{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,25]],"date-time":"2025-12-25T07:21:00Z","timestamp":1766647260438,"version":"3.37.3"},"reference-count":98,"publisher":"Public Library of Science (PLoS)","issue":"4","license":[{"start":{"date-parts":[[2023,4,13]],"date-time":"2023-04-13T00:00:00Z","timestamp":1681344000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004837","name":"Ministerio de Ciencia e Innovaci\u00f3n","doi-asserted-by":"publisher","award":["BCAM Severo Ochoa accreditation CEX2021-001142-S \/ MICIN \/ AEI \/ 10.13039\/501100011033"],"award-info":[{"award-number":["BCAM Severo Ochoa accreditation CEX2021-001142-S \/ MICIN \/ AEI \/ 10.13039\/501100011033"]}],"id":[{"id":"10.13039\/501100004837","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011033","name":"Agencia Estatal de Investigaci\u00f3n","doi-asserted-by":"publisher","award":["S3M1P4R (PID2020-115882RB-I00)"],"award-info":[{"award-number":["S3M1P4R (PID2020-115882RB-I00)"]}],"id":[{"id":"10.13039\/501100011033","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003086","name":"Eusko Jaurlaritza","doi-asserted-by":"publisher","award":["Artificial Intelligence in BCAM 2019\/00432"],"award-info":[{"award-number":["Artificial Intelligence in BCAM 2019\/00432"]}],"id":[{"id":"10.13039\/501100003086","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003086","name":"Eusko Jaurlaritza","doi-asserted-by":"publisher","award":["Mathematical Modelling Applied to Health strategy"],"award-info":[{"award-number":["Mathematical Modelling Applied to Health strategy"]}],"id":[{"id":"10.13039\/501100003086","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003086","name":"Eusko Jaurlaritza","doi-asserted-by":"publisher","award":["BERC 2018\u20132021 programme"],"award-info":[{"award-number":["BERC 2018\u20132021 programme"]}],"id":[{"id":"10.13039\/501100003086","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003086","name":"Eusko Jaurlaritza","doi-asserted-by":"publisher","award":["BERC 2022\u20132025 programme"],"award-info":[{"award-number":["BERC 2022\u20132025 programme"]}],"id":[{"id":"10.13039\/501100003086","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:p>With the COVID-19 pandemic having caused unprecedented numbers of infections and deaths, large research efforts have been undertaken to increase our understanding of the disease and the factors which determine diverse clinical evolutions. Here we focused on a fully data-driven exploration regarding which factors (clinical or otherwise) were most informative for SARS-CoV-2 pneumonia severity prediction via machine learning (ML). In particular, feature selection techniques (FS), designed to reduce the dimensionality of data, allowed us to characterize which of our variables were the most useful for ML prognosis. We conducted a multi-centre clinical study, enrolling<jats:italic>n<\/jats:italic>= 1548 patients hospitalized due to SARS-CoV-2 pneumonia: where 792, 238, and 598 patients experienced low, medium and high-severity evolutions, respectively. Up to 106 patient-specific clinical variables were collected at admission, although 14 of them had to be discarded for containing \u2a7e60% missing values. Alongside 7 socioeconomic attributes and 32 exposures to air pollution (chronic and acute), these became<jats:italic>d<\/jats:italic>= 148 features after variable encoding. We addressed this ordinal classification problem both as a ML classification and regression task. Two imputation techniques for missing data were explored, along with a total of 166 unique FS algorithm configurations: 46 filters, 100 wrappers and 20 embeddeds. Of these, 21 setups achieved satisfactory bootstrap stability (\u2a7e0.70) with reasonable computation times: 16 filters, 2 wrappers, and 3 embeddeds. The subsets of features selected by each technique showed modest Jaccard similarities across them. However, they consistently pointed out the importance of certain explanatory variables. Namely: patient\u2019s C-reactive protein (CRP), pneumonia severity index (PSI), respiratory rate (RR) and oxygen levels \u2013saturation Sp O2, quotients Sp O2\/RR and arterial Sat O2\/Fi O2\u2013, the neutrophil-to-lymphocyte ratio (NLR) \u2013to certain extent, also neutrophil and lymphocyte counts separately\u2013, lactate dehydrogenase (LDH), and procalcitonin (PCT) levels in blood. A remarkable agreement has been found<jats:italic>a posteriori<\/jats:italic>between our strategy and independent clinical research works investigating risk factors for COVID-19 severity. Hence, these findings stress the suitability of this type of fully data-driven approaches for knowledge extraction, as a complementary to clinical perspectives.