Table 6 Accuracy, sensitivity and specificity of the proposed prediction model in the test dataset at different thresholds
Survival probability | Threshold | True positive | False positive | True negative | False negative | Accuracy | Sensitivity | Specificity |
|---|---|---|---|---|---|---|---|---|
0.1 | 2.197 | 8824 | 87 | 4,570,611 | 6444 | 0.999 (0.999—0.999) | 0.578 (0.570—0.586) | 1.000 (1.000—1.000) |
0.2 | 1.386 | 8829 | 169 | 4,570,529 | 6339 | 0.999 (0.999—0.999) | 0.585 (0.577—0.593) | 1.000 (1.000—1.000) |
0.3 | 0.847 | 9049 | 342 | 4,570,356 | 6219 | 0.999 (0.999—0.999) | 0.593 (0.585—0.600) | 1.000 (1.000—1.000) |
0.4 | 0.405 | 9154 | 497 | 4,570,201 | 6114 | 0.999 (0.999—0.999) | 0.600 (0.592—0.607) | 1.000 (1.000—1.000) |
0.5 | 0 | 9329 | 820 | 4,569,878 | 5939 | 0.999 (0.998—0.999) | 0.611 (0.603—0.619) | 1.000 (1.000—1.000) |
0.6 | -0.405 | 9457 | 1074 | 4,569,624 | 5811 | 0.998 (0.998—0.999) | 0.619 (0.612—0.627) | 1.000 (1.000—1.000) |
0.7 | -0.847 | 9695 | 1662 | 4,569,036 | 5573 | 0.998 (0.998—0.998) | 0.635 (0.627—0.643) | 1.000 (1.000—1.000) |
0.8 | -1.386 | 9951 | 2360 | 4,568,338 | 5317 | 0.998 (0.998—0.998) | 0.652 (0.644—0.659) | 0.999 (0.999—1.000) |
0.9 | -2.197 | 10,332 | 4470 | 4,566,228 | 4936 | 0.998 (0.998—0.998) | 0.677 (0.669—0.684) | 0.999 (0.999—0.999) |
0.99 | -4.595 | 11,961 | 42,963 | 4,527,735 | 3307 | 0.990 (0.990—0.990) | 0.783 (0.777—0.790) | 0.991 (0.991—0.991) |
0.999 | -6.907 | 14,434 | 680,757 | 3,889,941 | 834 | 0.851 (0.851—0.852) | 0.945 (0.942—0.949) | 0.851 (0.851—0.851) |
Youden | -5.869 | 13,439 | 190,555 | 4,380,143 | 1829 | 0.958 (0.958—0.958) | 0.880 (0.875—0.885) | 0.958 (0.958—0.958) |