Binary Logistic Regression and Linear Discriminant Analyses in Evaluating Laboratory Factors Associated with COVID-19: A Comparison of Two Statistical Methods
Introduction: Few studies have been conducted to construct a reliable predictive model for the differential diagnosis of severe and non-severe Coronavirus disease-2019 (COVID-19) in the early stages of the disease. This study aimed to compare the accuracy of linear discriminate analysis (LDA) and bi...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | Turkish |
| Published: |
Galenos Yayinevi
2022-05-01
|
| Series: | Mediterranean Journal of Infection, Microbes and Antimicrobials |
| Subjects: | |
| Online Access: | http://www.mjima.org/text.php?&id=318 |
| _version_ | 1797908727962009600 |
|---|---|
| author | Mohammad Mahdi POORHAJI Maryam SHAHRIYARI Mohammad Mahdi ASADI Farideh BAHRAMI Hadi Esmaeili GOUVRCHINGHALEH Tahere MOHAMMADZADEH Zeinab REZAYI Ensieh NAVIDIAN Zeinab SHANKAYI |
| author_facet | Mohammad Mahdi POORHAJI Maryam SHAHRIYARI Mohammad Mahdi ASADI Farideh BAHRAMI Hadi Esmaeili GOUVRCHINGHALEH Tahere MOHAMMADZADEH Zeinab REZAYI Ensieh NAVIDIAN Zeinab SHANKAYI |
| author_sort | Mohammad Mahdi POORHAJI |
| collection | DOAJ |
| description | Introduction: Few studies have been conducted to construct a reliable predictive model for the differential diagnosis of severe and non-severe Coronavirus disease-2019 (COVID-19) in the early stages of the disease. This study aimed to compare the accuracy of linear discriminate analysis (LDA) and binary logistic regression (BLR), as two empirical correlations, in predicting COVID-19 severity using single laboratory data and calculated indexes such as the neutrophil-to-lymphocyte ratio (NLR) and systemic immune-inflammation index (SII).
Materials and Methods: We investigated 109 patients with confirmed COVID-19 pneumonia. Epidemiological, demographic, clinical, laboratory, and outcome data were obtained, and the patients were classified into two groups: mild group (42 patients) and severe group (67 patients).
Results: A comparison of the clinical data in the severe and non-severe groups showed significant differences in SpO2 and respiratory rate. In addition, significant difference in NLR, SII, white blood cell count, neutrophil count, mean corpuscular volume and mean corpuscular hemoglobin, lymphocyte count, erythrocyte sedimentation rate, lactate dehydrogenase, and blood urea nitrogen was found between both groups. Moreover, there was a small difference between the LDA and LR models, and LDA was more appropriate for a smaller sample size.
Conclusion: Our predictive models could help clinicians to identify patients at risk of severe COVID-19 Such prediction can be performed by a simple blood test. LDA and BLR can be used to effectively classify patients with severe and non-severe COVID-19, even with violation of the normality assumption. |
| first_indexed | 2024-04-10T10:57:10Z |
| format | Article |
| id | doaj.art-1f2ce380446f42389f8778624cd3ac40 |
| institution | Directory Open Access Journal |
| issn | 2147-673X |
| language | Turkish |
| last_indexed | 2024-04-10T10:57:10Z |
| publishDate | 2022-05-01 |
| publisher | Galenos Yayinevi |
| record_format | Article |
| series | Mediterranean Journal of Infection, Microbes and Antimicrobials |
| spelling | doaj.art-1f2ce380446f42389f8778624cd3ac402023-02-15T16:19:51ZturGalenos YayineviMediterranean Journal of Infection, Microbes and Antimicrobials2147-673X2022-05-0111110.4274/mjima.galenos.2022.2021.20Binary Logistic Regression and Linear Discriminant Analyses in Evaluating Laboratory Factors Associated with COVID-19: A Comparison of Two Statistical MethodsMohammad Mahdi POORHAJI0https://orcid.org/0000-0003-2862-0458Maryam SHAHRIYARI1https://orcid.org/0000-0002-7861-6767Mohammad Mahdi ASADI2https://orcid.org/0000-0002-0426-1756Farideh BAHRAMI3https://orcid.org/0000-0002-7160-0834Hadi Esmaeili GOUVRCHINGHALEH4https://orcid.org/0000-0001-7176-2633Tahere MOHAMMADZADEH5https://orcid.org/0000-0002-5241-0285Zeinab REZAYI6https://orcid.org/0000-0003-3058-3342Ensieh NAVIDIAN7https://orcid.org/0000-0003-0094-7088Zeinab SHANKAYI8https://orcid.org/0000-0003-0522-6853Baqiyatallah University of Medical Sciences, Students’ Research Committee, Tehran, IranBaqiyatallah University of Medical Sciences, Students’ Research Committee, Tehran, IranBaqiyatallah University of Medical Sciences, Students’ Research Committee, Tehran, IranBaqiyatallah University of Medical Sciences, Neuroscience Research Center; Baqiyatallah University of Medical Sciences, School of Medicine, Department of Physiology and Medical Physics, Tehran, IranBaqiyatallah University of Medical Sciences, Applied Virology Research Center, Tehran, IranBaqiyatallah University of Medical Sciences, Lifestyle Institute, Health Research Center, Tehran, IranBaqiyatallah University of Medical Sciences, Students’ Research Committee, Tehran, IranBaqiyatallah University of Medical Sciences, Students’ Research Committee, Tehran, IranBaqiyatallah University of Medical Sciences, Neuroscience Research