|
Advancing Dermatological Care through AI: A Deep Learning-Based LINE Chatbot for Skin Disease Diagnosis |
|---|---|
| รหัสดีโอไอ | |
| Creator | Prem Enkvetchakul |
| Title | Advancing Dermatological Care through AI: A Deep Learning-Based LINE Chatbot for Skin Disease Diagnosis |
| Contributor | Waranya Chawooram, Adisorn Pluempan, Sangdaow Noppitak |
| Publisher | Faculty of Informatics, Mahasarakham University |
| Publication Year | 2569 |
| Journal Title | Journal of Applied Informatics and Technology |
| Journal Vol. | 8 |
| Journal No. | 1 |
| Page no. | 257065 |
| Keyword | Data Augmentation, Deep Learning, Diagnosis, LINE Chatbot, Skin Disease |
| URL Website | https://ph01.tci-thaijo.org/index.php/jait |
| Website title | Journal of Applied Informatics and Technology |
| ISSN | 3088-1803 |
| Abstract | This paper presents the development and deployment of a LINE chatbotfor diagnosing skin diseases using advanced deep learning techniques, ad-dressing the challenge of timely and accurate diagnosis in resource-limitedsettings. While previous studies have explored convolutional neural net-works (CNNs) for medical image classification, our research distinguishesitself by integrating MobileNetV2, DenseNet201, and EfficientNetB4 ar-chitectures within a mobile messaging platform. These CNN architecturesare well-recognized for their robustness in image analysis, yet few stud-ies have harnessed their potential in real-time diagnostic tools accessibleto the general public via widely-used platforms like LINE. Our chatbotfacilitates the immediate assessment of user-uploaded images, offering aproactive tool for managing skin health. By leveraging deep learning,we enhance diagnostic accuracy and reduce the reliance on traditionalmedical consultations. Experimental results indicate that our approachnot only improves diagnosis precision but also extends the accessibilityof dermatological care, particularly in underserved regions. This workcontributes to the growing body of mobile health technologies by show-casing the transformative potential of AI-driven solutions in healthcare.The novelty of our research lies in the seamless integration of cutting-edgeCNNs into an easy-to-use chatbot, enabling real-time, remote diagnosticsin a practical, scalable manner. |
