Lymphocyte–monocyte–neutrophil index: a predictor of severity of coronavirus disease 2019 patients produced by sparse principal component analysis

Qi, Yingjie; Jia, Jian-an; Li, Huiming; Wan, Nagen; Zhang, Shuqin; Ma, Xiaoling

doi:10.1186/s12985-021-01561-9

Virology Journal

Table 4 Summary of severity prediction efficiency of COVID-19 patients in the independent cohort (Nanchang Cohort)

From: Lymphocyte–monocyte–neutrophil index: a predictor of severity of coronavirus disease 2019 patients produced by sparse principal component analysis

	Cutoff	AUC(95% CI)	AUC(95% CI)	SEN(95% CI)	SPE(95% CI)	PPV(95% CI)	NPV(95% CI)
Model-A	0.484	0.835 (0.774–0.895)	0.835 (0.774–0.895)	0.831 (0.735–0.926)	0.718 (0.634–0.802)	0.612 (0.506–0.719)	0.888 (0.822–0.953)
LMN	0.711	0.8 (0.733–0.868)	0.8 (0.733–0.868)	0.729 (0.615–0.842)	0.745 (0.664–0.827)	0.606 (0.492–0.719)	0.837 (0.764–0.91)
ALB	38.25	0.816 (0.742–0.891)	0.816 (0.742–0.891)	0.769 (0.655–0.884)	0.788 (0.71–0.867)	0.645 (0.526–0.764)	0.872 (0.805–0.94)
CD4	308	0.708 (0.624–0.791)	0.708 (0.624–0.791)	0.625 (0.498–0.752)	0.731 (0.646–0.816)	0.556 (0.433–0.678)	0.784 (0.702–0.865)
CD8	176	0.694 (0.608–0.781)	0.694 (0.608–0.781)	0.554 (0.423–0.684)	0.75 (0.667–0.833)	0.544 (0.415–0.673)	0.757 (0.674–0.84)
CRP	8.15	0.7 (0.618–0.781)	0.7 (0.618–0.781)	0.724 (0.609–0.839)	0.578 (0.485–0.671)	0.477 (0.373–0.582)	0.797 (0.709–0.886)
DD	0.99	0.758 (0.675–0.841)	0.758 (0.675–0.841)	0.615 (0.483–0.748)	0.823 (0.747–0.899)	0.653 (0.52–0.786)	0.798 (0.719–0.877)
Lym	0.605	0.785 (0.714–0.855)	0.785 (0.714–0.855)	0.593 (0.468–0.719)	0.872 (0.809–0.934)	0.714 (0.588–0.841)	0.798 (0.726–0.87)
Lym%	13.95	0.788 (0.716–0.859)	0.788 (0.716–0.859)	0.746 (0.635–0.857)	0.743 (0.661–0.825)	0.611 (0.499–0.724)	0.844 (0.771–0.916)
Neu	5.055	0.71 (0.625–0.794)	0.71 (0.625–0.794)	0.729 (0.615–0.842)	0.661 (0.572–0.749)	0.538 (0.428–0.647)	0.818 (0.738–0.899)
Neu%	78.4	0.775 (0.701–0.849)	0.775 (0.701–0.849)	0.763 (0.654–0.871)	0.706 (0.621–0.792)	0.584 (0.474–0.694)	0.846 (0.772–0.92)
NLR	5.691	0.784 (0.711–0.856)	0.784 (0.711–0.856)	0.746 (0.635–0.857)	0.743 (0.661–0.825)	0.611 (0.499–0.724)	0.844 (0.771–0.916)

Disease severity prediction models: Model-A and LMN index were produced by SPCA and logistic regression from Hefei Cohort. Prediction efficiency of these models and clinical markers were assessed in independent validation cohort using ROC and AUC. ACC, SEN, SPE, PPV, NPV were calculated
ALB albumin, AUC area under curve, CD4 CD4 + T lymphocytes, CD8 CD8 + T lymphocytes, CI confidence interval, COVID-19 coronavirus disease 2019, CRP C-reactive protein, DD D-Dimer, LMN index lymphocyte–monocyte–neutrophil index, simplified version of Model-A, LYM lymphocyte count, LYM% lymphocyte percentage, Model-A prediction model based on the first and 12th principal components produced by sparse principal component analysis, NEU neutrophil count, NEU% neutrophils percentage, NLR netrophil-to-lymphocyte ratio, NPV negative predictive value, PPV positive predictive value, NPV negative predictive value, PPV positive predictive value

Back to article page

ISSN: 1743-422X

Contact us

Submission enquiries: journalsubmissions@springernature.com