Table 3 Evaluation of our solution’s performance versus commonly used GST discrimination techniques
From: Intelligent identification system of gastric stromal tumors based on blood biopsy indicators
Prediction method | Sample number | Sens (%) | Spec (%) | AUC | ACC |
|---|---|---|---|---|---|
This work | 697 | 0.928 | 0.856 | 0.953 | 0.855 |
CEA(16) | 104 | 0.805 | 0.561 | 0.734 | 0.683 |
CA-199(16) | 104 | 0.512 | 0.805 | 0.634 | 0.658 |
CEA+CA-199(16) | 104 | 0.927 | 0.488 | 0.752 | 0.707 |
CA724(18) | 123 | 0.815 | 0.548 | 0.79 | 0.572 |
CEA+CA-199+CA724(18) | 123 | 0.827 | 0.595 | 0.84 | 0.591 |
CD117(17) | 124 | 0.989 | 0.800 | 0.945 | 0.894 |
DOG1(17) | 124 | 0.968 | 0.710 | 0.895 | 0.839 |
PDGFRA(17) | 124 | 0.981 | 0.343 | 0.748 | 0.662 |