{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,3]],"date-time":"2026-10-03T03:25:20Z","timestamp":1790997920017,"version":"4.1.0"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,5,24]],"date-time":"2021-05-24T00:00:00Z","timestamp":1621814400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,5,24]],"date-time":"2021-05-24T00:00:00Z","timestamp":1621814400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Smart Blood Analytics Swiss SA"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Physicians taking care of patients with COVID-19 have described different changes in routine blood parameters. However, these changes hinder them from performing COVID-19 diagnoses. We constructed a machine learning model for COVID-19 diagnosis that was based and cross-validated on the routine blood tests of 5333 patients with various bacterial and viral infections, and 160 COVID-19-positive patients. We selected the operational ROC point at a sensitivity of 81.9% and a specificity of 97.9%. The cross-validated AUC was 0.97. The five most useful routine blood parameters for COVID-19 diagnosis according to the feature importance scoring of the XGBoost algorithm were: MCHC, eosinophil count, albumin, INR, and prothrombin activity percentage. t-SNE visualization showed that the blood parameters of the patients with a severe COVID-19 course are more like the parameters of a bacterial than a viral infection. The reported diagnostic accuracy is at least comparable and probably complementary to RT-PCR and chest CT studies. Patients with fever, cough, myalgia, and other symptoms can now have initial routine blood tests assessed by our diagnostic tool. All patients with a positive COVID-19 prediction would then undergo standard RT-PCR studies to confirm the diagnosis. We believe that our results represent a significant contribution to improvements in COVID-19 diagnosis.<\/jats:p>","DOI":"10.1038\/s41598-021-90265-9","type":"journal-article","created":{"date-parts":[[2021,5,24]],"date-time":"2021-05-24T10:02:53Z","timestamp":1621850573000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":150,"title":["COVID-19 diagnosis by routine blood tests using machine learning"],"prefix":"10.1038","volume":"11","author":[{"given":"Matja\u017e","family":"Kukar","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gregor","family":"Gun\u010dar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Toma\u017e","family":"Vovko","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Simon","family":"Podnar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter","family":"\u010cernel\u010d","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Miran","family":"Brvar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mateja","family":"Zalaznik","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mateja","family":"Notar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sa\u0161o","family":"Mo\u0161kon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marko","family":"Notar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,5,24]]},"reference":[{"key":"90265_CR1","doi-asserted-by":"publisher","first-page":"727","DOI":"10.1056\/NEJMoa2001017","volume":"382","author":"N Zhu","year":"2020","unstructured":"Zhu, N. et al. A novel coronavirus from patients with pneumonia in China, 2019. N. Engl. J. Med. 382, 727\u2013733 (2020).","journal-title":"N. Engl. J. Med."},{"key":"90265_CR2","doi-asserted-by":"publisher","first-page":"536","DOI":"10.1038\/s41564-020-0695-z","volume":"5","author":"A Gorbalenya","year":"2020","unstructured":"Gorbalenya, A. et al. The species severe acute respiratory syndrome related coronavirus: Classifying 2019-nCoV and naming it SARS-CoV-2. Nat. Microbiol. 5, 536\u2013544 (2020).","journal-title":"Nat. Microbiol."},{"key":"90265_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3201\/eid2607.200282","volume":"26","author":"S Sanche","year":"2020","unstructured":"Sanche, S. et al. High contagiousness and rapid spread of severe acute respiratory syndrome coronavirus 2. Emerg. Infect. Dis. 26, 1 (2020).","journal-title":"Emerg. Infect. Dis."},{"key":"90265_CR4","unstructured":"World health organization. WHO Director-General\u2019s remarks at the media briefing on 2019-nCoV on 11 February 2020. https:\/\/www.who.int\/dg\/speeches\/detail\/who-director-general-s-remarks-at-the-media-briefing-on-2019-ncov-on-11-february-2020 (2020)."