Table 2.
Performance of noninvasive model for predicting latent shock, mean (95% CI).
| Minutes before the intervention | Threshold | DAR | AUROC | Recall | Specificity | NPV | PPV | F1-score |
|---|---|---|---|---|---|---|---|---|
| MIMIC-IV-EDa | ||||||||
| 0 | 0.4 | 0.97 (0.97–0.98) | 0.99 (0.98–0.99) | 0.96 (0.95–0.97) | 0.97 (0.97–0.98) | 1.00 (1.00–1.00) | 0.46 (0.44–0.47) | 0.62 (0.60–0.64) |
| ICCA-EDb | ||||||||
| 0 | 0.2 | 0.85 (0.79–0.92) | 0.99 (0.97–1.00) | 0.98 (0.96–1.00) | 0.85 (0.79–0.91) | 1.00 (0.99–1.00) | 0.16 (0.12–0.20) | 0.27 (0.22–0.33) |
| 10 | 0.2 | 0.86 (0.78–0.93) | 0.90 (0.84–0.96) | 0.86 (0.79–0.93) | 0.86 (0.78–0.93) | 1.00 (0.98–1.00) | 0.11 (0.08–0.15) | 0.20 (0.15–0.25) |
| 20 | 0.2 | 0.84 (0.78–0.91) | 0.86 (0.80–0.92) | 0.74 (0.66–0.82) | 0.85 (0.78–0.91) | 0.99 (0.97–1.00) | 0.12 (0.09–0.15) | 0.20 (0.16–0.25) |
| 30 | 0.2 | 0.85 (0.78–0.91) | 0.86 (0.79–0.92) | 0.69 (0.61–0.76) | 0.85 (0.79–0.92) | 0.99 (0.97–1.00) | 0.12 (0.09–0.15) | 0.20 (0.16–0.25) |
| 40 | 0.2 | 0.84 (0.77–0.91) | 0.86 (0.79–0.93) | 0.73 (0.64–0.81) | 0.84 (0.77–0.91) | 0.99 (0.97–1.00) | 0.11 (0.08–0.14) | 0.19 (0.14–0.23) |
| 50 | 0.2 | 0.84 (0.76–0.92) | 0.85 (0.78–0.93) | 0.75 (0.66–0.84) | 0.84 (0.77–0.92) | 0.99 (0.97–1.00) | 0.11 (0.08–0.14) | 0.19 (0.14–0.24) |
| 60 | 0.2 | 0.83 (0.75–0.92) | 0.81 (0.72–0.90) | 0.63 (0.56–0.76) | 0.84 (0.75–0.92) | 0.99 (0.97–1.00) | 0.09 (0.06–0.12) | 0.16 (0.11–0.21) |
| 70 | 0.2 | 0.84 (0.74–0.93) | 0.80 (0.70–0.90) | 0.56 (0.44–0.67) | 0.84 (0.75–0.94) | 0.99 (0.96–1.00) | 0.07 (0.04–0.10) | 0.12 (0.08–0.17) |
| 80 | 0.2 | 0.83 (0.73–0.93) | 0.85 (0.76–0.94) | 0.77 (0.66–0.88) | 0.83 (0.73–0.93) | 0.99 (0.97–1.00) | 0.09 (0.06–0.13) | 0.17 (0.11–0.22) |
| 90 | 0.2 | 0.83 (0.72–0.94) | 0.80 (0.68–0.92) | 0.70 (0.57–0.83) | 0.84 (0.73–0.95) | 0.99 (0.97–1.00) | 0.08 (0.04–0.11) | 0.14 (0.09–0.20) |
| 100 | 0.2 | 0.83 (0.71–0.95) | 0.80 (0.67–0.93) | 0.65 (0.50–0.79) | 0.83 (0.71–0.95) | 0.99 (0.96–1.00) | 0.07 (0.04–0.10) | 0.12 (0.07–0.18) |
| 110 | 0.2 | 0.82 (0.67–0.97) | 0.80 (0.65–0.95) | 0.58 (0.41–0.75) | 0.82 (0.68–0.97) | 0.99 (0.96–1.00) | 0.05 (0.02–0.08) | 0.09 (0.04–0.14) |
| 120 | 0.2 | 0.82 (0.62–1.00) | 0.73 (0.52–0.95) | 0.57(0.35–0.79) | 0.82(0.63–1.00) | 0.99(0.96–1.00) | 0.03(0.01–0.05) | 0.06(0.02–0.10) |
a
The noninvasive model of potential shock was externally validated on 0 min with the data set derived from MIMIC-IV-ED.
b
The noninvasive model of potential shock was externally validated every 10 min with the data set derived from ICCA in ED.