickly increasing, particularly in young people and have increased in the previous 30 years, despite the fact that cancer rates for other prevalent cancers have decreased. Melanoma is highly treatable if found early. While late-stage melanoma treatments are quickly improving, prevention and early detection remain the best treatment options. Our study delves into the critical realm of skin cancer detection with the aim of evaluating the efficacy of various cutting-edge machine learning algorithms including Random Forest, Support Vector Machine, and CNN is exploring skin cancer patterns. Through careful examination, utilizing metrics like accuracy, precision, and recall, we highlight the superior performance of SVC and CNN. Our research not only contributes to the ongoing studies in skin cancer detection but also underscores the potential of advanced computational strategies in augmenting preventive healthcare strategies.},
journal = {Journal of Computer Science},
publisher = {Science Publications}
}