ARTIFICIAL INTELLIGENCE-BASED SUPERVISED LEARNING APPROACHES FOR DERMATOPHYTOSIS PREDICTION

Abstract

Artificial Intelligence (AI) has emerged as an important technology in modern healthcare, particularly in disease prediction and medical diagnosis. Dermatophytoses are common fungal skin infections that are increasing globally due to environmental factors such as rising temperature and humidity. Early and accurate diagnosis of these infections is essential for effective treatment and prevention of complications. This study investigates the application of supervised machine learning techniques for dermatophytoses prediction using clinical dermatology data. The research utilizes the publicly available Dermatology Dataset obtained from the UCI Machine Learning Repository. Several preprocessing techniques, including handling missing values, normalization, and feature selection, were applied to improve data quality and model performance. Two supervised learning algorithms, Support Vector Machine (SVM) and K-Nearest Neighbors (KNN), were implemented and evaluated for disease classification. The dataset was divided into training and testing subsets using an 80:20 ratio. The performance of both models was evaluated using standard classification metrics such as accuracy, precision, recall, F1-score, and confusion matrix analysis. Experimental results demonstrated that the SVM model outperformed the KNN model in predicting dermatological disease patterns. The SVM classifier achieved an accuracy of approximately 91%, while KNN achieved an accuracy of approximately 85%. In addition, SVM produced fewer false predictions and showed better generalization capability compared to KNN.

The findings of this study highlight the effectiveness of supervised learning approaches in supporting dermatological disease prediction and healthcare decision-making. The results suggest that Support Vector Machine (SVM) is a more reliable and accurate model for dermatophytoses prediction. This research also demonstrates the potential of Artificial Intelligence in improving early diagnosis and enhancing healthcare services in dermatology.