Tuberculosis (TB) is known as a disease that prone to spatial clustering. Recent development has seen a sharp rise in the number of epidemiologic studies employing Geographical Information System (GIS), particularly in identifying TB clusters and evidences of etiologic factors. This retrospective population-based study was conducted to analyze spatial patterns of TB incidence in Punjab province, Pakistan. TB notification data from 2007 to 2017 collected from TB clinics throughout the province was used along with population data to reveal a descriptive epidemiology of TB incidences. Spatial distribution of the disease was observed by using ArcGis. Machine learning algorithms like ANN, SVM and Maximum Entropy were used to predict the presence of the disease with a prediction power of 82, 75 and 78 percent respectively. This study has also shown a heterogeneous pattern of the disease over the years with some consistently high risked areas. This study can be very helpful for policy makers to refine their policies for successful eradication of the disease. Identifying heterogeneity in the spatial distribution of TB cases and characterizing its drivers can help to inform targeted public health responses, making it an attractive approach. However, there are practical challenges in appropriate interpretation of spatial clusters of TB. Of particular importance is that the observed spatial pattern of TB may be affected by factors other than genuine TB transmission or reactivation, including the type and resolution of data and the spatial analysis methods used. For instance, use of incidence data versus notification data could give considerably different spatial pattern , as the latter misses a large number of TB cases and could be skewed towards areas with better access to health care in high-burden settings. Thus, spatial analysis using notification data alone in such settings could result in misleading conclusions .Similarly, the type of model used and the spatial unit of data analysis are important determinants of the patterns identified and their associations. That is, different spatial resolutions could lead to markedly different results for the same dataset regardless of the true extent of spatial correlation.
Submit manuscript via https://www.scholarscentral.org/submissions/epidemiology-open-access.html or email us at submissions@omicsonline.com
Regards
Alpine
Managing Editor
Epidemiology: Open Access