Background: Malaria remains a significant public health concern in developing countries including Ethiopia. It is one cause of high-level of morbidity in the Amhara region. Distinct geographical regions have different factors that influence malaria transmission. So, the purpose of this study was to forecasting malaria outbreaks by using an empirical model developed in the Amhara region, in Ethiopia

Methods and analysis: A retrospective follow-up study was conducted from April 01 to 30, 2022. Regional malaria recorded cases were taken from 34 woredas and data base were extracted and entered in to SPSS Version 25. Finally, R version 4.0.4 was used for analysis. Bivariable logistic regression analysis was done, and the forecasting model was developed by backward stepwise multivariable logistic regression. Time series seasonal decomposition was included. The best model was selected by likelihood ratio score. Model accuracy was assessed by the area under the curve and calibration plot.  and           internally validated by the bootstrapping method. The results of significant predictors were reported as coefficients with 95% confidence intervals.

Result: A total of 919,586 malaria cases were confirmed from 34 woredas out of 3,839,034 total laboratories tests with a test positivity rate of 23.9%. Presence of irrigation (OR = 1.522, 95% CI = 1.161-2.142), sunshine above the mean (SH>=7.167) (OR = 4.104 95%, CI = 1.706-9.791), rain fall above the mean (>=98.178) (OR = 21.73% CI = 5.755-141.326) and minimum temperate pressure (OR = 0.956, 95% CI = 0.956-0.997) were significantly associated with malaria outbreaks in Amhara region. The p-value of the calibration belt was 0.798. Sensitivity and specificity of the model was 99.12% and 3.72% respectively.

Conclusions and recommendations: Sunshine, minimum temperature, rain fall and irrigation were important forecasting determinants for malaria outbreak in the Amhara region. Moreover, the risk model developed from the risk score had comparable prediction accuracy with a model created using coefficients. Climatic data, irrigation, distance related to malaria area, migrants related to its origin and other climatic related factors should be recorded from the origin.

Keywords: Keywords: Malarial outbreak, forecast, model, Ethiopia