Fig. 1From: Development and validation of an online model to predict critical COVID-19 with immune-inflammatory parametersFeature selection by LASSO. a LASSO variable trace profiles of the 6 features. The vertical dashed line shows the best lambda value (0.025) chosen by tenfold cross validation. b Feature with zero coefficient (colored with gray) at lambda = 0.025, was considered less crucial to the patient’s critical illness status and removed by Lasso logistic regression analysis. Feature with positive coefficient (colored with red) are regarded high risk in respect to critical illness. LASSO, least absolute shrinkage and selection operator. CRP, C reactive protein. PCT, procalcitonin. IL-2R, interleukin 2 receptor. IL-6, interleukin 6. T + B + NK, T lymphocyte and B lymphocyte and natural killer cells. Th/Ts,T-helper/T-suppressor lymphocyteBack to article page