Disease Outbreak Detection Using Data Mining And Data Warehousing

The review of existing approaches in disease surveillance indicates that while various methods have been proposed for outbreak detection, ranging from traditional statistical models to spatio-temporal clustering and machine learning techniques, many systems remain limited in practical integration and scalability. Manual monitoring and threshold-based reporting are inefficient and reactive, whereas several advanced analytical models focus primarily on pattern identification without incorporating centralized data warehousing and user-friendly deployment frameworks. This gap highlights the need for a comprehensive, intelligent, and automated solution for effective disease outbreak detection.   The proposed Disease Outbreak Detection System aims to bridge this gap by integrating data warehousing, data mining, and machine learning into a unified platform. The system centralizes historical disease records structured by ICD-10 codes, automates data preprocessing and predictive modeling, and provides real-time outbreak probability predictions through a web-based interface. By combining structured storage with intelligent analytics, the solution enhances prediction accuracy, reduces manual workload, and supports proactive healthcare decision-making.

[1]  H. Kamran, D. M. Aleman, M. W. Carter, and K. M. Moore, “Spatio-Temporal Clustering of Multi-Location Time Series to Model Seasonal Influenza Spread,” IEEE Journal of Biomedical and Health Informatics, vol. 27, no. 4, pp. 2138–2148, Apr. 2023. [2]  World Health Organization, “Global Influenza Programme,” WHO, Geneva, Switzerland, 2015. [Online]. Available: http://www.who.int/influenza/en/ [3]  Centers for Disease Control and Prevention, “FluView: Influenza Surveillance Report,” CDC, Atlanta, GA, USA, 2022. [Online]. Available: https://www.cdc.gov/flu/weekly/ [4]  Public Health Agency of Canada, “FluWatch Report: Influenza Surveillance,” PHAC, Ottawa, ON, Canada, 2022. [Online]. Available: https://www.canada.ca/en/public-health/services/diseases/flu-influenza/influenza-surveillance.html [5]  X. Wang, A. Mueen, H. Ding, G. Trajcevski, P. Scheuermann, and E. Keogh, “Experimental Comparison of Representation Methods and Distance Measures for Time Series Data,” Data Mining and Knowledge Discovery, vol. 26, pp. 275–309, 2013. [6]  T. Giorgino, “Computing and Visualizing Dynamic Time Warping Alignments in R: The DTW Package,” Journal of Statistical Software, vol. 31, no. 7, pp. 1–24, 2009. [7]  B. Y. Reis and K. D. Mandl, “Time Series Modeling for Syndromic Surveillance,” BMC Medical Informatics and Decision Making, vol. 3, no. 2, 2003. [8]  H. Achrekar, A. Gandhe, R. Lazarus, S.-H. Yu, and B. Liu, “Predicting Flu Trends Using Twitter Data,” in Proc. IEEE Int. Conf. Computer Communications Workshops, 2011, pp. 702–707. [9]  D. Butler, “When Google Got Flu Wrong,” Nature, vol. 494, no. 7436, pp. 155–156, 2013. [10]     R. M. Anderson and R. M. May, Infectious Diseases of Humans: Dynamics and Control. Hoboken, NJ, USA: Wiley, 1992. [11]     C. Viboud et al., “Synchrony, Waves, and Spatial Hierarchies in the Spread of Influenza,” Science, vol. 312, no. 5772, pp. 447–451, 2006. [12]     L. Schiöler, “Characterisation of Influenza Outbreaks in Sweden,” Scandinavian Journal of Social Medicine, vol. 39, no. 4, pp. 427–436, 2011.