Hemogram data as a tool for decision-making in COVID-19 management: applications to resource scarcity scenarios.
COVID-19
Hemogram
Machine learning
Naïve-Bayes
Scarcity
Journal
PeerJ
ISSN: 2167-8359
Titre abrégé: PeerJ
Pays: United States
ID NLM: 101603425
Informations de publication
Date de publication:
2020
2020
Historique:
received:
10
05
2020
accepted:
15
06
2020
entrez:
14
7
2020
pubmed:
14
7
2020
medline:
14
7
2020
Statut:
epublish
Résumé
COVID-19 pandemics has challenged emergency response systems worldwide, with widespread reports of essential services breakdown and collapse of health care structure. A critical element involves essential workforce management since current protocols recommend release from duty for symptomatic individuals, including essential personnel. Testing capacity is also problematic in several countries, where diagnosis demand outnumbers available local testing capacity. This work describes a machine learning model derived from hemogram exam data performed in symptomatic patients and how they can be used to predict qRT-PCR test results. Hemogram exams data from 510 symptomatic patients (73 positives and 437 negatives) were used to model and predict qRT-PCR results through Naïve-Bayes algorithms. Different scarcity scenarios were simulated, including symptomatic essential workforce management and absence of diagnostic tests. Adjusts in assumed Proposed models can predict COVID-19 qRT-PCR results in symptomatic individuals with high accuracy, sensitivity and specificity, yielding a 100% sensitivity and 22.6% specificity with a Machine learning models can be derived from widely available, quick, and inexpensive exam data in order to predict qRT-PCR results used in COVID-19 diagnosis. These models can be used to assist strategic decision-making in resource scarcity scenarios, including personnel shortage, lack of medical resources, and testing insufficiency.
Sections du résumé
BACKGROUND
BACKGROUND
COVID-19 pandemics has challenged emergency response systems worldwide, with widespread reports of essential services breakdown and collapse of health care structure. A critical element involves essential workforce management since current protocols recommend release from duty for symptomatic individuals, including essential personnel. Testing capacity is also problematic in several countries, where diagnosis demand outnumbers available local testing capacity.
PURPOSE
OBJECTIVE
This work describes a machine learning model derived from hemogram exam data performed in symptomatic patients and how they can be used to predict qRT-PCR test results.
METHODS
METHODS
Hemogram exams data from 510 symptomatic patients (73 positives and 437 negatives) were used to model and predict qRT-PCR results through Naïve-Bayes algorithms. Different scarcity scenarios were simulated, including symptomatic essential workforce management and absence of diagnostic tests. Adjusts in assumed
RESULTS
RESULTS
Proposed models can predict COVID-19 qRT-PCR results in symptomatic individuals with high accuracy, sensitivity and specificity, yielding a 100% sensitivity and 22.6% specificity with a
CONCLUSIONS
CONCLUSIONS
Machine learning models can be derived from widely available, quick, and inexpensive exam data in order to predict qRT-PCR results used in COVID-19 diagnosis. These models can be used to assist strategic decision-making in resource scarcity scenarios, including personnel shortage, lack of medical resources, and testing insufficiency.
Identifiants
pubmed: 32656001
doi: 10.7717/peerj.9482
pii: 9482
pmc: PMC7331623
doi:
Types de publication
Journal Article
Langues
eng
Pagination
e9482Informations de copyright
© 2020 Avila et al.
Déclaration de conflit d'intérêts
The authors declare that they have no competing interests.
Références
JAMA. 2020 May 6;:
pubmed: 32374370
N Engl J Med. 2020 Mar 26;382(13):1194-1196
pubmed: 32074416
Lancet. 2003 Aug 2;362(9381):362-9
pubmed: 12907009
Lancet. 2020 May 2;395(10234):1418-1420
pubmed: 32305073
Lancet. 2020 Mar 21;395(10228):931-934
pubmed: 32164834
Am J Hematol. 2020 Jul;95(7):E158-E160
pubmed: 32279352
Am J Hematol. 2020 Jul;95(7):834-847
pubmed: 32282949
N Engl J Med. 2020 Apr 30;382(18):e41
pubmed: 32212516
Lancet Infect Dis. 2005 May;5(5):305-12
pubmed: 15854886
BMJ. 2020 Apr 7;369:m1328
pubmed: 32265220
Clin Immunol. 2020 Jun;215:108409
pubmed: 32276137
J Infect. 2013 Jun;66(6):545-7
pubmed: 23318262
Clin Chem Lab Med. 2020 Jun 25;58(7):1063-1069
pubmed: 32191623
Clin Biochem. 2020 Jul;81:1-8
pubmed: 32473151
Lancet. 2020 Mar 28;395(10229):1047-1053
pubmed: 32199075
Comput Biomed Res. 1968 May;1(5):490-507
pubmed: 5696985
J Infect. 2020 Jul;81(1):1-9
pubmed: 32315723
BMJ. 2020 Mar 18;368:m1090
pubmed: 32188598
N Engl J Med. 2020 May 21;382(21):2049-2055
pubmed: 32202722
N Engl J Med. 2020 Apr 30;382(18):1708-1720
pubmed: 32109013
Clin Chem Lab Med. 2020 Jul 28;58(8):1365-1371
pubmed: 32441666
Int J Surg. 2020 Jun;78:185-193
pubmed: 32305533
Expert Rev Mol Diagn. 2020 May;20(5):453-454
pubmed: 32297805
Lancet. 2020 Feb 15;395(10223):497-506
pubmed: 31986264
Am J Med Sci. 1960 Nov;240:571-8
pubmed: 13767416
Infect Dis Poverty. 2020 Mar 17;9(1):29
pubmed: 32183901