<![CDATA[Skin diseases are among the most common health problems affecting the community. This study aims to develop a skin disease classification system based on symptoms using the K-Nearest Neighbor (KNN) algorithm and to provide treatment recommendations. The dataset used consists of 405 records containing disease symptoms, disease location, disease shape, disease name, and treatment recommendations. Text-based symptom data were transformed into numerical representations using the Term Frequency-Inverse Document Frequency (TF-IDF) method before the classification process was carried out using the KNN algorithm. The experiments were conducted using K values of 3, 5, and 7. The results showed that the best performance was achieved with K=7, obtaining an accuracy of 90.12%, a precision of 0.91, a recall of 0.93, and an F1-score of 0.91. Meanwhile, K=5 achieved an accuracy of 88.89%, and K=3 achieved an accuracy of 87.65%. Furthermore, the system was successfully implemented using Streamlit, allowing users to interactively classify skin diseases and obtain treatment recommendations based on the symptoms entered.]]>
Copyrights © 2026