<\/jats:p>","DOI":"10.1371\/journal.pone.0284150","type":"journal-article","created":{"date-parts":[[2023,4,13]],"date-time":"2023-04-13T17:29:01Z","timestamp":1681406941000},"page":"e0284150","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":9,"title":["Extracting relevant predictive variables for COVID-19 severity prognosis: An exhaustive comparison of feature selection techniques"],"prefix":"10.1371","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6382-9743","authenticated-orcid":true,"given":"Miren","family":"Hayet-Otero","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6605-9038","authenticated-orcid":true,"given":"Fernando","family":"Garc\u00eda-Garc\u00eda","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8995-8535","authenticated-orcid":true,"given":"Dae-Jin","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1016-8734","authenticated-orcid":true,"given":"Joaqu\u00edn","family":"Mart\u00ednez-Minaya","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pedro Pablo","family":"Espa\u00f1a Yandiola","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Isabel","family":"Urrutia Landa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"M\u00f3nica","family":"Nieves Ermecheo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jos\u00e9 Mar\u00eda","family":"Quintana","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rosario","family":"Men\u00e9ndez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Antoni","family":"Torres","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rafael","family":"Zalacain Jorge","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Inmaculada","family":"Arostegui","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"name":"with the COVID-19 & Air Pollution Working Group","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2023,4,13]]},"reference":[{"key":"pone.0284150.ref001","article-title":"Prediction models for diagnosis and prognosis of COVID-19: Systematic review and critical appraisal","volume":"369","author":"L Wynants","year":"2020","journal-title":"BMJ"},{"key":"pone.0284150.ref002","doi-asserted-by":"crossref","DOI":"10.1016\/j.imu.2021.100564","article-title":"Machine learning approaches in COVID-19 diagnosis, mortality, and severity risk prediction: a review","volume":"24","author":"N Alballa","year":"2021","journal-title":"Informatics in Medicine Unlocked"},{"issue":"10","key":"pone.0284150.ref003","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pdig.0000132","article-title":"Artificial intelligence applications used in the clinical response to COVID-19: A scoping review","volume":"1","author":"S Mann","year":"2022","journal-title":"PLOS Digital Health"},{"issue":"5","key":"pone.0284150.ref004","doi-asserted-by":"crossref","first-page":"1548","DOI":"10.3390\/jcm9051548","article-title":"Early predictors of clinical deterioration in a cohort of 239 patients hospitalized for COVID-19 infection in Lombardy, Italy","volume":"9","author":"M Cecconi","year":"2020","journal-title":"J Clin Med"},{"issue":"15","key":"pone.0284150.ref005","doi-asserted-by":"crossref","first-page":"833","DOI":"10.1093\/cid\/ciaa443","article-title":"A tool for early prediction of severe coronavirus disease 2019 (COVID-19): A multicenter study using the risk nomogram in Wuhan and Guangdong, China","volume":"71","author":"J Gong","year":"2020","journal-title":"Clin Infect Dis"},{"issue":"1","key":"pone.0284150.ref006","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-021-83967-7","article-title":"Machine learning based predictors for COVID-19 disease severity","volume":"11","author":"D Patel","year":"2021","journal-title":"Sci Rep"},{"issue":"1","key":"pone.0284150.ref007","doi-asserted-by":"crossref","DOI":"10.1016\/j.retram.2021.103319","article-title":"Clinical prognosis evaluation of COVID-19 patients: An interpretable hybrid machine learning approach","volume":"70","author":"O Kocadagli","year":"2022","journal-title":"Current Research in Translational