Table 5.
Analysis, validation, and results for csPCa prediction in the selected studies based on clinical and combined models.
| Reference, Year | Analysis | Validation | PSA-D [CI, 95%]a | Clinical Model [CI, 95%] a | Combined Model [CI, 95%] a | ||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| AUC | Sensitivity | Specificity | AUC | Sensitivity | Specificity | AUC | Sensitivity | Specificity | |||
| Dominguez et al. 2023 [24] | Index | CV//Hold-out set | 0.77 [0.66–0.87]//NR | NR | NR | 0.76 [0.62–0.87]//0.80 (PV-MR, PSA, PSA-D) | NR | NR | 0.91 [0.76–0.99]//0.80 (Clinical Model and Radiomic Model) | NR | NR |
| Prata et al. 2023 [25] | Index | Hold-out set | NA | NA | NA | 0.69 (DRE, PI-RADS) | NR | NR | 0.80 (DRE, PI-RADS and Radiomic Model) | 0.915 | 0.844 |
| Jin et al. 2023 [26] | Index | Hold-out set//External (1 set) | 0.71//0.69 | 0.84//0.77 | 0.60//0.62 | NA | NA | NA | N/A | NA | NA |
| Jing et al. 2022 [29] | Index | Hold-out set//External (2 sets) | NA | NA | NA | NA | N/A | N/A | 0.96 [0.90, 1.00]//0.95 [0.87, 1.00]//0.94 [0.90, 0.99] (Radiomic Model + PI-RADS) | 0.952//0.978//0.861 | 0.944//0.857//0.907 |
| Hectors et al. 2021 [34] | Index | Hold-out set | 0.61 [0.41, 0.80] | 0.72 | 0.52 | NA | NA | NA | NA | NA | NA |
| Li et al. 2020 [36] | Index | Hold-out set | NA | NA | NA | 0.79 [0.70–0.88] (Age, PSA, PSA-D) | 0.76 | 0.74 | 0.98 [0.97–1.00] (Age, PSA, PSA-D and Radiomic Model) | 0.82 | 0.97 |
AUC = area under the curve, CI = confidence intervals, CV = cross-validation, csPCa = clinically significant prostate cancer, DRE = digital rectal examination, Index = index lesion, NA = not applicable, NR = not reported, PI-RADS = Prostate Imaging Reporting and Data System, PSA = prostate-specific antigen, PSA-D = prostate-specific antigen density, PV-MR = prostate volume calculated with magnetic resonance. a Data are expressed in the corresponding metric and the CI, 95% for each validation method separated by//. If the CI is not included it means that it was not reported in the study.