},{"key":"90265_CR5","first-page":"1","volume":"1","author":"WJ Guan","year":"2020","unstructured":"Guan, W. J. et al. Clinical characteristics of coronavirus disease 2019 in China. N. Engl. J. Med. 1, 1 (2020).","journal-title":"N. Engl. J. Med."},{"key":"90265_CR6","doi-asserted-by":"publisher","first-page":"497","DOI":"10.1016\/S0140-6736(20)30183-5","volume":"395","author":"C Huang","year":"2020","unstructured":"Huang, C. et al. Clinical features of patients infected with 2019 novel coronavirus in Wuhan, China. Lancet 395, 497\u2013506 (2020).","journal-title":"Lancet"},{"key":"90265_CR7","first-page":"1","volume":"1","author":"JA Lewnard","year":"2020","unstructured":"Lewnard, J. A. & Lo, N. C. Scientific and ethical basis for social-distancing interventions against COVID-19. Lancet Infect. Dis. 1, 1 (2020).","journal-title":"Lancet Infect. Dis."},{"key":"90265_CR8","first-page":"1","volume":"1","author":"JR Koo","year":"2020","unstructured":"Koo, J. R. et al. Interventions to mitigate early spread of SARS-CoV-2 in Singapore: a modelling study. Lancet Infect. Dis. 1, 1 (2020).","journal-title":"Lancet Infect. Dis."},{"key":"90265_CR9","doi-asserted-by":"crossref","first-page":"20225","DOI":"10.4414\/smw.2020.20457","volume":"150","author":"M Salathe","year":"2020","unstructured":"Salathe, M. et al. COVID-19 epidemic in Switzerland: on the importance of testing, contact tracing and isolation. Swiss. Med. Wkly 150, 20225 (2020).","journal-title":"Swiss. Med. Wkly"},{"key":"90265_CR10","doi-asserted-by":"publisher","first-page":"747","DOI":"10.1080\/22221751.2020.1745095","volume":"9","author":"MJ Loeffelholz","year":"2020","unstructured":"Loeffelholz, M. J. & Tang, Y. W. Laboratory diagnosis of emerging human coronavirus infections: The state of the art. Emerg. Microbes Infect. 9, 747\u2013756 (2020).","journal-title":"Emerg. Microbes Infect."},{"key":"90265_CR11","first-page":"1","volume":"25","author":"VM Corman","year":"2020","unstructured":"Corman, V. M. et al. Detection of 2019 novel coronavirus (2019-nCoV) by real-time RT-PCR. Euro Surveill. 25, 1 (2020).","journal-title":"Euro Surveill."},{"issue":"4","key":"90265_CR12","doi-asserted-by":"publisher","first-page":"505","DOI":"10.3348\/kjr.2020.0146","volume":"21","author":"D Li","year":"2020","unstructured":"Li, D. & Wang, D. False-negative results of real-time reverse-transcriptase polymerase chain reaction for severe acute respiratory syndrome coronavirus 2: role of deep-learning-based CT diagnosis and insights from two cases. Korean J. Radiol. 21(4), 505\u2013508 (2020).","journal-title":"Korean J. Radiol."},{"issue":"2","key":"90265_CR13","doi-asserted-by":"publisher","first-page":"E32","DOI":"10.1148\/radiol.2020200642","volume":"296","author":"T Ai","year":"2020","unstructured":"Ai, T. et al. Correlation of chest CT and RT-PCR testing in coronavirus disease 2019 (COVID-19) in China: a report of 1014 cases. Radiology 296(2), E32-E40 (2020).","journal-title":"Radiology"},{"key":"90265_CR14","doi-asserted-by":"crossref","unstructured":"Yang, Y. et al. Evaluating the accuracy of different respiratory specimens in the laboratory diagnosis and monitoring the viral shedding of 2019-nCoV infections. MedRxiv (2020).","DOI":"10.1101\/2020.02.11.20021493"},{"key":"90265_CR15","first-page":"1","volume":"1","author":"G Lippi","year":"2020","unstructured":"Lippi, G., Simundic, A. M. & Plebani, M. Potential preanalytical and analytical vulnerabilities in the laboratory diagnosis of coronavirus disease 2019 (COVID-19). Clin. Chem. Lab. Med. 1, 1 (2020).","journal-title":"Clin. Chem. Lab. Med."},{"key":"90265_CR16","first-page":"1","volume":"1","author":"MD Hope","year":"2020","unstructured":"Hope, M. D., Raptis, C. A., Shah, A., Hammer, M. M. & Henry, T. S. A role for CT in COVID-19? What data really tell us so far. Lancet 1, 1 (2020).","journal-title":"Lancet"},{"key":"90265_CR17","doi-asserted-by":"publisher","first-page":"101623","DOI":"10.1016\/j.tmaid.2020.101623","volume":"1","author":"AJ Rodriguez-Morales","year":"2020","unstructured":"Rodriguez-Morales, A. J. et al. Clinical, laboratory and imaging features of COVID-19: A systematic review and meta-analysis. Travel. Med. Infect. Dis. 1, 101623 (2020).","journal-title":"Travel. Med. Infect. Dis."},{"key":"90265_CR18","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1038\/s41598-017-18564-8","volume":"8","author":"G Guncar","year":"2018","unstructured":"Guncar, G. et al. An application of machine learning to haematological diagnosis. Sci. Rep. 8, 411 (2018).","journal-title":"Sci. Rep."