Cargando…
Prediction of COVID-19 severity using laboratory findings on admission: informative values, thresholds, ML model performance
BACKGROUND: Despite the necessity, there is no reliable biomarker to predict disease severity and prognosis of patients with COVID-19. The currently published prediction models are not fully applicable to clinical use. OBJECTIVES: To identify predictive biomarkers of COVID-19 severity and to justify...
Autores principales: | , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
BMJ Publishing Group
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7918887/ https://www.ncbi.nlm.nih.gov/pubmed/33637550 http://dx.doi.org/10.1136/bmjopen-2020-044500 |
_version_ | 1783658025106538496 |
---|---|
author | Statsenko, Yauhen Al Zahmi, Fatmah Habuza, Tetiana Gorkom, Klaus Neidl-Van Zaki, Nazar |
author_facet | Statsenko, Yauhen Al Zahmi, Fatmah Habuza, Tetiana Gorkom, Klaus Neidl-Van Zaki, Nazar |
author_sort | Statsenko, Yauhen |
collection | PubMed |
description | BACKGROUND: Despite the necessity, there is no reliable biomarker to predict disease severity and prognosis of patients with COVID-19. The currently published prediction models are not fully applicable to clinical use. OBJECTIVES: To identify predictive biomarkers of COVID-19 severity and to justify their threshold values for the stratification of the risk of deterioration that would require transferring to the intensive care unit (ICU). METHODS: The study cohort (560 subjects) included all consecutive patients admitted to Dubai Mediclinic Parkview Hospital from February to May 2020 with COVID-19 confirmed by the PCR. The challenge of finding the cut-off thresholds was the unbalanced dataset (eg, the disproportion in the number of 72 patients admitted to ICU vs 488 non-severe cases). Therefore, we customised supervised machine learning (ML) algorithm in terms of threshold value used to predict worsening. RESULTS: With the default thresholds returned by the ML estimator, the performance of the models was low. It was improved by setting the cut-off level to the 25th percentile for lymphocyte count and the 75th percentile for other features. The study justified the following threshold values of the laboratory tests done on admission: lymphocyte count <2.59×10(9)/L, and the upper levels for total bilirubin 11.9 μmol/L, alanine aminotransferase 43 U/L, aspartate aminotransferase 32 U/L, D-dimer 0.7 mg/L, activated partial thromboplastin time (aPTT) 39.9 s, creatine kinase 247 U/L, C reactive protein (CRP) 14.3 mg/L, lactate dehydrogenase 246 U/L, troponin 0.037 ng/mL, ferritin 498 ng/mL and fibrinogen 446 mg/dL. CONCLUSION: The performance of the neural network trained with top valuable tests (aPTT, CRP and fibrinogen) is admissible (area under the curve (AUC) 0.86; 95% CI 0.486 to 0.884; p<0.001) and comparable with the model trained with all the tests (AUC 0.90; 95% CI 0.812 to 0.902; p<0.001). Free online tool at https://med-predict.com illustrates the study results. |
format | Online Article Text |
id | pubmed-7918887 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | BMJ Publishing Group |
record_format | MEDLINE/PubMed |
spelling | pubmed-79188872021-03-02 Prediction of COVID-19 severity using laboratory findings on admission: informative values, thresholds, ML model performance Statsenko, Yauhen Al Zahmi, Fatmah Habuza, Tetiana Gorkom, Klaus Neidl-Van Zaki, Nazar BMJ Open Health Informatics BACKGROUND: Despite the necessity, there is no reliable biomarker to predict disease severity and prognosis of patients with COVID-19. The currently published prediction models are not fully applicable to clinical use. OBJECTIVES: To identify predictive biomarkers of COVID-19 severity and to justify their threshold values for the stratification of the risk of deterioration that would require transferring to the intensive care unit (ICU). METHODS: The study cohort (560 subjects) included all consecutive patients admitted to Dubai Mediclinic Parkview Hospital from February to May 2020 with COVID-19 confirmed by the PCR. The challenge of finding the