Table 2 Parameters included in the AI model from the training set (n = 386) and external testing set (n = 1278)
From: Multicenter evaluation of interpretable AI for coronary artery disease diagnosis from PET biomarkers
Overall, n (%) | CAD, n (%) | No CAD, n (%) | P-value | |
|---|---|---|---|---|
Training set (n = 386) | ||||
Ischemic TPD | 7 (3, 13) | 10 (6, 16) | 4 (2, 6) | <0.001 |
Stress TPD | 9 (4, 17) | 13 (7, 22) | 5 (2, 9) | <0.001 |
Coronary calcium | 372 (52, 1039) | 651 (142, 1485) | 150 (11, 572) | <0.001 |
Stress MBF | 1.27 (0.86, 1.79) | 1.07 (0.72, 1.47) | 1.59 (1.20, 2.16) | <0.001 |
MFR | 1.30 (0.89, 1.85) | 1.07 (0.77, 1.56) | 1.68 (1.28, 2.18) | <0.001 |
TID | 1.05 (0.99, 1.16) | 1.06 (1.00, 1.17) | 1.04 (0.97, 1.12) | 0.022 |
Rest EF, % | 62 (47, 70) | 62 (47, 69) | 63 (46, 72) | 0.4 |
RPP | 9452 (8308, 11136) | 9452 (8320, 11136) | 9455 (8240, 11152) | >0.9 |
Stress EF, % | 63 (47, 72) | 62 (45, 71) | 67 (49, 75) | 0.011 |
Male | 250 (65%) | 156 (66%) | 94 (63%) | 0.6 |
External testing set (n = 1278) | ||||
Ischemic TPD | 6 (3, 11) | 10 (6, 16) | 4 (2, 6) | <0.001 |
Stress TPD | 10 (5, 19) | 16 (9, 25) | 6 (3, 11) | <0.001 |
Coronary calcium | 208 (10, 801) | 423 (77, 1414) | 73 (0, 426) | <0.001 |
Stress MBF | 1.12 (0.75, 1.56) | 0.88 (0.59, 1.26) | 1.39 (1.03, 1.76) | <0.001 |
MFR | 1.49 (1.08, 1.97) | 1.22 (0.86, 1.61) | 1.81 (1.39, 2.25) | <0.001 |
TID | 1.05 (0.98, 1.12) | 1.07 (1.01, 1.14) | 1.03 (0.96, 1.10) | <0.001 |
Rest EF, % | 61 (47, 70) | 61 (48, 69) | 61 (46, 72) | 0.2 |
RPP | 9268 (7811, 11079) | 9292 (7853, 11097) | 9221 (7786, 11054) | 0.6 |
Stress EF, % | 62 (47, 72) | 60 (46, 70) | 65 (49, 75) | <0.001 |
Male | 835 (65%) | 484 (72%) | 351 (58%) | <0.001 |
