Feature selection reveal peripheral blood parameter's changes between COVID-19 infections patients from Brazil and Ecuador.

The investigation of conventional complete blood-count (CBC) data for classifying the SARS-CoV-2 infection status became a topic of interest, particularly as a complementary laboratory tool in developing and third-world countries that financially struggled to test their population. Although hematological parameters in COVID-19-affected individuals from Asian and USA populations are available, there are no descriptions of comparative analyses of CBC findings between COVID-19 positive and negative cases from Latin American countries. In this sense, machine learning techniques have been employed to examine CBC data and aid in screening patients suspected of SARS-CoV-2 infection. In this work, we used machine learning to compare CBC data between two highly genetically distinguished Latin American countries: Brazil and Ecuador. We notice a clear distribution pattern of positive and negative cases between the two countries. Interestingly, almost all red blood cell count parameters were divergent. For males, neutrophils and lymphocytes are distinct between Brazil and Ecuador, while eosinophils are distinguished for females. Finally, neutrophils, lymphocytes, and monocytes displayed a particular distribution for both genders. Therefore, our findings demonstrate that the same set of CBC features relevant to one population is unlikely to apply to another. This is the first study to compare CBC data from two genetically distinct Latin American countries.

A BRBES to Support Diagnosis of COVID-19 Using Clinical and CT Scan Data

In the prevailing COVID-19 pandemic, accurate diagnosis plays a vital role in preventing the mass transmission of the SARS-CoV-2 virus. Especially patients with pneumonia need correct diagnosis for proper treatment of their respiratory distress. However, the current standard diagnosis method, RT-PCR testing has a significant false negative and false positive rate. As alternatives, diagnosis methods based on artificial intelligence can be applied for faster and more accurate diagnosis. Currently, various machine learning and deep learning techniques are being researched on to develop better COVID-19 diagnosis system. However, these approaches do not consider the uncertainty in data. Deep learning approaches use backpropagation. It is an unexplainable black box approach and is prone to problems like catastrophic forgetting. This article applies a belief rule-based expert system (BRBES) for diagnosis of COVID-19 on hematological data and CT scan data of lung tissue infection of adult pneumonia patients. The system is optimized with nature-inspired optimization algorithm—BRBES-based adaptive differential evolution (BRBaDE). This model has been evaluated on a real-world dataset of COVID-19 patients published in a previous work. Also, performance of the BRBaDE has been compared with BRBES optimized with genetic algorithm and MATLAB’s fmincon function where BRBaDE outperformed genetic algorithm and fmincon and showed best accuracy of 73.91%. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.