cut-off thresholds was the unbalanced dataset (eg, the disproportion in the number of 72 patients admitted to ICU vs 488 non-severe cases). Therefore, we customised supervised machine learning (ML) algorithm in terms of threshold value used to predict worsening. RESULTS: With the default thresholds returned by the ML estimator, the performance of the models was low. It was improved by setting the cut-off level to the 25th percentile for lymphocyte count and the 75th percentile for other features. The study justified the following threshold values of the laboratory tests done on admission: lymphocyte count <2.59×10(9)/L, and the upper levels for total bilirubin 11.9 μmol/L, alanine aminotransferase 43 U/L, aspartate aminotransferase 32 U/L, D-dimer 0.7 mg/L, activated partial thromboplastin time (aPTT) 39.9 s, creatine kinase 247 U/L, C reactive protein (CRP) 14.3 mg/L, lactate dehydrogenase 246 U/L, troponin 0.037 ng/mL, ferritin 498 ng/mL and fibrinogen 446 mg/dL. CONCLUSION: The performance of the neural network trained with top valuable tests (aPTT, CRP and fibrinogen) is admissible (area under the curve (AUC) 0.86; 95% CI 0.486 to 0.884; p<0.001) and comparable with the model trained with all the tests (AUC 0.90; 95% CI 0.812 to 0.902; p<0.001). Free online tool at https://med-predict.com illustrates the study results. BMJ Publishing Group 2021-02-26 /pmc/articles/PMC7918887/ /pubmed/33637550 http://dx.doi.org/10.1136/bmjopen-2020-044500 Text en © Author(s) (or their employer(s)) 2021. Re-use permitted under CC BY-NC. No commercial re-use. See rights and permissions. Published by BMJ. http://creativecommons.org/licenses/by-nc/4.0/ http://creativecommons.org/licenses/by-nc/4.0/This is an open access article distributed in accordance with the Creative Commons Attribution Non Commercial (CC BY-NC 4.0) license, which permits others to distribute, remix, adapt, build upon this work non-commercially, and license their derivative works on different terms, provided the original work is properly cited, appropriate credit is given, any changes made indicated, and the use is non-commercial. See: http://creativecommons.org/licenses/by-nc/4.0/. |
spellingShingle | Health Informatics Statsenko, Yauhen Al Zahmi, Fatmah Habuza, Tetiana Gorkom, Klaus Neidl-Van Zaki, Nazar Prediction of COVID-19 severity using laboratory findings on admission: informative values, thresholds, ML model performance |
title | Prediction of COVID-19 severity using laboratory findings on admission: informative values, thresholds, ML model performance |
title_full | Prediction of COVID-19 severity using laboratory findings on admission: informative values, thresholds, ML model performance |
title_fullStr | Prediction of COVID-19 severity using laboratory findings on admission: informative values, thresholds, ML model performance |
title_full_unstemmed | Prediction of COVID-19 severity using laboratory findings on admission: informative values, thresholds, ML model performance |
title_short | Prediction of COVID-19 severity using laboratory findings on admission: informative values, thresholds, ML model performance |
title_sort | prediction of covid-19 severity using laboratory findings on admission: informative values, thresholds, ml model performance |
topic | Health Informatics |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7918887/ https://www.ncbi.nlm.nih.gov/pubmed/33637550 http://dx.doi.org/10.1136/bmjopen-2020-044500 |
work_keys_str_mv | AT statsenkoyauhen predictionofcovid19severityusinglaboratoryfindingsonadmissioninformativevaluesthresholdsmlmodelperformance AT alzahmifatmah predictionofcovid19severityusinglaboratoryfindingsonadmissioninformativevaluesthresholdsmlmodelperformance AT habuzatetiana predictionofcovid19severityusinglaboratoryfindingsonadmissioninformativevaluesthresholdsmlmodelperformance AT gorkomklausneidlvan predictionofcovid19severityusinglaboratoryfindingsonadmissioninformativevaluesthresholdsmlmodelperformance AT zakinazar predictionofcovid19severityusinglaboratoryfindingsonadmissioninformativevaluesthresholdsmlmodelperformance |