Machine Learning Successfully Detects Patients with COVID-19 Prior to PCR Results and Predicts Their Survival Based on Standard Laboratory Parameters in an Observational Study.

COVID-19 prognosis Laboratory parameters Machine learning Predictive features SARS-CoV-2 diagnosis

Journal

Infectious diseases and therapy
ISSN: 2193-8229
Titre abrégé: Infect Dis Ther
Pays: New Zealand
ID NLM: 101634499

Informations de publication

Date de publication:
Jan 2023
Historique:
received: 25 07 2022
accepted: 27 09 2022
pubmed: 6 11 2022
medline: 6 11 2022
entrez: 5 11 2022
Statut: ppublish

Résumé

In the current COVID-19 pandemic, clinicians require a manageable set of decisive parameters that can be used to (i) rapidly identify SARS-CoV-2 positive patients, (ii) identify patients with a high risk of a fatal outcome on hospital admission, and (iii) recognize longitudinal warning signs of a possible fatal outcome. This comparative study was performed in 515 patients in the Maria Skłodowska-Curie Specialty Voivodeship Hospital in Zgierz, Poland. The study groups comprised 314 patients with COVID-like symptoms who tested negative and 201 patients who tested positive for SARS-CoV-2 infection; of the latter, 72 patients with COVID-19 died and 129 were released from hospital. Data on which we trained several machine learning (ML) models included clinical findings on admission and during hospitalization, symptoms, epidemiological risk, and reported comorbidities and medications. We identified a set of eight on-admission parameters: white blood cells, antibody-synthesizing lymphocytes, ratios of basophils/lymphocytes, platelets/neutrophils, and monocytes/lymphocytes, procalcitonin, creatinine, and C-reactive protein. The medical decision tree built using these parameters differentiated between SARS-CoV-2 positive and negative patients with up to 90-100% accuracy. Patients with COVID-19 who on hospital admission were older, had higher procalcitonin, C-reactive protein, and troponin I levels together with lower hemoglobin and platelets/neutrophils ratio were found to be at highest risk of death from COVID-19. Furthermore, we identified longitudinal patterns in C-reactive protein, white blood cells, and D dimer that predicted the disease outcome. Our study provides sets of easily obtainable parameters that allow one to assess the status of a patient with SARS-CoV-2 infection, and the risk of a fatal disease outcome on hospital admission and during the course of the disease.

Identifiants

pubmed: 36333475
doi: 10.1007/s40121-022-00707-8
pii: 10.1007/s40121-022-00707-8
pmc: PMC9638383
doi:

Types de publication

Journal Article

Langues

eng

Pagination

111-129

Subventions

Organisme : Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung
ID : 310030_189334

Informations de copyright

© 2022. The Author(s).

