METHODS FOR PREDICTING AND CLASSIFYING VULNERABILITY OF TB CASES USING EXPONENTIAL SMOOTHING AND HIERARCHIAL CLUSTERING

Abstract

This invention relates to a method for predicting and classifying the vulnerability of Tuberculosis (TB) cases based on spatial-temporal analysis using the integration of Exponential Smoothing and Hierarchical Clustering methods implemented in an interactive Web GIS system. The invention aims to assist health agencies in mapping priority areas for TB treatment based on the results of the predicted number of cases and the classification of regional vulnerability levels. The method begins with collecting historical data on TB cases and regional indicator data, including the number of health facilities, the number of uninhabitable houses, population density, and environmental sanitation conditions. Next, the data pre-processing process is carried out, then the Exponential Smoothing method is used to predict the number of TB cases in the future period.The prediction results are used as one of the parameters in the classification process using the Hierarchical Clustering method to group regions based on the level of TB susceptibility. The analysis results are visualized in the form of an interactive risk map and a Web GIS-based analytical dashboard using Leaflet.js integrated with the PostgreSQL–PostGIS database. This invention produces a spatial-temporal analysis that is able to show historical conditions as well as projections of future regional risks so that it can be used as a decision support system in risk mapping, determining priority intervention areas, and controlling TB cases effectively and based on data.