An Overview of Supervised Machine Learning Methods and Data Analysis for COVID-19 Detection.

Item request has been placed! ×
Item request cannot be made. ×
loading   Processing Request
Read More Add to Saved list
  • Additional Information
    • Source:
      Publisher: Hindawi Publishing Country of Publication: England NLM ID: 101528166 Publication Model: eCollection Cited Medium: Internet ISSN: 2040-2309 (Electronic) Linking ISSN: 20402295 NLM ISO Abbreviation: J Healthc Eng Subsets: MEDLINE
    • Publication Information:
      Publication: 2016-2024 : London: Hindawi Publishing
      Original Publication: [Essex] : Multi-Science Pub.
    • Subject Terms:
      COVID-19* ; Data Analysis*; Algorithms ; Brazil ; COVID-19 Testing ; Humans ; SARS-CoV-2 ; Supervised Machine Learning ; Support Vector Machine
    • Abstract:
      Methods: Our analysis and machine learning algorithm is based on most cited two clinical datasets from the literature: one from San Raffaele Hospital Milan Italia and the other from Hospital Israelita Albert Einstein São Paulo Brasilia. The datasets were processed to select the best features that most influence the target, and it turned out that almost all of them are blood parameters. EDA (Exploratory Data Analysis) methods were applied to the datasets, and a comparative study of supervised machine learning models was done, after which the support vector machine (SVM) was selected as the one with the best performance.
      Results: SVM being the best performant is used as our proposed supervised machine learning algorithm. An accuracy of 99.29%, sensitivity of 92.79%, and specificity of 100% were obtained with the dataset from Kaggle (https://www.kaggle.com/einsteindata4u/covid19) after applying optimization to SVM. The same procedure and work were performed with the dataset taken from San Raffaele Hospital (https://zenodo.org/record/3886927#.YIluB5AzbMV). Once more, the SVM presented the best performance among other machine learning algorithms, and 92.86%, 93.55%, and 90.91% for accuracy, sensitivity, and specificity, respectively, were obtained.
      Conclusion: The obtained results, when compared with others from the literature based on these same datasets, are superior, leading us to conclude that our proposed solution is reliable for the COVID-19 diagnosis.
      Competing Interests: The authors declare that they have no conflicts of interest.
      (Copyright © 2021 Aurelle Tchagna Kouanou et al.)
    • References:
      Nature. 2020 Mar;579(7798):270-273. (PMID: 32015507)
      JAMA. 2020 Aug 25;324(8):782-793. (PMID: 32648899)
      Int J Antimicrob Agents. 2020 Mar;55(3):105924. (PMID: 32081636)
      Int J Med Inform. 2021 Jan;145:104290. (PMID: 33099184)
      Euro Surveill. 2012 Sep 27;17(39):. (PMID: 23041020)
      BMJ. 2020 Apr 7;369:m1328. (PMID: 32265220)
      J Med Virol. 2020 Sep;92(9):1518-1524. (PMID: 32104917)
      J Med Syst. 2020 Jul 1;44(8):135. (PMID: 32607737)
      Inform Med Unlocked. 2020;21:100449. (PMID: 33102686)
      Sci Rep. 2021 May 24;11(1):10738. (PMID: 34031483)
      Phys Eng Sci Med. 2020 Jun;43(2):635-640. (PMID: 32524445)
      Euro Surveill. 2020 Jan;25(3):. (PMID: 31992387)
      J Assoc Physicians India. 2019 Apr;67(4):71-73. (PMID: 31309802)
      Lancet. 2003 May 24;361(9371):1767-72. (PMID: 12781535)
      Korean J Lab Med. 2009 Feb;29(1):1-9. (PMID: 19262072)
      IEEE Trans Neural Netw Learn Syst. 2012 Aug;23(8):1304-12. (PMID: 24807526)
      Clin Chem. 2020 Nov 1;66(11):1396-1404. (PMID: 32821907)
      Radiology. 2020 Aug;296(2):E65-E71. (PMID: 32191588)
      Int Immunopharmacol. 2020 Sep;86:106705. (PMID: 32652499)
      J Nonparametr Stat. 2015;27(2):167-179. (PMID: 27630515)
      PLoS Med. 2018 Dec 31;15(12):e1002721. (PMID: 30596635)
      J Healthc Eng. 2021 May 30;2021:9998819. (PMID: 34122785)
      BMC Med Inform Decis Mak. 2020 Sep 29;20(1):247. (PMID: 32993652)
      Int J Environ Res Public Health. 2020 May 24;17(10):. (PMID: 32456329)
      Ann Clin Lab Sci. 2020 May;50(3):299-307. (PMID: 32581016)
      Ann Card Anaesth. 2019 Oct-Dec;22(4):407-411. (PMID: 31621677)
      Nat Med. 2019 Jan;25(1):44-56. (PMID: 30617339)
      Radiology. 2020 Aug;296(2):E32-E40. (PMID: 32101510)
      J Healthc Eng. 2019 Sep 17;2019:6123745. (PMID: 31636879)
      Front Med (Lausanne). 2020 Feb 05;7:27. (PMID: 32118012)
      N Engl J Med. 2003 Dec 18;349(25):2431-41. (PMID: 14681510)
      Comput Biol Med. 2021 May;132:104335. (PMID: 33812263)
      J Infect. 2020 Apr;80(4):394-400. (PMID: 32109443)
      Ann Transl Med. 2019 Apr;7(8):161. (PMID: 31168442)
      Radiology. 2020 Aug;296(2):E41-E45. (PMID: 32049601)
      Biochem Med (Zagreb). 2011;21(3):203-9. (PMID: 22420233)
      Clin Chem Lab Med. 2020 Jun 25;58(7):1095-1099. (PMID: 32301746)
    • Publication Date:
      Date Created: 20211202 Date Completed: 20211206 Latest Revision: 20211214
    • Publication Date:
      20221213
    • Accession Number:
      PMC8629644
    • Accession Number:
      10.1155/2021/4733167
    • Accession Number:
      34853669