Selected article for: "blood exam and false negative"

Author: Felipe Soares; Aline Villavicencio; Michel Jose Anzanello; Flavio Sanson Fogliatto; Marco Idiart; Mark Stevenson
Title: A novel high specificity COVID-19 screening method based on simple blood exams and artificial intelligence
  • Document date: 2020_4_14
  • ID: 2s5xd1oc_50
    Snippet: The copyright holder for this preprint . We found that the proposed AI method was successful at discarding negative patients while flagging potential positive patients for COVID-19. When performing error analysis of the 100 replications, we found that 99 out of 599 patients were misclassified at least once, as shown in Table 2 . Of the patients misclassified as negative (false negatives), 28% were admitted to the hospital, possibly due to the sev.....
    Document: The copyright holder for this preprint . We found that the proposed AI method was successful at discarding negative patients while flagging potential positive patients for COVID-19. When performing error analysis of the 100 replications, we found that 99 out of 599 patients were misclassified at least once, as shown in Table 2 . Of the patients misclassified as negative (false negatives), 28% were admitted to the hospital, possibly due to the severity of their symptoms or to other factors such as comorbidities. In comparison, only 9.31% of the COVID-19 positive patients in the complete dataset were hospitalized. Thus, even with an average sensitivity of 70.25% obtained using a limited number of blood exam variables (which may already be viewed as an important finding), the combination of ER-CoV with clinical features may improve COVID-19 diagnosis and guarantee that people receive the adequate care.

    Search related documents:
    Co phrase search for related documents
    • adequate care and limited number: 1, 2, 3
    • AI method and average sensitivity: 1
    • AI method and false negative: 1
    • average sensitivity and error analysis: 1, 2
    • average sensitivity and false negative: 1, 2, 3, 4, 5, 6, 7
    • average sensitivity and limited number: 1
    • complete dataset and false negative: 1, 2
    • error analysis and false negative: 1
    • false negative and important finding: 1
    • false negative and limited number: 1, 2, 3, 4, 5, 6, 7, 8