Artificial neural network identifies nonsteroidal anti-inflammatory drugs exacerbated respiratory disease (N-ERD) cohort.
artificial neural network
aspirin-tolerant asthma
induced sputum
nonsteroidal anti-inflammatory drug (NSAID)-exacerbated respiratory disease (N-ERD)
support vector machines
Journal
Allergy
ISSN: 1398-9995
Titre abrégé: Allergy
Pays: Denmark
ID NLM: 7804028
Informations de publication
Date de publication:
07 2020
07 2020
Historique:
received:
24
06
2019
revised:
16
12
2019
accepted:
02
01
2020
pubmed:
6
2
2020
medline:
15
5
2021
entrez:
4
2
2020
Statut:
ppublish
Résumé
To date, there has been no reliable in vitro test to either diagnose or differentiate nonsteroidal anti-inflammatory drug (NSAID)-exacerbated respiratory disease (N-ERD). The aim of the present study was to develop and validate an artificial neural network (ANN) for the prediction of N-ERD in patients with asthma. This study used a prospective database of patients with N-ERD (n = 121) and aspirin-tolerant (n = 82) who underwent aspirin challenge from May 2014 to May 2018. Eighteen parameters, including clinical characteristics, inflammatory phenotypes based on sputum cells, as well as eicosanoid levels in induced sputum supernatant (ISS) and urine were extracted for the ANN. The validation sensitivity of ANN was 94.12% (80.32%-99.28%), specificity was 73.08% (52.21%-88.43%), and accuracy was 85.00% (77.43%-92.90%) for the prediction of N-ERD. The area under the receiver operating curve was 0.83 (0.71-0.90). The designed ANN model seems to have powerful prediction capabilities to provide diagnosis of N-ERD. Although it cannot replace the gold-standard aspirin challenge test, the implementation of the ANN might provide an added value for identification of patients with N-ERD. External validation in a large cohort is needed to confirm our results.
Sections du résumé
BACKGROUND
To date, there has been no reliable in vitro test to either diagnose or differentiate nonsteroidal anti-inflammatory drug (NSAID)-exacerbated respiratory disease (N-ERD). The aim of the present study was to develop and validate an artificial neural network (ANN) for the prediction of N-ERD in patients with asthma.
METHODS
This study used a prospective database of patients with N-ERD (n = 121) and aspirin-tolerant (n = 82) who underwent aspirin challenge from May 2014 to May 2018. Eighteen parameters, including clinical characteristics, inflammatory phenotypes based on sputum cells, as well as eicosanoid levels in induced sputum supernatant (ISS) and urine were extracted for the ANN.
RESULTS
The validation sensitivity of ANN was 94.12% (80.32%-99.28%), specificity was 73.08% (52.21%-88.43%), and accuracy was 85.00% (77.43%-92.90%) for the prediction of N-ERD. The area under the receiver operating curve was 0.83 (0.71-0.90).
CONCLUSIONS
The designed ANN model seems to have powerful prediction capabilities to provide diagnosis of N-ERD. Although it cannot replace the gold-standard aspirin challenge test, the implementation of the ANN might provide an added value for identification of patients with N-ERD. External validation in a large cohort is needed to confirm our results.
Identifiants
pubmed: 32012310
doi: 10.1111/all.14214
pmc: PMC7383769
doi:
Substances chimiques
Anti-Inflammatory Agents, Non-Steroidal
0
Pharmaceutical Preparations
0
Aspirin
R16CO5Y76E
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
1649-1658Informations de copyright
© 2020 The Authors. Allergy published by John Wiley & Sons Ltd.
Références
Allergy. 2014 Nov;69(11):1550-9
pubmed: 25123806
Ann Allergy Asthma Immunol. 2014 Sep;113(3):314-20
pubmed: 25037608
J Allergy Clin Immunol Pract. 2016 Jul-Aug;4(4):665-70
pubmed: 27080204
Allergy Asthma Proc. 2013 Jul-Aug;34(4):378-82
pubmed: 23883603
Allergy. 2019 May;74(5):922-932
pubmed: 30446997
Clin Mol Allergy. 2017 Apr 13;15:10
pubmed: 28413358
Allergy. 2005 Sep;60(9):1139-45
pubmed: 16076298
J Allergy Clin Immunol. 2017 Mar;139(3):819-825.e6
pubmed: 27567328
J Allergy Clin Immunol Pract. 2017 Jul - Aug;5(4):1061-1070.e3
pubmed: 28286156
J Allergy Clin Immunol. 2017 Jun;139(6):1797-1807
pubmed: 27773852
Br Med J. 1975 Jan 11;1(5949):67-9
pubmed: 1109660
J Allergy Clin Immunol Pract. 2019 Apr;7(4):1174-1180
pubmed: 30391549
Allergy. 2020 Jul;75(7):1649-1658
pubmed: 32012310
Ann Allergy Asthma Immunol. 2006 Aug;97(2):190-5
pubmed: 16937750
N Engl J Med. 2018 Sep 13;379(11):1060-1070
pubmed: 30207919
J Allergy Clin Immunol. 2016 May;137(5):1566-1576.e5
pubmed: 26691435
Allergy. 2007 Oct;62(10):1111-8
pubmed: 17521312
J Allergy Clin Immunol. 2015 Mar;135(3):676-81.e1
pubmed: 25282015
Eur Respir J Suppl. 2002 Sep;37:9s-18s
pubmed: 12361366
Clin Exp Allergy. 2015 Dec;45(12):1779-89
pubmed: 26449970
PLoS Med. 2018 Nov 13;15(11):e1002691
pubmed: 30422985
J Allergy Clin Immunol Pract. 2019 May - Jun;7(5):1580-1588
pubmed: 30580047
Sci Rep. 2018 Aug 3;8(1):11645
pubmed: 30076356
Respir Med. 2019 Jun;152:51-59
pubmed: 31128610
Clin Exp Allergy. 2004 Sep;34(9):1448-57
pubmed: 15347380
Allergy. 2019 Jul;74(7):1364-1373
pubmed: 30737985
J Allergy Clin Immunol Pract. 2017 Jul - Aug;5(4):990-997.e1
pubmed: 28202405
Clin Exp Allergy. 2017 Jan;47(1):37-47
pubmed: 27533637
PLoS One. 2013 Jun 21;8(6):e66644
pubmed: 23805255
Eur Respir J Suppl. 2002 Sep;37:1s-2s
pubmed: 12361359