COVID-19 Research Paper Volume 13, Issue 2 pp 1608—1619

Predicting severe or critical symptoms in hospitalized patients with COVID-19 from Yichang, China

Decision curve analysis on the net benefits gained by adding significant factors to the basic model. Abbreviations: FM, full model; BM, basic model. The orange solid line corresponds to the basic model that includes age, sex, smoking, hypertension, diabetes, cardiovascular disease, and cerebrovascular disease. The green solid line corresponds to the full model that includes both factors in the basic model and the five newly-identified unrelated significant factors including diagnostic delay, albumin, lactate dehydrogenase, white blood cell, and neutrophil. Over threshold probabilities of 0.17, the net benefit gained by adding the five significant factors was greater than that in the basic model.

Figure 1. Decision curve analysis on the net benefits gained by adding significant factors to the basic model. Abbreviations: FM, full model; BM, basic model. The orange solid line corresponds to the basic model that includes age, sex, smoking, hypertension, diabetes, cardiovascular disease, and cerebrovascular disease. The green solid line corresponds to the full model that includes both factors in the basic model and the five newly-identified unrelated significant factors including diagnostic delay, albumin, lactate dehydrogenase, white blood cell, and neutrophil. Over threshold probabilities of 0.17, the net benefit gained by adding the five significant factors was greater than that in the basic model.