The COVID-19 pandemic served as a reminder of the necessity of efficient tracking and managing the disease spread or transmission. The study introduces an AI-based system of spread pattern analytics as part of the COVID-19 response. Utilizing data on mobile tracing applications in six Nigerian cities (Akure, Wukari, Osara, Calabar, Sokoto, and Anambra), the system employs multiple clustering algorithms (K-Means, DBSCAN, and Agglomerative Clustering) to analyze movement patterns and derive insights into transmission networks. The core analytical component is a rule-based alert system capable of producing notifications to health analysts on the development of emerging hotspots, driven by a set of decision rules embedded in a knowledge base. The user interface provides real-time conditions of the spread of the disease, which are supposed to facilitate timely and right decisions. Evaluation demonstrated the system's effectiveness in identifying arising hotspots, achieving an overall accuracy of 90.25% in classifying high-risk regions. The proposed scalable, data-driven framework establishes a practical model for improving national disease surveillance and emergent public health response in resource-limited settings.