Cholera is more likely to affect those who live near risky water resource basins and poor sanitation services. Accurate and early estimates of cholera outbreaks are required to implement preventative measures at the appropriate time. Using MDCNN as a prediction foundation, environmental data, water quality indicators, and previous epidemic registries may be used to better assess cholera illness. MDCNN employs wide connections between its convolutional layers to increase feature propagation while also lowering gradient disappearance, resulting in improved model outputs. This platform provides the precise results, complete data transparency, and rapid execution capabilities necessary for active prediction services, as well as public health warnings provided by the MDCNN, which may be utilized by government agencies to launch water purification and preventive vaccination programs. These difficulties stem from attempting to employ deep learning methods to comprehend complicated data sets. The strategy enhances public health management and, depending on the data, may help forecast illnesses. The proposed technique offers a novel approach to cholera monitoring system-specific forecasting, which may be used to a variety of disease prediction models.