Introduction:

Different populations coexistence scenarios are very complex, which contributes to the spread of diseases. Diagnosing infectious diseases early is a critical task in reducing its spread and preventing epidemics. However, inconsistency in population data and the inability to have timely diagnosis in many cases result in the proliferation of pandemics such as COVID-19.

Objective:

Develop a support system for COVID-19 medical diagnostic from modeling causal relations of diagnostic criteria, to form the diffuse cognitive map.

Methods:

Theoretical, empirical and statistical methods were used for the development of the research, such as: analytical-synthetic, inductive-deductive, hypothetical-deductive, modeling. As an empirical method, the semi-structured interview was used with the intention of collecting information that would include unprescribed contents and require expert knowledge of the main indicators for decision-making in COVID-19 medical diagnosis.

Results:

The system works through a diffuse cognitive map to model causal relationships that represent the inference´s basis. Artificial intelligence techniques are used as a basis for medical diagnosis. A demonstrative example is presented for COVID-19 medical diagnosis in which are modelled the causal relations of the different concepts that the disease describes.

Conclusions:

The designed system is a viable support tool for decision-making in COVID-19 medical diagnosis, which allows to obtain evaluative criteria from the modelling of causal relations, and this makes it extendable to other types of health emergencies situations.

        · abstract in Spanish     · text in Spanish     · Spanish ( pdf )