Center; Baqiyatallah University of Medical Sciences, School of Medicine, Department of Physiology and Medical Physics, Tehran, IranIntroduction: Few studies have been conducted to construct a reliable predictive model for the differential diagnosis of severe and non-severe Coronavirus disease-2019 (COVID-19) in the early stages of the disease. This study aimed to compare the accuracy of linear discriminate analysis (LDA) and binary logistic regression (BLR), as two empirical correlations, in predicting COVID-19 severity using single laboratory data and calculated indexes such as the neutrophil-to-lymphocyte ratio (NLR) and systemic immune-inflammation index (SII). Materials and Methods: We investigated 109 patients with confirmed COVID-19 pneumonia. Epidemiological, demographic, clinical, laboratory, and outcome data were obtained, and the patients were classified into two groups: mild group (42 patients) and severe group (67 patients). Results: A comparison of the clinical data in the severe and non-severe groups showed significant differences in SpO2 and respiratory rate. In addition, significant difference in NLR, SII, white blood cell count, neutrophil count, mean corpuscular volume and mean corpuscular hemoglobin, lymphocyte count, erythrocyte sedimentation rate, lactate dehydrogenase, and blood urea nitrogen was found between both groups. Moreover, there was a small difference between the LDA and LR models, and LDA was more appropriate for a smaller sample size. Conclusion: Our predictive models could help clinicians to identify patients at risk of severe COVID-19 Such prediction can be performed by a simple blood test. LDA and BLR can be used to effectively classify patients with severe and non-severe COVID-19, even with violation of the normality assumption.http://www.mjima.org/text.php?&id=318severe covid-19linear discriminant analysisbinary logistic regressionblood test data |
| spellingShingle | Mohammad Mahdi POORHAJI Maryam SHAHRIYARI Mohammad Mahdi ASADI Farideh BAHRAMI Hadi Esmaeili GOUVRCHINGHALEH Tahere MOHAMMADZADEH Zeinab REZAYI Ensieh NAVIDIAN Zeinab SHANKAYI Binary Logistic Regression and Linear Discriminant Analyses in Evaluating Laboratory Factors Associated with COVID-19: A Comparison of Two Statistical Methods Mediterranean Journal of Infection, Microbes and Antimicrobials severe covid-19 linear discriminant analysis binary logistic regression blood test data |
| title | Binary Logistic Regression and Linear Discriminant Analyses in Evaluating Laboratory Factors Associated with COVID-19: A Comparison of Two Statistical Methods |
| title_full | Binary Logistic Regression and Linear Discriminant Analyses in Evaluating Laboratory Factors Associated with COVID-19: A Comparison of Two Statistical Methods |
| title_fullStr | Binary Logistic Regression and Linear Discriminant Analyses in Evaluating Laboratory Factors Associated with COVID-19: A Comparison of Two Statistical Methods |
| title_full_unstemmed | Binary Logistic Regression and Linear Discriminant Analyses in Evaluating Laboratory Factors Associated with COVID-19: A Comparison of Two Statistical Methods |
| title_short | Binary Logistic Regression and Linear Discriminant Analyses in Evaluating Laboratory Factors Associated with COVID-19: A Comparison of Two Statistical Methods |
| title_sort | binary logistic regression and linear discriminant analyses in evaluating laboratory factors associated with covid 19 a comparison of two statistical methods |
| topic | severe covid-19 linear discriminant analysis binary logistic regression blood test data |
| url | http://www.mjima.org/text.php?&id=318 |
| work_keys_str_mv | AT mohammadmahdipoorhaji binarylogisticregressionandlineardiscriminantanalysesinevaluatinglaboratoryfactorsassociatedwithcovid19acomparisonoftwostatisticalmethods AT maryamshahriyari binarylogisticregressionandlineardiscriminantanalysesinevaluatinglaboratoryfactorsassociatedwithcovid19acomparisonoftwostatisticalmethods AT mohammadmahdiasadi binarylogisticregressionandlineardiscriminantanalysesinevaluatinglaboratoryfactorsassociatedwithcovid19acomparisonoftwostatisticalmethods AT faridehbahrami binarylogisticregressionandlineardiscriminantanalysesinevaluatinglaboratoryfactorsassociatedwithcovid19acomparisonoftwostatisticalmethods AT hadiesmaeiligouvrchinghaleh binarylogisticregressionandlineardiscriminantanalysesinevaluatinglaboratoryfactorsassociatedwithcovid19acomparisonoftwostatisticalmethods AT taheremohammadzadeh binarylogisticregressionandlineardiscriminantanalysesinevaluatinglaboratoryfactorsassociatedwithcovid19acomparisonoftwostatisticalmethods AT zeinabrezayi binarylogisticregressionandlineardiscriminantanalysesinevaluatinglaboratoryfactorsassociatedwithcovid19acomparisonoftwostatisticalmethods AT ensiehnavidian binarylogisticregressionandlineardiscriminantanalysesinevaluatinglaboratoryfactorsassociatedwithcovid19acomparisonoftwostatisticalmethods AT zeinabshankayi binarylogisticregressionandlineardiscriminantanalysesinevaluatinglaboratoryfactorsassociatedwithcovid19acomparisonoftwostatisticalmethods |