Affordable Access

deepdyve-link
Publisher Website

Simple hemogram to support the decision-making of COVID-19 diagnosis using clusters analysis with self-organizing maps neural network

Authors
  • Souza, Alexandra A. de1
  • Almeida, Danilo Candido de2
  • Barcelos, Thiago S.1
  • Bortoletto, Rodrigo Campos1
  • Munoz, Roberto3
  • Waldman, Helio4
  • Goes, Miguel Angelo2
  • Silva, Leandro A.5
  • 1 Laboratory of Applied Computing - LABCOM3, Federal Institute of Education, Science and Technology of São Paulo, São Paulo, Brazil
  • 2 Federal University of São Paulo,
  • 3 Universidad de Valparaíso,
  • 4 Department of Communications, FEEC Unicamp, Campinas, SP Brazil
  • 5 Mackenzie Presbiterian University,
Type
Published Article
Journal
Soft Computing
Publisher
Springer-Verlag
Publication Date
May 17, 2021
Pages
1–12
Identifiers
DOI: 10.1007/s00500-021-05810-5
PMID: 34025211
PMCID: PMC8127503
Source
PubMed Central
Keywords
Disciplines
  • Focus
License
Unknown

Abstract

The pandemic caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) which is related to new coronavirus disease (COVID-19) has mobilized several scientifics to explore clinical data using soft-computing approaches. In the context of machine learning, previous studies have explored supervised algorithms to predict and support diagnosis based on several clinical parameters from patients diagnosed with and without COVID-19. However, in most of them the decision is based on a “black-box” method, making it impossible to discover the variable relevance in decision making. Hence, in this study, we introduce a non-supervised clustering analysis with neural network self-organizing maps (SOM) as a strategy of decision-making. We propose to identify potential variables in routine blood tests that can support clinician decision-making during COVID-19 diagnosis at hospital admission, facilitating rapid medical intervention. Based on SOM features (visual relationships between clusters and identification of patterns and behaviors), and using linear discriminant analysis , it was possible to detect a group of units of the map with a discrimination power around 83% to SARS-CoV-2-positive patients. In addition, we identified some variables in admission blood tests (Leukocytes, Basophils, Eosinophils, and Red cell Distribution Width) that, in combination had strong influence in the clustering performance, which could assist a possible clinical decision. Thus, although with limitations, we believe that SOM can be used as a soft-computing approach to support clinician decision-making in the context of COVID-19.

Report this publication

Statistics

Seen <100 times