Fig. 1: Statistics of the study data. | Nature Biomedical Engineering

Fig. 1: Statistics of the study data.

From: Open resource of clinical data from patients with pneumonia for the prediction of COVID-19 outcomes via deep learning

Fig. 1

a, Numbers of control subjects, subjects with suspected COVID-19, and patients with confirmed mild, regular, severe and critically ill forms of COVID-19 in cohorts 1 and 2. b, Numbers of patients that are cured, deceased and with unknown outcome in the two cohorts. c, Numbers of chest CT slices of patients with or without COVID-19 pneumonia and cured and deceased cases in the two cohorts. d, Statistical comparisons of CFs between subjects with COVID-19 (type I and type II) and controls (P < 10−5), between type II and type I cases (P < 10−9), and between deceased and cured cases (P < 10−5). Two-sided unpaired t-test was performed for data following a normal distribution; otherwise a Mann–Whitney U test was used. ALG, albumin/globulin ratio; ALB, albumin; ALP, alkaline phosphatase; APTT, activated partial thromboplastin time; AST, aspartate aminotransferase; BUN, urea nitrogen; CA, calcium; CRP, C-reactive protein; DBIL, direct bilirubin; DD, D-dimer; EO, eosinophil count; EOP, eosinophil percentage; GGT, γ-glutamyltransferase; GLB, globulin; GLU, glucose; HSCRP, high-sensitivity C-reactive protein; IL-6, interleukin-6; INR, international normalization ratio; LDH, lactate dehydrogenase; LY, lymphocyte count; LYP, lymphocyte percentage; MOP, monocyte percentage; NE, neutrophil count; NEP, neutrophil percentage; PCT, procalcitonin; PT, prothrombin time; RDWCV, red cell volume distribution width; RDWSD, standard deviation of red cell volume distribution width; TBIL, total bilirubin; and WBC, white blood cell. The full list and details of the CFs are presented in Supplementary Data 1. Further details on the statistical analyses are presented in Supplementary Data 3.

Back to article page