Medicine"},{"key":"pone.0284150.ref008","doi-asserted-by":"crossref","DOI":"10.1016\/j.imu.2021.100825","article-title":"A new COVID-19 intubation prediction strategy using an intelligent feature selection and K-NN method","volume":"28","author":"ZA Varzaneh","year":"2022","journal-title":"Informatics in Medicine Unlocked"},{"issue":"3","key":"pone.0284150.ref009","doi-asserted-by":"crossref","first-page":"282","DOI":"10.1093\/ajh\/hpaa225","article-title":"High systolic blood pressure at hospital admission is an important risk factor in models predicting outcome of COVID-19 patients","volume":"34","author":"A Caillon","year":"2021","journal-title":"Am J Hypertens"},{"key":"pone.0284150.ref010","doi-asserted-by":"crossref","DOI":"10.3389\/fpubh.2021.626697","article-title":"Machine learning based clinical decision support system for early COVID-19 mortality prediction","volume":"9","author":"A Karthikeyan","year":"2021","journal-title":"Front Public Health"},{"issue":"9","key":"pone.0284150.ref011","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1371\/journal.pone.0274171","article-title":"Machine-learning-derived predictive score for early estimation of COVID-19 mortality risk in hospitalized patients","volume":"17","author":"A Gonz\u00e1lez-Cebri\u00e1n","year":"2022","journal-title":"PLoS One"},{"key":"pone.0284150.ref012","unstructured":"Kalousis A, Prados J, Hilario M. Stability of feature selection algorithms. In: Proc IEEE Int Conf Data Mining; 2005. p. 8\u201315."},{"issue":"4","key":"pone.0284150.ref013","doi-asserted-by":"crossref","first-page":"1060","DOI":"10.1016\/j.jksuci.2019.06.012","article-title":"Stability of feature selection algorithm: A review","volume":"34","author":"UM Khaire","year":"2022","journal-title":"Journal of King Saud University\u2014Computer and Information Sciences"},{"issue":"1","key":"pone.0284150.ref014","first-page":"1","article-title":"On the stability of feature selection algorithms","volume":"18","author":"S Nogueira","year":"2018","journal-title":"Journal of Machine Learning Research"},{"issue":"9","key":"pone.0284150.ref015","doi-asserted-by":"crossref","first-page":"4434","DOI":"10.1016\/j.eswa.2014.01.011","article-title":"Knowledge discovery in medicine: Current issue and future trend","volume":"41","author":"N Esfandiari","year":"2014","journal-title":"Expert Syst Appl"},{"issue":"1","key":"pone.0284150.ref016","doi-asserted-by":"crossref","first-page":"159","DOI":"10.3233\/IDA-173763","article-title":"A review of feature selection techniques in sentiment analysis","volume":"23","author":"SR Ahmad","year":"2019","journal-title":"Intelligent Data Analysis"},{"key":"pone.0284150.ref017","doi-asserted-by":"crossref","DOI":"10.1016\/j.apenergy.2020.115835","article-title":"The relationship between air pollution and COVID-19-related deaths: An application to three French cities","volume":"279","author":"C Magazzino","year":"2020","journal-title":"Appl Energy"},{"key":"pone.0284150.ref018","article-title":"The effects of air pollution on COVID-19 infection and mortality\u2014A review on recent evidence","volume":"8","author":"N Ali","year":"2020","journal-title":"Front Public Health"},{"issue":"2","key":"pone.0284150.ref019","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1016\/j.jinf.2020.05.031","article-title":"Severe air pollution links to higher mortality in COVID-19 patients: The \u2018double-hit\u2019 hypothesis","volume":"81","author":"A Frontera","year":"2020","journal-title":"J Infect"},{"key":"pone.0284150.ref020","doi-asserted-by":"crossref","first-page":"139853","DOI":"10.1016\/j.scitotenv.2020.139853","article-title":"Comment to the paper \u2018Assessing nitrogen dioxide (NO2) levels as a contributing factor to coronavirus (COVID-19) fatality\u2019, by Ogen, 2020","volume":"738","author":"E Pisoni","year":"2020","journal-title":"Sci Total Environ"},{"key":"pone.0284150.ref021","doi-asserted-by":"crossref","DOI":"10.1016\/j.envres.2021.111930","article-title":"Positive association between outdoor air pollution and the incidence and severity of COVID-19. A review of the recent scientific evidences","volume":"203","author":"M Marqu\u00e8s","year":"2022","journal-title":"Environ Res"},{"key":"pone.0284150.ref022","article-title":"The impact of air pollution on COVID-19 incidence, severity, and mortality: A systematic review of studies in