SYNDROMIC SURVEILLANCE OF DENGUE USING THE EXPONENTIALLY WEIGHTED MOVING AVERAGE IN THE DISTRICT OF WESTERN MAHARASHTRA

Background: Public health officials require the immediate identification of dengue outbreaks. This study sought to evaluate the efficacy of the Exponentially Weighted Moving Average (EWMA) in identifying dengue outbreaks. Methods: The EWMA algorithms were utilized on daily dengue case counts to identify actual outbreaks in western Maharashtra, India, from January 2018 to December 2022. The EWMA model values were calculated for λ ranging from 0.1 to 0.9, and the Upper Control Limit (UCL) was determined for each EWMA model with a fixed k of 2 and σ equal to 1. The efficacy of EWMA models was evaluated through Sensitivity, Specificity, Positive Predictive Value, Negative Predictive Value, False Positive Rate, and False Negative Rate. Of the various algorithms, EWMA wit Results: h λ= 0.9 exhibited the most effective performance in detecting outbreaks from 2018 to 2022. The EWMA 9 (λ = 0.9) attains the optimal equilibrium among EWMA 1 to EWMA 9, exhibiting a sensitivity of 80.2%, specificity of 100%, positive predictive value of 100%, and negative predictive value of 90.9%. Using different EWMA settings ( Conclusion: λ and σ) showed that models with higher smoothing parameters EWMA 9, had improved sensitivity and specificity.