An Approach Based on Fuzzy Cognitive Maps with Federated Learning to Predict Severity in Viral Diseases

Viral diseases such as dengue and COVID-19 constitute a public health problem due to high morbidity and mortality rates when diagnosis is not rapid and appropriate. The difficulties in the diagnostic process of these diseases lie in the variability of the clinical manifestations and the similarity with other viral diseases such as Zika and chikungunya. The implementation of computer-aided approaches can support medical professionals to support and improve decision making. In this article, we propose two medical decision support systems for severity prediction in dengue and COVID-19. The proposed systems use fuzzy cognitive maps for prediction and federated learning to increase the feature space, sample size, and ensure data privacy and security. The models were evaluated using dengue and COVID-19 datasets, and the results showed good performance in predicting severity and classifying patients. The implementation of the proposed systems in real clinical settings would be useful for the diagnosis of viral diseases such as dengue and COVID-19.