Heg.IA: An intelligent system to support diagnosis of Covid-19 based on blood tests

Abstract

A new kind of coronavirus, the SARS-Cov2, started the biggest pandemic of the century. It has already killed more than 250,000 people. Because of this, it is necessary quick and precise diagnosis test. The current gold standard is the RT-PCR with DNA sequencing and identification, but its results takes too long to be available. Tests base on IgM/IgG antibodies have been used, but their sensitivity and specificity may be very low. Many studies have been demonstrating the Covid-19 impact in hematological parameters. This work proposes an intelligent system to support Covid-19 diagnosis based on blood testing. We tested several machine learning methods, and we achieved high classification performance: 95.159% ± 0.693 of overall accuracy, kappa index of 0.903 ± 0.014, sensitivity of 0.968 ± 0.007, precision of 0.938 ± 0.010 and specificity of 0.936 ± 0.011. These results were achieved using classical and low computational cost classifiers, with Bayes Network being the best of them. In addition, only 24 blood tests were needed. This points to the possibility of a new rapid test with low cost. The desktop version of the system is fully functional and available for free use. *

Applications of artificial intelligence in battling against covid-19: A literature review

“…In [79] , a machine learning algorithm to perform test based on blood tests is proposed. A Naive-Bayes model is used in [80] to build a model of hemogram data taken from symptomatic patients in order to predict qRT-PCR test resutls.…”

Optimizing the molecular diagnosis of Covid-19 by combining RT-PCR and a pseudo-convolutional machine learning approach to characterize virus DNA sequences

“…For the last metric, the authors believe that severe cases, however negative for Covid-19, generated more confusion in the classification. Another study Barbosa et al (2020), using the same initial database, applied attribute extraction methods (Particle Swarm Optimization) to search for the best tests among the 108 initial ones. Then, the authors manually selected exams in order to reduce costs.…”

Covid-19 rapid test by combining a random forest based web system and blood tests

“…In our previous work (Barbosa et al, 2020a) we proposed an intelligent system to aid Covid-19 diagnosis using blood exams. After testing several machine learning methods, we achieved high classification performance using Bayes network as classifier.…”

“…Similarly, the study by Soares et al (2020) uses a method based on artificial intelligence to identify Covid-19 through blood tests. As in our previous work (Barbosa et al, 2020a), they used the database from the Hospital Israelita In this sense, many other studies are also being conducted in order to optimize Covid-19 diagnosis using these other testing methods. Gomes et al (2020c) proposed a new technique for representing DNA sequences to optimize the molecular diagnosis of Covid-19.…”