Item request has been placed! ×
Item request cannot be made. ×
loading  Processing Request

Machine learning model for predicting severity prognosis in patients infected with COVID-19: Study protocol from COVID-AI Brasil.

Item request has been placed! ×
Item request cannot be made. ×
loading   Processing Request
Read Online Read More Add to Saved list
  • Additional Information
    • Corporate Authors:
      COVID-AI-Brasil
    • Source:
      Publisher: Public Library of Science Country of Publication: United States NLM ID: 101285081 Publication Model: eCollection Cited Medium: Internet ISSN: 1932-6203 (Electronic) Linking ISSN: 19326203 NLM ISO Abbreviation: PLoS One Subsets: MEDLINE
    • Publication Information:
      Original Publication: San Francisco, CA : Public Library of Science
    • Subject Terms:
      Artificial Intelligence* ; Machine Learning* ; Severity of Illness Index*; COVID-19/*diagnosis ; COVID-19/*pathology; Algorithms ; Brazil ; Humans ; Prognosis ; Sample Size
    • Abstract:
      The new coronavirus, which began to be called SARS-CoV-2, is a single-stranded RNA beta coronavirus, initially identified in Wuhan (Hubei province, China) and currently spreading across six continents causing a considerable harm to patients, with no specific tools until now to provide prognostic outcomes. Thus, the aim of this study is to evaluate possible findings on chest CT of patients with signs and symptoms of respiratory syndromes and positive epidemiological factors for COVID-19 infection and to correlate them with the course of the disease. In this sense, it is also expected to develop specific machine learning algorithm for this purpose, through pulmonary segmentation, which can predict possible prognostic factors, through more accurate results. Our alternative hypothesis is that the machine learning model based on clinical, radiological and epidemiological data will be able to predict the severity prognosis of patients infected with COVID-19. We will perform a multicenter retrospective longitudinal study to obtain a large number of cases in a short period of time, for better study validation. Our convenience sample (at least 20 cases for each outcome) will be collected in each center considering the inclusion and exclusion criteria. We will evaluate patients who enter the hospital with clinical signs and symptoms of acute respiratory syndrome, from March to May 2020. We will include individuals with signs and symptoms of acute respiratory syndrome, with positive epidemiological history for COVID-19, who have performed a chest computed tomography. We will assess chest CT of these patients and to correlate them with the course of the disease. Primary outcomes:1) Time to hospital discharge; 2) Length of stay in the ICU; 3) orotracheal intubation;4) Development of Acute Respiratory Discomfort Syndrome. Secondary outcomes:1) Sepsis; 2) Hypotension or cardiocirculatory dysfunction requiring the prescription of vasopressors or inotropes; 3) Coagulopathy; 4) Acute Myocardial Infarction; 5) Acute Renal Insufficiency; 6) Death. We will use the AUC and F1-score of these algorithms as the main metrics, and we hope to identify algorithms capable of generalizing their results for each specified primary and secondary outcome.
      Competing Interests: The authors have read the journal’s policy and have the following potential competing interests: FPPLL has received sponsorship for participation in courses and symposia from Bayer, and for scientific consultancy and lectures for Bayer and Novartis. GS has received sponsorship for participation in courses and symposia for Bayer, and fees for Lectures in Cardiothoracic Imaging for Bayer, Novartis, and Amgen. FCK is a paid employee of Diagnósticos da América (DASA) and a consultant for MD.ai. GFP has received sponsorship for participation in courses and symposia from Boehringer-Ingelheim, AstraZeneca and Bristol Myers Squibb, and for scientific consultancy and lectures from Boehringer-Ingelheim, AstraZeneca, Pfizer, Bristol Myers Squibb, Merck Sharpe & Dohme. VPSR and MRFM are paid employees of DASA. This does not alter our adherence to PLOS ONE policies on sharing data and materials. There are no patents, products in development or marketed products associated with this research to declare.
    • References:
      Nature. 2020 Mar;579(7798):270-273. (PMID: 32015507)
      JAMA Netw Open. 2018 Sep 7;1(5):e182658. (PMID: 30646173)
      Lancet. 2020 Mar 28;395(10229):1054-1062. (PMID: 32171076)
      Radiology. 2018 Aug;288(2):318-328. (PMID: 29944078)
      Theranostics. 2020 Apr 27;10(12):5613-5622. (PMID: 32373235)
      JAMA. 2012 Jun 20;307(23):2526-33. (PMID: 22797452)
      Lancet. 2020 Feb 15;395(10223):497-506. (PMID: 31986264)
      J Med Virol. 2020 Jun;92(6):577-583. (PMID: 32162702)
      Radiol Cardiothorac Imaging. 2020 Mar 30;2(2):e200047. (PMID: 33778560)
      Nature. 2015 Feb 26;518(7540):529-33. (PMID: 25719670)
      Radiology. 2020 Aug;296(2):E46-E54. (PMID: 32155105)
      J Thorac Imaging. 2020 Jul;35(4):219-227. (PMID: 32324653)
      Nature. 2020 Aug;584(7821):430-436. (PMID: 32640463)
      PLoS One. 2020 Mar 19;15(3):e0230548. (PMID: 32191764)
      Radiographics. 2017 Nov-Dec;37(7):2113-2131. (PMID: 29131760)
      Radiology. 2018 Mar;286(3):800-809. (PMID: 29309734)
      Nephrology (Carlton). 2014 May;19(5):261-5. (PMID: 24571801)
      J Med Internet Res. 2020 Aug 10;22(8):e19104. (PMID: 32584780)
    • Publication Date:
      Date Created: 20210201 Date Completed: 20210209 Latest Revision: 20240330
    • Publication Date:
      20240330
    • Accession Number:
      PMC7850490
    • Accession Number:
      10.1371/journal.pone.0245384
    • Accession Number:
      33524039