},{"key":"90265_CR19","doi-asserted-by":"publisher","first-page":"14481","DOI":"10.1038\/s41598-019-51147-3","volume":"9","author":"S Podnar","year":"2019","unstructured":"Podnar, S. et al. Diagnosing brain tumours by routine blood tests using machine learning. Sci. Rep. 9, 14481 (2019).","journal-title":"Sci. Rep."},{"key":"90265_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1373\/49.1.1","volume":"49","author":"PM Bossuyt","year":"2003","unstructured":"Bossuyt, P. M. et al. Towards complete and accurate reporting of studies of diagnostic accuracy: the STARD initiative. Standards for Reporting of Diagnostic Accuracy. Clin. Chem. 49, 1\u20136 (2003).","journal-title":"Clin. Chem."},{"key":"90265_CR21","first-page":"918","volume":"82","author":"FW Scholz","year":"1987","unstructured":"Scholz, F. W. & M.A. S, ,. K-sample Anderson-darling tests. J. Am. Stat. Assoc. 82, 918\u2013924 (1987).","journal-title":"J. Am. Stat. Assoc."},{"key":"90265_CR22","first-page":"2579","volume":"9","author":"M Lvd","year":"2008","unstructured":"Lvd, M. & Hinton, G. Visualizing data using t-SNE. J. Mach. Learn. Res. 9, 2579\u20132605 (2008).","journal-title":"J. Mach. Learn. Res."},{"key":"90265_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41467-019-13056-x","volume":"10","author":"D Kobak","year":"2019","unstructured":"Kobak, D. & Berens, P. The art of using t-SNE for single-cell transcriptomics. Nat. Commun. 10, 1\u201314 (2019).","journal-title":"Nat. Commun."},{"key":"90265_CR24","doi-asserted-by":"publisher","unstructured":"Wattenberg, M., Vi\u00e9gas, F. & Johnson, I. How to use t-sne effectively. Distill. https:\/\/doi.org\/10.23915\/distill.00002 (2016).","DOI":"10.23915\/distill.00002"},{"key":"90265_CR25","doi-asserted-by":"crossref","unstructured":"Policar, P. G., Strazar, M., Zupan, B. openTSNE: a modular Python library for t-SNE dimensionality reduction and embedding. BioRxiv 731877 (2019).","DOI":"10.1101\/731877"},{"key":"90265_CR26","first-page":"3221","volume":"15","author":"L Van Der Maaten","year":"2014","unstructured":"Van Der Maaten, L. Accelerating t-SNE using tree-based algorithms. J. Mach. Learn. Res. 15, 3221\u20133245 (2014).","journal-title":"J. Mach. Learn. Res."},{"key":"90265_CR27","unstructured":"Smart Vision Europe CRISP-DM, Cross-industry standard process for data mining. https:\/\/www.sv-europe.com\/crisp-dm-methodology (2015)."},{"key":"90265_CR28","unstructured":"Smart Blood Analytics. Available from: https:\/\/www.smartbloodanalytics.com\/ (2020)"},{"key":"90265_CR29","doi-asserted-by":"publisher","first-page":"785","DOI":"10.1145\/2939672.2939785","volume-title":"The 22nd ACM SIGKDD international conference on knowledge discovery and data mining, KDD \u201916","author":"T Chen","year":"2016","unstructured":"Chen, T. & Guestrin, C. XGBoost: A scalable tree boosting system. In The 22nd ACM SIGKDD international conference on knowledge discovery and data mining, KDD \u201916 (eds Krishnapuram, B. et al.) 785\u2013794 (ACM, 2016)."},{"key":"90265_CR30","doi-asserted-by":"publisher","first-page":"1189","DOI":"10.1214\/aos\/1013203451","volume":"29","author":"JH Friedman","year":"2001","unstructured":"Friedman, J. H. Greedy function approximation: A gradient boosting machine. Ann. Stat. 29, 1189\u20131232 (2001).","journal-title":"Ann. Stat."},{"key":"90265_CR31","doi-asserted-by":"publisher","first-page":"367","DOI":"10.1016\/S0167-9473(01)00065-2","volume":"38","author":"JH Friedman","year":"2002","unstructured":"Friedman, J. H. Stochastic gradient boosting. Comput. Stat. Data Anal. 38, 367\u2013378 (2002).","journal-title":"Comput. Stat. Data Anal."},{"key":"90265_CR32","volume-title":"Tree boosting with XGBoost \u2013 why does XGBoost win \u201cevery\u201d machine learning competition? [Master\u2019s thesis]","author":"D Nielsen","year":"2016","unstructured":"Nielsen, D. Tree boosting with XGBoost \u2013 why does XGBoost win \u201cevery\u201d machine learning competition? [Master\u2019s thesis] (Norwegian University of Science and Technology, 2016)."},{"key":"90265_CR33","first-page":"930","volume":"264","author":"S Chen","year":"2019","unstructured":"Chen, S. et al. A Regularization-based extreme gradient boosting approach in foodborne disease trend forecasting. Stud. Health Technol. Inform. 264, 930\u2013934 (2019).","journal-title":"Stud. Health Technol. Inform."