Europe and North America","author":"IH Carballo","year":"2022","journal-title":"Environ Res"},{"issue":"1","key":"pone.0284150.ref023","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-022-17215-x","article-title":"Assessing the impact of long-term exposure to nine outdoor air pollutants on COVID-19 spatial spread and related mortality in 107 Italian provinces","volume":"12","author":"G Perone","year":"2022","journal-title":"Sci Rep"},{"issue":"1","key":"pone.0284150.ref024","doi-asserted-by":"crossref","DOI":"10.1136\/bmjopen-2020-044640","article-title":"Demographic risk factors for COVID-19 infection, severity, ICU admission and death: A meta-analysis of 59 studies","volume":"11","author":"BG Pijls","year":"2021","journal-title":"BMJ Open"},{"key":"pone.0284150.ref025","article-title":"Socioeconomic inequalities and COVID-19\u2014A review of the current international literature","author":"B Wachtler","year":"2020","journal-title":"J Health Monit"},{"issue":"2","key":"pone.0284150.ref026","first-page":"131","article-title":"COVID-19 mortality in English neighborhoods: The relative role of socioeconomic and environmental factors","volume":"4","author":"P Congdon","year":"2021","journal-title":"J"},{"issue":"3","key":"pone.0284150.ref027","doi-asserted-by":"crossref","DOI":"10.3390\/ijerph18031256","article-title":"Socioeconomic inequalities in COVID-19 in a European urban area: Two waves, two patterns","volume":"18","author":"M Mar\u00ed-Dell\u2019Olmo","year":"2021","journal-title":"Int J Environ Res Public Health"},{"issue":"3","key":"pone.0284150.ref028","article-title":"Socio-economic disparities and COVID-19 in the USA","volume":"2","author":"A Paul","year":"2021","journal-title":"Journal of Physics: Complexity"},{"issue":"11","key":"pone.0284150.ref029","doi-asserted-by":"crossref","first-page":"2243","DOI":"10.3201\/eid2811.220614","article-title":"Socioeconomic inequalities in COVID-19 vaccination and infection in adults, Catalonia, Spain","volume":"28","author":"E Roel","year":"2022","journal-title":"Emerg Infect Dis"},{"key":"pone.0284150.ref030","unstructured":"Garc\u00eda-Garc\u00eda F, Lee DJ, Espa\u00f1a Yandiola P, Urrutia Landa I, Mart\u00ednez-Minaya J, Hayet-Otero M, et al. Predicting SARS-CoV-2 pneumonia severity by cost-sensitive, ordinal classification methods. Manuscript submitted for publication. 2022;."},{"key":"pone.0284150.ref031","unstructured":"National Statistics Institute. Household income distribution atlas; 2019. Available from: https:\/\/www.ine.es\/dynt3\/inebase\/en\/index.htm?padre=7132."},{"key":"pone.0284150.ref032","unstructured":"Basque Network for the Surveillance of Air Quality. Air quality measurements in the Basque Country; 2020. Available from: https:\/\/www.opendata.euskadi.eus\/catalogo\/-\/calidad-aire-en-euskadi-2020."},{"key":"pone.0284150.ref033","unstructured":"Catalan Network for the Monitoring and Prediction of Air Pollution. Air quality measurements in Catalonia; 2020. Available from: https:\/\/analisi.transparenciacatalunya.cat\/es\/Medi-Ambient\/Qualitat-de-l-aire-als-punts-de-mesurament-autom%C3%A0t\/tasf-thgu."},{"key":"pone.0284150.ref034","unstructured":"Valencian Network for the Monitoring and Surveillance of Air Pollution. Air quality measurements in the Valencian Community; 2020. Available from: https:\/\/agroambient.gva.es\/es\/web\/calidad-ambiental\/datos-historicos."},{"issue":"3","key":"pone.0284150.ref035","doi-asserted-by":"crossref","first-page":"612","DOI":"10.1080\/10618600.2017.1407325","article-title":"BAMLSS: Bayesian additive models for location, scale, and shape (and beyond)","volume":"27","author":"N Umlauf","year":"2018","journal-title":"Journal of Computational and Graphical Statistics"},{"key":"pone.0284150.ref036","article-title":"Pedestrian exposure to black carbon and PM2.5 emissions in urban hot spots: new findings using mobile measurement techniques and flexible Bayesian regression models","author":"HD Alas","year":"2021","journal-title":"J Exposure Sci Environ Epidemiol"},{"volume-title":"The elements of statistical learning: Data mining, inference, and prediction","year":"2021","author":"T Hastie","key":"pone.0284150.ref037"},{"issue":"Mar","key":"pone.0284150.ref038","first-page":"1157","article-title":"An introduction to variable and feature selection","volume":"3","author":"I Guyon","year":"2003","journal-title":"Journal of Machine Learning Research"},{"issue":"2","key":"pone.0284150.ref039","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1142\/S0219720005001004","article-title":"Minimum redundancy feature selection from microarray gene expression data","volume":"3","author":"C Ding","year":"2005","journal-title":"J Bioinform Comput Biol"},{"key":"pone.0284150.ref040","unstructured":"Yu L, Liu H. Feature selection for high-dimensional data: A fast correlation-based filter solution. In: Proc Int Conf Machine Learning; 2003. p. 856\u2013863."