Artificial Intelligent Framework for Semantic-Driven Disease Surveillance Using Machine Learning

Effective disease surveillance is essential for early detection and control of outbreaks; however, traditional systems often suffer from fragmented data sources, limited interpretability, and low predictive accuracy. Recent advances in artificial intelligence offer opportunities to enhance surveillance through intelligent data analysis. This study proposes a semantic-driven disease surveillance framework that integrates machine learning with ontology-based knowledge representation. The system employs a multi-layered architecture comprising data acquisition, preprocessing, semantic enrichment, and predictive modeling. Supervised learning algorithms, including Random Forest and Support Vector Machines, are applied to semantically enhanced datasets for classification and anomaly detection. Experimental evaluation demonstrates that the proposed model achieves superior performance, with an accuracy of 94.5%, precision of 93.2%, recall of 92.8%, and F1-score of 93.0%. The confusion matrix shows minimal misclassification, while the ROC curve indicates a high Area Under the Curve (AUC), confirming strong discriminative capability. The integration of semantic technologies with machine learning significantly improves predictive accuracy, interpretability, and decision-making in disease surveillance systems. The proposed framework provides a scalable and efficient solution for real-time monitoring and early outbreak detection in modern healthcare environments.