},{"key":"90265_CR34","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1613\/jair.953","volume":"16","author":"NV Chawla","year":"2002","unstructured":"Chawla, N. V., Bowyer, K. W., Hall, L. O. & Kegelmeyer, W. P. SMOTE: synthetic minority over-sampling technique. J Artif Intell Res 16, 341\u2013378 (2002).","journal-title":"J Artif Intell Res"},{"key":"90265_CR35","doi-asserted-by":"publisher","first-page":"380","DOI":"10.1016\/j.asoc.2018.12.024","volume":"76","author":"S Maldonado","year":"2019","unstructured":"Maldonado, S., L\u00f3pez, J. & Vairetti, C. An alternative SMOTE oversampling strategy for high-dimensional datasets. Appl. Soft Comput. 76, 380\u2013389 (2019).","journal-title":"Appl. Soft Comput."},{"key":"90265_CR36","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1186\/1471-2105-14-106","volume":"14","author":"R Blagus","year":"2013","unstructured":"Blagus, R. & Lusa, L. SMOTE for high-dimensional class-imbalanced data. BMC Bioinformatics 14, 106 (2013).","journal-title":"BMC Bioinformatics"},{"key":"90265_CR37","doi-asserted-by":"crossref","unstructured":"Davis, J., & Goadrich, M. The relationship between Precision-Recall and ROC curves. in Proceedings of the 23rd international conference on Machine learning (2006).","DOI":"10.1145\/1143844.1143874"},{"key":"90265_CR38","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1214\/ss\/1009213286","volume":"16","author":"L Brown","year":"2001","unstructured":"Brown, L., Cai, T. & DasGupta, A. Interval estimation for a binomial proportion. Stat. Sci. 16, 101\u2013117 (2001).","journal-title":"Stat. Sci."},{"key":"90265_CR39","first-page":"657","volume-title":"The 28th International Conference on Machine Learning, ICML\u201911","author":"P Flach","year":"2011","unstructured":"Flach, P., Hern\u00e1ndez-Orallo, J. & Ferri, C. A coherent interpretation of AUC as a measure of aggregated classification performance. In The 28th International Conference on Machine Learning, ICML\u201911 (eds Getoor, L. & Scheffer, T.) 657\u2013664 (Omnipress, 2011)."},{"key":"90265_CR40","doi-asserted-by":"crossref","unstructured":"Wu, J. et al. Rapid and accurate identification of COVID-19 infection through machine learning based on clinical available blood test results. MedRxiv (2020).","DOI":"10.1101\/2020.04.02.20051136"},{"key":"90265_CR41","unstructured":"Batista, A. F. M., Miraglia, J. L., Donato, T. H. R. & Chiavegatto Filho, A. D. P. COVID-19 diagnosis prediction in emergency care patients: A machine learning approach. medRxiv (2020)."},{"key":"90265_CR42","first-page":"1","volume":"1","author":"N Tang","year":"2020","unstructured":"Tang, N. et al. Anticoagulant treatment is associated with decreased mortality in severe coronavirus disease 2019 patients with coagulopathy. J. Thromb. Haemost. 1, 1 (2020).","journal-title":"J. Thromb. Haemost."},{"issue":"7","key":"90265_CR43","doi-asserted-by":"publisher","DOI":"10.15252\/emmm.202012560","volume":"12","author":"JA Bengoechea","year":"2020","unstructured":"Bengoechea, J. A., & Bamford, C. G. SARS-CoV-2, bacterial co-infections, and AMR: the deadly trio in COVID-19? EMBO Mol. Med. 12(7), e12560 (2020).","journal-title":"EMBO Mol. Med."},{"key":"90265_CR44","doi-asserted-by":"publisher","first-page":"1626","DOI":"10.3389\/fimmu.2020.01626","volume":"11","author":"RB Polidoro","year":"2020","unstructured":"Polidoro, R. B., Hagan, R. S., de Santis Santiago, R. & Schmidt, N. W. Overview: systemic inflammatory response derived from lung injury caused by SARS-CoV-2 infection explains severe outcomes in COVID-19. Front. Immunol. 11, 1626 (2020).","journal-title":"Front. Immunol."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-021-90265-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-021-90265-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-021-90265-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,28]],"date-time":"2022-12-28T10:16:10Z","timestamp":1672222570000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-021-90265-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,24]]},"references-count":44,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2021,12]]}},"alternative-id":["90265"],"URL":"https:\/\/doi.org\/10.1038\/s41598-021-90265-9","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,5,24]]},"assertion":[{"value":"10 July 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 May 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 May 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Marko Notar is the CEO of Smart Blood Analytics SA. Matja\u017e Kukar, Gregor Gun\u010dar, and Mateja Notar are Smart Blood Analytics advisors, and other authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"10738"}}