},{"key":"pone.0284150.ref041","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1016\/j.jbi.2018.07.014","article-title":"Relief-based feature selection: Introduction and review","volume":"85","author":"RJ Urbanowicz","year":"2018","journal-title":"J Biomed Inform"},{"key":"pone.0284150.ref042","first-page":"403","article-title":"Comparative study of techniques for large-scale feature selection","volume":"16","author":"FJ Ferri","year":"1994","journal-title":"Machine Intelligence and Pattern Recognition"},{"key":"pone.0284150.ref043","doi-asserted-by":"crossref","unstructured":"Chen XW. Gene selection for cancer classification using bootstrapped genetic algorithms and support vector machines. In: Proc IEEE Bioinformatics Conf CSB. vol. 46; 2003. p. 504\u2013505.","DOI":"10.1109\/CSB.2003.1227389"},{"key":"pone.0284150.ref044","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/1090.001.0001","volume-title":"Adaptation in natural and artificial systems: an introductory analysis with applications to biology, control, and artificial intelligence","author":"JH Holland","year":"1992"},{"key":"pone.0284150.ref045","doi-asserted-by":"crossref","unstructured":"Kennedy J, Eberhart RC. A discrete binary version of the particle swarm algorithm. In: Proc IEEE Int Conf Systems, Man Cybern. vol. 5; 1997. p. 4104\u20134108.","DOI":"10.1109\/ICSMC.1997.637339"},{"key":"pone.0284150.ref046","doi-asserted-by":"crossref","unstructured":"Harris DM, Harris SL. Digital design and computer architecture. O\u2019Reilly; 2012.","DOI":"10.1016\/B978-0-12-394424-5.00006-9"},{"issue":"6","key":"pone.0284150.ref047","doi-asserted-by":"crossref","first-page":"520","DOI":"10.1093\/bioinformatics\/17.6.520","article-title":"Missing value estimation methods for DNA microarrays","volume":"17","author":"O Troyanskaya","year":"2001","journal-title":"Bioinformatics"},{"issue":"3","key":"pone.0284150.ref048","first-page":"1","article-title":"mice: Multivariate imputation by chained equations in R","volume":"45","author":"S van Buuren","year":"2011","journal-title":"Journal of Statistical Software"},{"issue":"1","key":"pone.0284150.ref049","doi-asserted-by":"crossref","first-page":"106","DOI":"10.1186\/1471-2105-14-106","article-title":"SMOTE for high-dimensional class-imbalanced data","volume":"14","author":"R Blagus","year":"2013","journal-title":"BMC Bioinf"},{"issue":"1","key":"pone.0284150.ref050","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1007\/s10618-012-0295-5","article-title":"Training and assessing classification rules with imbalanced data","volume":"28","author":"G Menardi","year":"2014","journal-title":"Data Mining and Knowledge Discovery"},{"issue":"1","key":"pone.0284150.ref051","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1109\/TKDE.2015.2457911","article-title":"Ordinal regression methods: Survey and experimental study","volume":"28","author":"PA Guti\u00e9rrez","year":"2016","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"pone.0284150.ref052","unstructured":"Hayet-Otero M. Variable selection in high-dimensional data: application in a SARS-CoV-2 pneumonia clinical data-set [MSc Thesis]. University of the Basque Country (UPV\/EHU); 2021. Available from: https:\/\/bird.bcamath.org\/handle\/20.500.11824\/1537."