Dataset Open Access

Development, evaluation, and validation of machine learning models for COVID-19 detection based on routine blood tests

Cabitza, Federico; Campagner, Andrea; Ferrari, Davide; Di Resta, Chiara; Ceriotti, Daniele; Sabetta, Eleonora; Colombini, Alessandra; De Vecchi, Elena; Banfi, Giuseppe; Locatelli, Massimo; Carobene, Anna


JSON-LD (schema.org) Export

{
  "description": "<p>The .xlsx dataset includes all patients used for training, internal-external and external validation: these can be distinguished by looking at the ID (first column) in the dataset: those in format Axxxx-&lt;Date&gt; are the data used for the training, those in the format 20xx are the data used for the internal-external validation, while the remaining data were used for external validation.</p>\n\n<p>As regards the features: for the Target feature the value 1 stands for &quot;Positive to COVID-19&quot; while the value 0 stands for &quot;Negative to COVID-19&quot;; while for the Sex feature the value 1 stands for &quot;Male&quot; while the value 0 stands for &quot;Female&quot;.</p>\n\n<p>The full article is available at: https://www.degruyter.com/view/journals/cclm/ahead-of-print/article-10.1515-cclm-2020-1294/article-10.1515-cclm-2020-1294.xml.</p>\n\n<p>A pre-print version of the article is also available on MedrXiv:&nbsp;https://www.medrxiv.org/content/10.1101/2020.10.02.20205070v1</p>\n\n<p><strong>ABSTRACT</strong></p>\n\n<p><strong>Background</strong> The rRT-PCR test, the current gold standard for the detection of coronavirus disease (COVID-19),&nbsp;presents with known shortcomings, such as long turnaround time, potential shortage of reagents, false-negative&nbsp;rates around 15&ndash;20%, and expensive equipment. The hematochemical values of routine blood exams could&nbsp;represent a faster and less expensive alternative.&nbsp;</p>\n\n<p><strong>Methods</strong> Three different training data set of hematochemical values from 1,624 patients (52% COVID-19&nbsp;positive), admitted at San Raphael Hospital (OSR) from February to May 2020, were used for developing machine&nbsp;learning (ML) models: the complete OSR dataset (72 features: complete blood count (CBC), biochemical,&nbsp;coagulation, hemogasanalysis and CO-Oxymetry values, age, sex and specific symptoms at triage) and two sub&nbsp;datasets (COVID-specific and CBC dataset, 32 and 21 features respectively). 58 cases (50% COVID-19 positive)&nbsp;from another hospital, and 54 negative patients collected in 2018 at OSR, were used for internal-external and external validation.</p>\n\n<p><strong>Results</strong> We developed five ML models: for the complete OSR dataset, the area under the receiver operating&nbsp;characteristic curve (AUC) for the algorithms ranged from 0.83 to 0.90; for the COVID-specific dataset from 0.83 15 to 0.87; and for the CBC dataset from 0.74 to 0.86. The validations also achieved good results: respectively, AUC 16 from 0.75 to 0.78; and specificity from 0.92 to 0.96.&nbsp;</p>\n\n<p><strong>Conclusions</strong> ML can be applied to blood tests as both an adjunct and alternative method to rRT-PCR for the fast&nbsp;and cost-effective identification of COVID-19-positive patients. This is especially useful in developing countries,&nbsp;or in countries facing an increase in contagions.</p>", 
  "license": "https://creativecommons.org/licenses/by/4.0/legalcode", 
  "creator": [
    {
      "affiliation": "DISCo, Universit\u00e0 degli Studi di Milano-Bicocca, Viale Sarca 336, Milano, 20126, Italy", 
      "@type": "Person", 
      "name": "Cabitza, Federico"
    }, 
    {
      "affiliation": "IRCCS Istituto Ortopedico Galeazzi, Orthopaedic Biotechnology Lab, Via Riccardo Galeazzi, 4, 20161, Milano, Italy", 
      "@type": "Person", 
      "name": "Campagner, Andrea"
    }, 
    {
      "affiliation": "SCVSA Department, University of Parma, Parco Area delle Science 11/a, 43124, Parma, Italy", 
      "@type": "Person", 
      "name": "Ferrari, Davide"
    }, 
    {
      "affiliation": "Vita-Salute San Raffaele University; Unit of Genomics for Human Disease Diagnosis, Division of Genetics and Cell Biology., Via Olgettina 58, 20132, Milan, Italy", 
      "@type": "Person", 
      "name": "Di Resta, Chiara"
    }, 
    {
      "affiliation": "Laboratory Medicine, IRCCS San Raffaele Scientific Institute, Via Olgettina 60, 20132, Milan, Italy", 
      "@type": "Person", 
      "name": "Ceriotti, Daniele"
    }, 
    {
      "affiliation": "Laboratory Medicine, IRCCS San Raffaele Scientific Institute, Via Olgettina 60, 20132, Milan, Italy", 
      "@type": "Person", 
      "name": "Sabetta, Eleonora"
    }, 
    {
      "affiliation": "IRCCS Istituto Ortopedico Galeazzi, Orthopaedic Biotechnology Lab, Via Riccardo Galeazzi, 4, 20161, Milano, Italy", 
      "@type": "Person", 
      "name": "Colombini, Alessandra"
    }, 
    {
      "affiliation": "IRCCS Istituto Ortopedico Galeazzi, Orthopaedic Biotechnology Lab, Via Riccardo Galeazzi, 4, 20161, Milano, Italy", 
      "@type": "Person", 
      "name": "De Vecchi, Elena"
    }, 
    {
      "affiliation": "IRCCS Istituto Ortopedico Galeazzi, Orthopaedic Biotechnology Lab, Via Riccardo Galeazzi, 4, 20161, Milano, Italy", 
      "@type": "Person", 
      "name": "Banfi, Giuseppe"
    }, 
    {
      "affiliation": "Laboratory Medicine, IRCCS San Raffaele Scientific Institute, Via Olgettina 60, 20132, Milan, Italy", 
      "@type": "Person", 
      "name": "Locatelli, Massimo"
    }, 
    {
      "affiliation": "Laboratory Medicine, IRCCS San Raffaele Scientific Institute, Via Olgettina 60, 20132, Milan, Italy", 
      "@type": "Person", 
      "name": "Carobene, Anna"
    }
  ], 
  "url": "https://zenodo.org/record/4081318", 
  "datePublished": "2020-10-12", 
  "@context": "https://schema.org/", 
  "distribution": [
    {
      "contentUrl": "https://zenodo.org/api/files/c9e39fc7-b83c-4f8c-b5eb-2173b1f9a2d9/all_training.xlsx", 
      "encodingFormat": "xlsx", 
      "@type": "DataDownload"
    }
  ], 
  "identifier": "https://doi.org/10.1515/cclm-2020-1294", 
  "@id": "https://doi.org/10.1515/cclm-2020-1294", 
  "@type": "Dataset", 
  "name": "Development, evaluation, and validation of machine learning models for COVID-19 detection based on routine blood tests"
}
1,065
473
views
downloads
Views 1,065
Downloads 473
Data volume 143.7 MB
Unique views 961
Unique downloads 393

Share

Cite as