Références

Sci Rep. 2021 Jul 9;11(1):14250
pubmed: 34244563
PLoS One. 2021 Jul 29;16(7):e0255154
pubmed: 34324560
J Med Syst. 2020 Jul 1;44(8):135
pubmed: 32607737
Am J Trop Med Hyg. 2021 Jan 22;104(3_Suppl):34-47
pubmed: 33534752
Med Microbiol Immunol. 2021 Feb;210(1):33-47
pubmed: 33219397
BMJ Health Care Inform. 2021 May;28(1):
pubmed: 33962987
Lancet Digit Health. 2021 Feb;3(2):e78-e87
pubmed: 33509388
PLoS One. 2021 Apr 28;16(4):e0250708
pubmed: 33909679
BMC Infect Dis. 2021 Feb 8;21(1):156
pubmed: 33557779
PLoS One. 2020 Nov 17;15(11):e0241955
pubmed: 33201896
JAMA. 2020 Mar 17;323(11):1061-1069
pubmed: 32031570
Euro Surveill. 2020 Jun;25(22):
pubmed: 32524949
Lancet. 2007 Oct 20;370(9596):1453-7
pubmed: 18064739
Lab Med. 2021 Mar 15;52(2):146-149
pubmed: 33340312
BMJ Evid Based Med. 2021 Jun;26(3):107-108
pubmed: 32934000
Biophys J. 2021 Jul 20;120(14):2838-2847
pubmed: 34087216
Lancet Respir Med. 2021 Jun;9(6):622-642
pubmed: 33965003
Microchem J. 2021 Aug;167:106305
pubmed: 33897053
N Engl J Med. 2020 May 21;382(21):2005-2011
pubmed: 32220208
Comput Struct Biotechnol J. 2021;19:2833-2850
pubmed: 34025952
Am J Emerg Med. 2021 Mar;41:110-119
pubmed: 33418211
J Clin Lab Anal. 2021 Dec;35(12):e24100
pubmed: 34762754
Intensive Care Med. 2020 Jul;46(7):1303-1325
pubmed: 32514598
BMJ. 2020 Apr 7;369:m1328
pubmed: 32265220
Eur Rev Med Pharmacol Sci. 2021 Jan;25(2):1135-1145
pubmed: 33577070
Am J Trop Med Hyg. 2021 Jan 06;104(3_Suppl):3-11
pubmed: 33410394
JAMA. 2013 Nov 27;310(20):2191-4
pubmed: 24141714
Emerg Infect Dis. 2020 Sep;26(9):2054-2063
pubmed: 32558639
Biomed Res Int. 2020 Nov 4;2020:8870249
pubmed: 33204723
Comput Biol Med. 2021 Jul;134:104531
pubmed: 34091385
Lancet. 2020 Feb 15;395(10223):497-506
pubmed: 31986264
Clin Chem Lab Med. 2020 Oct 21;59(2):421-431
pubmed: 33079698
Lancet. 2020 Feb 15;395(10223):507-513
pubmed: 32007143
Allergy. 2021 Feb;76(2):533-550
pubmed: 32662525
NPJ Digit Med. 2021 Jun 10;4(1):96
pubmed: 34112939
J Clin Pathol. 2020 Jul;73(7):370-377
pubmed: 32404473

Auteurs

Filip Styrzynski (F)

Department of Rheumatology with Subdepartment of Internal Medicine, Medical University of Lodz, 90-419, Lodz, Poland.

Damir Zhakparov (D)

Swiss Institute of Allergy and Asthma Research (SIAF), University of Zurich, Herman-Burchard-Strasse 9, 7265, Davos, Switzerland.
Swiss Institute of Bioinformatics, Lausanne, Switzerland.

Marco Schmid (M)

University of Applied Sciences of the Grisons, 7000, Chur, Switzerland.

Damian Roqueiro (D)

Swiss Institute of Bioinformatics, Lausanne, Switzerland.
Department of Biosystems Science and Engineering, ETH Zurich, 4058, Basel, Switzerland.

Zuzanna Lukasik (Z)

Department of Rheumatology with Subdepartment of Internal Medicine, Medical University of Lodz, 90-419, Lodz, Poland.
Swiss Institute of Allergy and Asthma Research (SIAF), University of Zurich, Herman-Burchard-Strasse 9, 7265, Davos, Switzerland.

Julia Solek (J)

Department of Pathology, Chair of Oncology, Medical University of Lodz, 90-419, Lodz, Poland.
Department of Biostatistics and Translational Medicine, Medical University of Lodz, 90-419, Lodz, Poland.

Jakub Nowicki (J)

Department of Paediatrics, Newborn Pathology and Bone Metabolic Diseases, Medical University of Lodz, 90-419, Lodz, Poland.

Milosz Dobrogowski (M)

Maria Sklodowska-Curie Specialty Voivodeship Hospital, 95-100, Zgierz, Poland.

Joanna Makowska (J)

Department of Rheumatology with Subdepartment of Internal Medicine, Medical University of Lodz, 90-419, Lodz, Poland. joanna.makowska@umed.lodz.pl.

Milena Sokolowska (M)

Swiss Institute of Allergy and Asthma Research (SIAF), University of Zurich, Herman-Burchard-Strasse 9, 7265, Davos, Switzerland. milena.sokolowska@siaf.uzh.ch.
Christine Kühne - Center for Allergy Research and Education (CK-CARE), 7265, Davos, Switzerland. milena.sokolowska@siaf.uzh.ch.

Katja Baerenfaller (K)

Swiss Institute of Allergy and Asthma Research (SIAF), University of Zurich, Herman-Burchard-Strasse 9, 7265, Davos, Switzerland. katja.baerenfaller@siaf.uzh.ch.
Swiss Institute of Bioinformatics, Lausanne, Switzerland. katja.baerenfaller@siaf.uzh.ch.

Classifications MeSH