},{"issue":"3","key":"pone.0284150.ref053","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1080\/00031305.1992.10475879","article-title":"An introduction to kernel and nearest-neighbor nonparametric regression","volume":"46","author":"NS Altman","year":"1992","journal-title":"The American Statistician"},{"issue":"3","key":"pone.0284150.ref054","doi-asserted-by":"crossref","first-page":"849","DOI":"10.1016\/S0031-3203(02)00257-1","article-title":"Strategies for learning in class imbalance problems","volume":"36","author":"R Barandela","year":"2003","journal-title":"Pattern Recognit"},{"issue":"8","key":"pone.0284150.ref055","doi-asserted-by":"crossref","first-page":"3494","DOI":"10.1016\/j.asoc.2013.03.021","article-title":"Modified binary PSO for feature selection using SVM applied to mortality prediction of septic patients","volume":"13","author":"SM Vieira","year":"2013","journal-title":"Appl Soft Comput"},{"key":"pone.0284150.ref056","first-page":"2825","article-title":"scikit-learn: Machine learning in Python","volume":"12","author":"F Pedregosa","year":"2011","journal-title":"Journal of Machine Learning Research"},{"issue":"17","key":"pone.0284150.ref057","first-page":"1","article-title":"imbalanced-learn: A Python toolbox to tackle the curse of imbalanced datasets in machine learning","volume":"18","author":"G Lema\u00eetre","year":"2017","journal-title":"Journal of Machine Learning Research"},{"issue":"8","key":"pone.0284150.ref058","doi-asserted-by":"crossref","first-page":"1226","DOI":"10.1109\/TPAMI.2005.159","article-title":"Feature selection based on mutual information: Criteria of max-dependency, max-relevance, and min-redundancy","volume":"27","author":"H Peng","year":"2005","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"6","key":"pone.0284150.ref059","first-page":"94","article-title":"Feature selection: A data perspective","volume":"50","author":"J Li","year":"2018","journal-title":"ACM Comput Surv"},{"key":"pone.0284150.ref060","doi-asserted-by":"crossref","first-page":"168","DOI":"10.1016\/j.jbi.2018.07.015","article-title":"Benchmarking Relief-based feature selection methods for bioinformatics data mining","volume":"85","author":"RJ Urbanowicz","year":"2018","journal-title":"J Biomed Inform"},{"key":"pone.0284150.ref061","unstructured":"Shetty K. Feature selection GA; 2021."},{"issue":"21","key":"pone.0284150.ref062","article-title":"PySwarms: A research toolkit for particle swarm optimization in Python","volume":"3","author":"LJV Miranda","year":"2018","journal-title":"Journal of Open Source Software"},{"key":"pone.0284150.ref063","unstructured":"Head T, MechCoder, Louppe G, Shcherbatyi I, fcharras, Vin\u00edcius Z, et al. Scikit-optimize\/scikit-optimize: v0.5.2; 2018."},{"key":"pone.0284150.ref064","doi-asserted-by":"crossref","unstructured":"McKerns MM, Strand L, Sullivan T, Fang A, Aivazis MA. Building a framework for predictive science. In: Proc 10th Python in Science Conf; 2011. p. 1\u201312. Available from: http:\/\/arxiv.org\/pdf\/1202.1056.","DOI":"10.25080\/Majora-ebaa42b7-00d"},{"issue":"3","key":"pone.0284150.ref065","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1109\/MCSE.2007.55","article-title":"Matplotlib: A 2D graphics environment","volume":"9","author":"JD Hunter","year":"2007","journal-title":"Computing in Science & Engineering"},{"issue":"60","key":"pone.0284150.ref066","doi-asserted-by":"crossref","first-page":"3021","DOI":"10.21105\/joss.03021","article-title":"Seaborn: statistical data visualization","volume":"6","author":"ML Waskom","year":"2021","journal-title":"Journal of Open Source Software"},{"key":"pone.0284150.ref067","doi-asserted-by":"crossref","unstructured":"Seabold S, Perktold J. Statsmodels: Econometric and statistical modeling with Python. In: Proc 9th Python in Science Conf; 2010. p. 92\u201396.","DOI":"10.25080\/Majora-92bf1922-011"},{"issue":"63","key":"pone.0284150.ref068","article-title":"Raincloud plots: a multi-platform tool for robust data visualization [version 2; peer review: 2 approved]","volume":"4","author":"M Allen","year":"2021","journal-title":"Wellcome Open Res"},{"key":"pone.0284150.ref069","unstructured":"Jordahl K, van den Bossche J, Fleischmann M, Wasserman J, McBride J, Gerard J, et al. Geopandas\/geopandas: v0.8.1; 2020."},{"key":"pone.0284150.ref070","unstructured":"World Health Organization. WHO global air quality guidelines: particulate matter (PM2.5 and PM10), ozone, nitrogen dioxide, sulfur dioxide and carbon monoxide. World Health Organization; 2021. Available from: https:\/\/apps.who.int\/iris\/handle\/10665\/345329."