Introduction: Diagnoses of diseases associated with COVID-19 become relevant considering their incidence and prevalence in central Mexico. Objective: The objective of this work was to compare a neural network model with the findings reported in the literature. Methodology: A documentary, cross-sectional, correlational, and retrospective work was conducted with a sample of 6,500 cases selected by centralized entity in Mexico. Results: The results demonstrate the learning sequence that goes from diagnoses to application entities, which reveals a collaborative network guided by tomography. Discussion: In relation to the state of the art where findings focused on decisions, collaborative strategies and knowledge management prevail, this work suggests including these dimensions to anticipate the responses of public health institutions in future health contingencies.