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

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.

[1]  Riccardo Poli,et al.  Particle swarm optimization , 1995, Swarm Intelligence.

[2]  Bernhard E. Boser,et al.  A training algorithm for optimal margin classifiers , 1992, COLT '92.

[3]  Martin Styner,et al.  Objective Evaluation of Multiple Sclerosis Lesion Segmentation using a Data Management and Processing Infrastructure , 2018, bioRxiv.

[4]  Nigel M Hooper,et al.  ACE2: from vasopeptidase to SARS virus receptor , 2004, Trends in Pharmacological Sciences.

[5]  Abel G. Silva-Filho,et al.  A semi-supervised fuzzy GrowCut algorithm to segment and classify regions of interest of mammographic images , 2016, Expert Syst. Appl..

[6]  Rita de Cássia Fernandes de Lima,et al.  Deep-wavelet neural networks for breast cancer early diagnosis using mammary termographies , 2020 .

[7]  Y. Xiong,et al.  Clinical features and treatment of COVID‐19 patients in northeast Chongqing , 2020, Journal of medical virology.

[8]  Tara C Smith,et al.  Report from the American Society for Microbiology COVID-19 International Summit, 23 March 2020: Value of Diagnostic Testing for SARS–CoV-2/COVID-19 , 2020, mBio.

[9]  Å. Lundkvist,et al.  Evaluation of a COVID-19 IgM and IgG rapid test; an efficient tool for assessment of past exposure to SARS-CoV-2 , 2020, Infection ecology & epidemiology.

[10]  Abel G. Silva-Filho,et al.  A methodology for classification of lesions in mammographies using Zernike Moments, ELM and SVM Neural Networks in a multi-kernel approach , 2014, 2014 IEEE International Conference on Systems, Man, and Cybernetics (SMC).

[11]  Lijuan Xiong,et al.  Longitudinal characteristics of lymphocyte responses and cytokine profiles in the peripheral blood of SARS-CoV-2 infected patients , 2020, EBioMedicine.

[12]  Y. Yazdanpanah,et al.  SARS-CoV-2 specific antibody responses in COVID-19 patients , 2020, medRxiv.

[13]  Matjaž Kukar,et al.  Application of machine learning for hematological diagnosis , 2017 .

[14]  Mario Plebani,et al.  Laboratory abnormalities in patients with COVID-2019 infection , 2020, Clinical chemistry and laboratory medicine.

[15]  Edmund E Wilkes,et al.  Using machine learning to predict laboratory test results , 2016, Annals of clinical biochemistry.

[16]  D. Wang,et al.  The origin, transmission and clinical therapies on coronavirus disease 2019 (COVID-19) outbreak – an update on the status , 2020, Military Medical Research.

[17]  Mingxia Zhang,et al.  Evaluations of serological test in the diagnosis of 2019 novel coronavirus (SARS-CoV-2) infections during the COVID-19 outbreak , 2020, medRxiv.

[18]  Pierre Geurts,et al.  Extremely randomized trees , 2006, Machine Learning.

[19]  Xiang Xie,et al.  COVID-19 and the cardiovascular system , 2020, Nature Reviews Cardiology.

[20]  Dengju Li,et al.  Abnormal coagulation parameters are associated with poor prognosis in patients with novel coronavirus pneumonia , 2020, Journal of Thrombosis and Haemostasis.

[21]  Hugo Guterman,et al.  Feature selection and chromosome classification using a multilayer perceptron neural network , 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).

[22]  F ROSENBLATT,et al.  The perceptron: a probabilistic model for information storage and organization in the brain. , 1958, Psychological review.

[23]  Qi Jin,et al.  Profiling Early Humoral Response to Diagnose Novel Coronavirus Disease (COVID-19) , 2020, Clinical infectious diseases : an official publication of the Infectious Diseases Society of America.

[24]  Abdesselam Bouzerdoum,et al.  Skin segmentation using color pixel classification: analysis and comparison , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[25]  Xiuyong Li,et al.  Diagnostic utility of clinical laboratory data determinations for patients with the severe COVID‐19 , 2020, Journal of medical virology.

[26]  N. Beeching,et al.  Covid-19: testing times , 2020, BMJ.

[27]  Matjaž Kukar,et al.  An application of machine learning to haematological diagnosis , 2017, Scientific Reports.

[28]  C. Boesecke,et al.  Rapid point-of-care testing for SARS-CoV-2 in a community screening setting shows low sensitivity , 2020, Public Health.

[29]  Wellington Pinheiro dos Santos,et al.  Detection and classification of masses in mammographic images in a multi-kernel approach , 2016, Comput. Methods Programs Biomed..

[30]  Mark J. Schreiber,et al.  Decision Tree Algorithms Predict the Diagnosis and Outcome of Dengue Fever in the Early Phase of Illness , 2008, PLoS neglected tropical diseases.

[31]  Filippo Menczer,et al.  Feature selection in unsupervised learning via evolutionary search , 2000, KDD '00.

[32]  Rita de Cássia Fernandes de Lima,et al.  Breast cancer diagnosis based on mammary thermography and extreme learning machines , 2018 .

[33]  Rita de Cássia Fernandes de Lima,et al.  Identification of mammary lesions in thermographic images: feature selection study using genetic algorithms and particle swarm optimization , 2019, Research on Biomedical Engineering.

[34]  Jonathan E. Schmitz,et al.  Laboratory Diagnosis of COVID-19: Current Issues and Challenges , 2020, Journal of Clinical Microbiology.

[35]  Feifei Ren,et al.  Diagnostic Indexes of a Rapid IgG/IgM Combined Antibody Test for SARS-CoV-2 , 2020, medRxiv.

[36]  J. H. de Vasconcelos,et al.  Analysis of Methods of Classification of Breast Thermographic Images to Determine their Viability in the Early Breast Cancer Detection , 2018 .

[37]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[38]  X. Yao.  Evolutionary Search of Approximated N-dimensional Landscapes , 2000 .

[39]  Abel Silva-Filho,et al.  Feature extraction employing fuzzy-morphological decomposition for detection and classification of mass on mammograms. , 2015, Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference.

[40]  Sidney M. L. Lima,et al.  Morphological extreme learning machines applied to the detection and classification of mammary lesions , 2021 .

[41]  Y. Hu,et al.  Clinical features of patients infected with 2019 novel coronavirus in Wuhan, China , 2020, The Lancet.

[42]  Rok Blagus,et al.  SMOTE for high-dimensional class-imbalanced data , 2013, BMC Bioinformatics.

[43]  G. B. Tan,et al.  Hematologic parameters in patients with COVID‐19 infection , 2020, American journal of hematology.

[44]  Xiangyang Wang,et al.  Feature selection based on rough sets and particle swarm optimization , 2007, Pattern Recognit. Lett..

[45]  Russell Greiner,et al.  Learning Bayesian Belief Network Classifiers: Algorithms and System , 2001, Canadian Conference on AI.

[46]  Chao Zhang,et al.  Liver injury in COVID-19: management and challenges , 2020, The Lancet Gastroenterology & Hepatology.

[47]  L Rampal,et al.  Coronavirus disease (COVID-19) pandemic. , 2020, The Medical journal of Malaysia.

[48]  F. R. Cordeiro,et al.  Analysis of supervised and semi-supervised GrowCut applied to segmentation of masses in mammography images , 2017, Comput. methods Biomech. Biomed. Eng. Imaging Vis..

[49]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.