Dengue fever is a tropical disease whose diagnosis is often delayed due to limitations of conventional diagnostic methodologies, which have an impact on the effectiveness of medical interventions. This research is designed to develop an Artificial Neural Network (ANN) model aimed at improving accuracy and speed in dengue diagnosis. Through quantitative methods, clinical data from 50 patients during the period 2020-2021 were analyzed using machine learning techniques to train the ANN model, including the process of data normalization and selection of relevant features. The test results of the model showed excellent diagnostic performance with accuracy reaching 87%, precision 92%, and F1-Score 92%, indicating its effective ability to identify positive and negative cases. The conclusion of this study is that the developed ANN model is able to overcome the limitations of conventional diagnostics and shows significant potential in improving medical responses to dengue outbreaks. Further research is recommended to expand the datasets used in order to improve the validation and generalization of the model in the context of broader clinical applications