},{"issue":"3","key":"pone.0284150.ref071","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1016\/j.jkss.2012.10.002","article-title":"A bias-correction for Cram\u00e9r\u2019s V and Tschuprow\u2019s T","volume":"42","author":"W Bergsma","year":"2013","journal-title":"Journal of the Korean Statistical Society"},{"key":"pone.0284150.ref072","doi-asserted-by":"crossref","DOI":"10.4324\/9780203771587","volume-title":"Statistical power analysis for the behavioral sciences","author":"J Cohen","year":"2013"},{"key":"pone.0284150.ref073","first-page":"598","volume-title":"Statistical methods for rates and proportions","author":"JL Fleiss","year":"2004"},{"issue":"6","key":"pone.0284150.ref074","doi-asserted-by":"crossref","first-page":"389","DOI":"10.1080\/10408363.2020.1770685","article-title":"Biomarkers associated with COVID-19 disease progression","volume":"57","author":"G Ponti","year":"2020","journal-title":"Crit Rev Clin Lab Sci"},{"key":"pone.0284150.ref075","doi-asserted-by":"crossref","first-page":"60","DOI":"10.11606\/s1518-8787.2020054002481","article-title":"A brief-review of the risk factors for COVID-19 severity","volume":"54","author":"JE Rod","year":"2020","journal-title":"Rev Saude Publica"},{"issue":"2","key":"pone.0284150.ref076","doi-asserted-by":"crossref","first-page":"420","DOI":"10.1093\/ije\/dyab012","article-title":"The role of C-reactive protein as a prognostic marker in COVID-19","volume":"50","author":"D Stringer","year":"2021","journal-title":"Int J Epidemiol"},{"issue":"4","key":"pone.0284150.ref077","doi-asserted-by":"crossref","first-page":"332","DOI":"10.1016\/j.medmal.2020.03.007","article-title":"C-reactive protein levels in the early stage of COVID-19","volume":"50","author":"W L","year":"2020","journal-title":"M\u00e9decine et Maladies Infectieuses"},{"issue":"23","key":"pone.0284150.ref078","doi-asserted-by":"crossref","first-page":"2270","DOI":"10.1093\/eurheartj\/ehaa1103","article-title":"C-reactive protein and clinical outcomes in patients with COVID-19","volume":"42","author":"NR Smilowitz","year":"2021","journal-title":"Eur Heart J"},{"issue":"4","key":"pone.0284150.ref079","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1056\/NEJM199701233360402","article-title":"A prediction rule to identify low-risk patients with community-acquired pneumonia","volume":"336","author":"MJ Fine","year":"1997","journal-title":"N Engl J Med"},{"key":"pone.0284150.ref080","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1016\/j.ijid.2020.06.038","article-title":"Performance of pneumonia severity index and CURB-65 in predicting 30-day mortality in patients with COVID-19","volume":"98","author":"C Satici","year":"2020","journal-title":"Int J Infect Dis"},{"key":"pone.0284150.ref081","doi-asserted-by":"crossref","first-page":"100042","DOI":"10.1016\/j.resplu.2020.100042","article-title":"Predicting severe COVID-19 in the emergency department","volume":"4","author":"AR Holten","year":"2020","journal-title":"Resuscitation Plus"},{"issue":"5","key":"pone.0284150.ref082","doi-asserted-by":"crossref","first-page":"467","DOI":"10.1111\/crj.13326","article-title":"Validation of PSI\/PORT, CURB-65 and SCAP scoring system in COVID-19 pneumonia for prediction of disease severity and 14-day mortality","volume":"15","author":"A Anurag","year":"2021","journal-title":"The Clinical Respiratory Journal"},{"issue":"12","key":"pone.0284150.ref083","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0244171","article-title":"Oxygen saturation as a predictor of mortality in hospitalized adult patients with COVID-19 in a public hospital in Lima, Peru","volume":"15","author":"F Mej\u00eda","year":"2020","journal-title":"PLoS One"},{"issue":"7","key":"pone.0284150.ref084","doi-asserted-by":"crossref","first-page":"3636","DOI":"10.3390\/ijms23073636","article-title":"Neutrophil to lymphocyte ratio: An emerging marker of the relationships between the immune system and diseases","volume":"23","author":"A Buonacera","year":"2022","journal-title":"Int J Mol Sci"},{"issue":"8","key":"pone.0284150.ref085","doi-asserted-by":"crossref","first-page":"1796","DOI":"10.1111\/jgs.14894","article-title":"Neutrophil-to-lymphocyte ratio: An emerging marker predicting prognosis in elderly adults with community-acquired pneumonia","volume":"65","author":"E Cataudella","year":"2017","journal-title":"J Am Geriatr Soc"},{"issue":"8","key":"pone.0284150.ref086","doi-asserted-by":"crossref","DOI":"10.3390\/jcm11082235","article-title":"Neutrophil-to-lymphocyte ratio (NLR) is a promising predictor of mortality and admission to intensive care unit of COVID-19 patients","volume":"11","author":"M