Table 3 AUROC within subpopulation in the internal-holdout dataset for detecting elevated mPCWP
From: Artificial intelligence for hemodynamic monitoring with a wearable electrocardiogram monitor
Patient Subgroups | AUROC (number of samples) | |
|---|---|---|
Internal-holdout set | External-validation set | |
HF & transplant | 0.82 \(\pm\) 0.0005 (979) | 0.78 \(\pm\) 0.0001 (3662) |
Heart failure | 0.66 \(\pm\) 0.001 (552) | 0.62 \(\pm\) 0.0004 (1340) |
Post cardiac transplant | 0.57 \(\pm\) 0.002 (427) | 0.69 \(\pm\) 0.0004 (2322) |
Coronary artery disease | 0.71 \(\pm\) 0.003 (163) | 0.65 \(\pm\) 0.002 (390) |
Pulmonary hypertension | 0.71 \(\pm\) 0.009 (62) | 0.69 \(\pm\) 0.01 (57) |
Valvular disease | 0.63 \(\pm\) 0.01 (60) | 0.68 \(\pm\) 0.005 (122) |
Other pulmonary disease | 0.83 \(\pm\) 0.01 (37) | 0.65 \(\pm\) 0.004 (226) |
Other | 0.94 \(\pm\) 0.007 (31) | 0.80 \(\pm\) 0.004 (114) |
