Table 5.
Diagnostic performance of the clinical routine and of the three ultrasound experts in the whole cohort (n = 1288)
| Clinical routine* | Ultrasound expert 1 | Ultrasound expert 2 | Ultrasound expert 3 | |
|---|---|---|---|---|
| AUC, whole cohort (95% CI) |
0.94 (0.92–0.95) |
0.76 (0.73–0.79) |
0.79 (0.76–0.82) |
0.82 (0.79–0.85) |
| AUC, validation set (95% CI) |
0.95 (0.93 to 0.97) |
0.82 (0.77 to 0.87) |
0.82 (0.77 to 0.87) |
0.84 (0.79 to 0.89) |
| Performance difference compared to validation set —p value | 0.390 | 0.121 | 0.659 | 0.739 |
| Sensitivity —% (no.) |
98.4% (362 of 368) |
85.6% (315 of 368) |
94.8% (349 of 368) |
78.8% (290 of 368) |
| Specificity —% (no.) |
46.2% (425 of 920) |
41.4% (381 of 920) |
21.5% (198 of 920) |
44.9% (413 of 920) |
| Negative predictive value —% (no.) |
98.6% (425 of 431) |
87.8% (381 of 434) |
91.2% (198 of 217) |
84.1% (413 of 491) |
| Positive predictive value —% (no.) |
42.2% (362 of 857) |
36.9% (315 of 854) |
32.6% (349 of 1071) |
36.4% (290 of 797) |
* Evaluation of different imaging modalities (mammography, 2D B-mode ultrasound, and/or MRI, as applicable in clinical routine) alongside additional demographic and clinical information about the patients’ age, disease history, and family medical history