Regolo","year":"2022","journal-title":"J Clin Med"},{"issue":"1","key":"pone.0284150.ref087","article-title":"Neutrophil-to-lymphocyte ratio and mortality in the United States general population","volume":"11","author":"M Song","year":"2021","journal-title":"Sci Rep"},{"key":"pone.0284150.ref088","doi-asserted-by":"crossref","first-page":"111035","DOI":"10.1016\/j.ecoenv.2020.111035","article-title":"Region-specific air pollutants and meteorological parameters influence COVID-19: A study from mainland China","volume":"204","author":"S Lin","year":"2020","journal-title":"Ecotoxicol Environ Saf"},{"issue":"4","key":"pone.0284150.ref089","doi-asserted-by":"crossref","first-page":"6267","DOI":"10.1007\/s11356-021-15507-9","article-title":"Analyzing the severity of coronavirus infections in relation to air pollution: Evidence-based study from Saudi Arabia","volume":"29","author":"AAJ Ghanim","year":"2022","journal-title":"Environmental Science and Pollution Research"},{"key":"pone.0284150.ref090","doi-asserted-by":"crossref","first-page":"100250","DOI":"10.1016\/j.envadv.2022.100250","article-title":"A review on the biological, epidemiological, and statistical relevance of COVID-19 paired with air pollution","volume":"8","author":"EF Yates","year":"2022","journal-title":"Environmental Advances"},{"issue":"1","key":"pone.0284150.ref091","doi-asserted-by":"crossref","first-page":"200413","DOI":"10.4209\/aaqr.2020.07.0413","article-title":"Long-term air pollution exposure impact on COVID-19 morbidity in China","volume":"21","author":"Y Wu","year":"2021","journal-title":"Aerosol Air Qual Res"},{"issue":"6","key":"pone.0284150.ref092","doi-asserted-by":"crossref","first-page":"1100","DOI":"10.1017\/S0266466620000535","article-title":"Estimation of time-varying covariance matrices for large datasets","volume":"37","author":"Y Dendramis","year":"2021","journal-title":"Econometric Theory"},{"key":"pone.0284150.ref093","unstructured":"Huyen C. Designing machine learning systems. O\u2019Reilly Media; 2022."},{"issue":"21","key":"pone.0284150.ref094","doi-asserted-by":"crossref","DOI":"10.3390\/ijerph182111534","article-title":"Role of Sat O2, Pa O2\/Fi O2 ratio and Pa O2 to predict adverse aoutcome in COVID-19: A retrospective, cohort study","volume":"18","author":"S Sartini","year":"2021","journal-title":"Int J Environ Res Public Health"},{"issue":"1","key":"pone.0284150.ref095","doi-asserted-by":"crossref","DOI":"10.3390\/pathogens10010058","article-title":"Systemic inflammatory index is a novel predictor of intubation requirement and mortality after SARS-CoV-2 infection","volume":"10","author":"S Muhammad","year":"2021","journal-title":"Pathogens"},{"issue":"9","key":"pone.0284150.ref096","doi-asserted-by":"crossref","first-page":"619","DOI":"10.3390\/diagnostics10090619","article-title":"The model for early COVID-19 recognition (MECOR) score: A proof-of-concept for a simple and low-cost tool to recognize a possible viral etiology in community-acquired pneumonia patients during COVID-19 outbreak","volume":"10","author":"G Sambataro","year":"2020","journal-title":"Diagnostics"},{"issue":"10","key":"pone.0284150.ref097","doi-asserted-by":"crossref","DOI":"10.1002\/jcla.23618","article-title":"Ferritin in the coronavirus disease 2019 (COVID-19): A systematic review and meta-analysis","volume":"34","author":"L Cheng","year":"2020","journal-title":"J Clin Lab Anal"},{"issue":"6","key":"pone.0284150.ref098","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1002\/rmv.2141","article-title":"Interleukin-6 in COVID-19: A systematic review and meta-analysis","volume":"30","author":"EA Coomes","year":"2020","journal-title":"Rev Med Virol"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0284150","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,18]],"date-time":"2024-10-18T07:27:14Z","timestamp":1729236434000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0284150"}},"subtitle":[],"editor":[{"given":"Sathishkumar","family":"V E","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2023,4,13]]},"references-count":98,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2023,4,13]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0284150","relation":{},"ISSN":["1932-6203"],"issn-type":[{"type":"electronic","value":"1932-6203"}],"subject":[],"published":{"date-parts":[[2023,4,13]]}}}