Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{195445,
        author = {KNVS Manasvi and Pavude Sridevi and Dhanvi Sompalli and B. Gnana Prasuna},
        title = {AI-Driven Skin Disease Diagnosis and Classification for Humans},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {26-31},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=195445},
        abstract = {Skin problems are very common in the world, and at times it is difficult to check them early, especially when people lack access to a dermatologist or even know what to check for. In addition, the physical examination of the skin by a human being is somewhat subjective, at least to me, and therefore it is a slow process. The main goal of this paper is to design an intelligent system that can assist in the immediate diagnosis of a person’s skin problems, changing the conventional way of checking to a more accessible form to everyone. It’s all built on a web platform, which essentially ties a few key things together. Like, user login, which is secure, and then smart use of images that are uploaded, and then the AI that’s trying to figure out what kind of disease it’s looking at based on what it’s seeing. There’re even pieces for information on the diseases that are well organized, and a dashboard for admins to manage all of this. It’s all well connected but not overly complicated. At the heart of all of this is this part about deep learning, which uses convolutional neural networks, or CNNs, to make precise predictions about skin diseases. There are also instances when generative adversarial networks, or GANs, are employed to increase the data set, hence the model, to combat any changes. While I am not sure just how well all of this integrates, I think it promises well. It was implemented using Python programming language along with the Streamlit library. A modular approach was chosen to increase its scalability if needed in the future and to increase its performance to work in real-time. There is a lot of emphasis on usability, I think, since it’s meant to be used by regular people. It was implemented using Python programming language along with the Streamlit library. A modular approach was chosen to increase its scalability if needed in the future and to increase its performance to work in real-time. There is a lot of emphasis on usability, I think, since it’s meant to be used by regular people. What’s interesting to note here is the way computer vision and analytics are being leveraged to speed up the early detection process and reduce waiting times for human review. It brings dermatology knowledge to many more people, increases awareness about symptoms and prevention, and basically makes healthcare a lot less out-of-reach. This kind of AI could be a real step forward for digital health, even if parts of it could be tweaked for better usage},
        keywords = {Skin Disease Detection, Artificial Intelligence in Healthcare, Deep Learning, Convolutional Neural Network.},
        month = {March},
        }