Statistical analysis
We expressed descriptive data as means (stds) for continuous variables and numbers (%) for categorical variables. Of the 192 critically ill patients with COVID-19, the mean age was (mean ), and 124 were male (64.6%). The most common clinical symptoms were fever (155 patients, 80.7%), cough (134 patients, 69.8%) and chest-pain (77 patients, 40.1%). A total of 134 (69.8%) patients had at least one basic disease. Among the non-survivors, 14 (28%) patients died of respiratory failure, 3 (6%) patients died of circulatory failure, 35 (70%) patients died of MOF, and 5 (10%) patients died of other causes, such as carcinoma, and severe immunological disorders secondary to rheumatic diseases.
We assessed the differences between survivors and non-survivors using a two-sample t test for continuous variables and a test of independence in a contingency table for categorical variables. The obtained test statistics and corresponding two-sided p values are listed in Table 1 and Table 2. Table 1 demonstrates the statistical analysis results of all self-evaluation indicators. Compared with survivors, non-survivors were older (t=-4.65, p=5.73×10-6), had a longer time from illness onset to admission (t=-13.2, p=1.2×10-28) and had a lower Barthel index score (t=7.75, p=2.1×10-13). There were significant differences between survivors and non-survivors in the distribution of age (χ2=33.8, p=2.5×10-6, Figure S1). Patients with chronic underlying conditions had worse outcomes, such as digestive disease (χ2=6.93, p=0.0085), cardiovascular disease (χ2=6.66, p=0.01), cerebrovascular disease (χ2=15.3, p=8.9×10-5) and chronic obstructive pulmonary disease (COPD) (χ2=5.6, p=0.018) than those without underlying conditions. The non-survivors were more likely to have dyspnea (χ2=7.82, p=5.1×10-4) than the survivors among all critically ill patients with COVID-19.
Table 2 demonstrates the statistical analysis results of all laboratory-examination indicators. As summarized in Table 2, the levels of inflammation or infection-related indices (C-reactive protein (CRP), white blood cell (WBC), Procalcitonin (PCT)) and hypercoagulability-related indicators (D-dimer, fibrin degradation products (FDP)) were significantly higher in the non-survivors than in the survivors. More prominent thrombocytopenia was found in non-survivors. Blood gas analysis and respiratory parameters revealed higher rates of hypoxia (lower PO2, SO2) and acidosis (lower pH values); higher CO2 levels; and greater lactate accumulation (higher PCO2, lat.) and respiratory impairment (lower oxygenation index (OI) values) in the non-survivors than in the survivors. The levels of albumin and calcium ions and lymphocyte counts (LYMPH) were significantly lower, and aspartate aminotransferase (AST), the international normalized ratio (INR), blood sugar and sodium ions were higher in the survivors than in the non-survivors. There were no significant differences in alanine aminotransferase (ALT), total bilirubin (TBIL), creatinine, blood urea nitrogen (BUN), or markers of hepatic or renal function between the survivors and non-survivors. There were no differences in the hemoglobin (Hb) level, erythrocyte sedimentation rate (ESR), prothrombin time (PT), activated partial thromboplastin time (APTT), fibrinogen (FIB) level or potassium ions between the two groups.
Classification performance and risk factors for mortality
To predict the prognosis of critically ill patients with COVID-19 according to indicators at admission, we constructed an SVM model with all the self-evaluation indicators and laboratory-examination indicators as input features. Over the 10 undersampling iterations, the classifiers achieved a mean test accuracy of 93% ± 2% between survivors and non-survivors from 10-fold CV, as shown in Figure 2 (A) (inner plot). Permutation testing showed that the accuracies reported by real-label samples were significantly different from those reported by random-label samples (p=0.019, Table S3).
Figure 2 (A) (outer plot) is the plot of all indicators sorted by weight. The greater the weight, the more likely the indicator was to be a risk factor for mortality. Duration (time from illness onset to admission) had the highest weight of 1, which meant it was the strongest predictor of all-cause mortality. The weights (ω) of 11 indicators were greater than 0.3, including 3 self-evaluation indicators: duration (ω=1±0), the Barthel index score (ω=0.45±0.11) and age (ω=0.33±0.12). For the non-survivors, the median time from illness onset to admission was 22.5 (IQR 15-28) days, and the median age was 71 (IQR 61-78) years, the median Barthel index score was 45 (IQR 10-70). When the duration, age and the Barthel index score increased by one day, one year and one point, the mortality increased by 3.6%, 2.4% and 0.9% respectively, as shown in black dashed lines in Figure 2 (B).
Eight laboratory-examination indicators with weights greater than 0.3, including CRP (ω=0.54±0.08), WBC (ω=0.5±0.09), Ca+ (ω=0.40±0.07), PLT (ω=0.39±0.08), FDP (ω=0.33±0.05), OI (ω=0.33±0.12), LYMPH (ω=0.31±0.08), and D-dimer (ω=0.30±0.06), were considered to be important risk factors. The detailed weights are listed in Table S4.
Predictive ability of self-evaluation indicators and laboratory-examination indicators
To estimate the predictive ability of the self-evaluation indicators and laboratory-examination indicators in predicting a poor prognosis, we constructed an SVM model with the self-evaluation indicators and laboratory-examination indicators as individual input features. Over the 10 under-sampling iterations, the classifiers achieved a mean test accuracy of 87.8% ± 1.8% between survivors and non-survivors from 10-fold CV when using the self-evaluation indicators and 85.6% ± 2.5% when using the laboratory-examination indicators. Duration (ω=1±0), the Barthel index score (ω=0.57±0.14) and age (ω=0.37±0.11) were still the most important risk factors when considering the self-evaluation indicators, as shown in Figure 3 (A). WBC (ω=0.96 ± 0.08), CRP (ω=0.91 ± 0.1), LYMPH (ω=0.65 ± 0.1), Ca+ (ω=0.59 ± 0.15), FDP (ω=0.56 ± 0.08), D-dimer (ω= 0.56 ± 0.12), and PLT (ω=0.55 ± 0.18) were risk factors when considering the laboratory-examination indicators, as shown in Figure 3 (B).