Table 2 Mean diagnostic performance of causal modeling predictions in the testing set, across all evaluations performed in 4 Cohorts 1–4
Patient cohorts | |||||
|---|---|---|---|---|---|
Metric trained on (column)/Predicted on (row) | Cohort 1 | Cohort 2 | Cohort 3 | Cohort 4 | |
Sensitivity | Cohort 1 | 0.84 (0.00) | 0.69 (0.01) | 0.78 (0.00) | 0.79 (0.00) |
Cohort 2 | 0.83 (0.00) | 0.70 (0.00) | 0.81 (0.00) | 0.78 (0.00) | |
Cohort 3 | 0.74 (0.00) | 0.67 (0.00) | 0.88 (0.00) | 0.76 (0.00) | |
Cohort 4 | 0.76 (0.00) | 0.66 (0.01) | 0.69 (0.00) | 0.78 (0.00) | |
Specificity | Cohort 1 | 0.69 (0.00) | 0.63 (0.00) | 0.62 (0.00) | 0.61 (0.00) |
Cohort 2 | 0.67 (0.00) | 0.75 (0.01) | 0.63 (0.01) | 0.61 (0.00) | |
Cohort 3 | 0.55 (0.01) | 0.55 (0.01) | 0.59 (0.00) | 0.56 (0.00) | |
Cohort 4 | 0.54 (0.01) | 0.54 (0.01) | 0.55 (0.00) | 0.55 (0.00) | |
Accuracy | Cohort 1 | 0.75 (0.00) | 0.65 (0.00) | 0.67 (0.00) | 0.66 (0.01) |
Cohort 2 | 0.73 (0.00) | 0.72 (0.00) | 0.69 (0.00) | 0.66 (0.00) | |
Cohort 3 | 0.58 (0.01) | 0.57 (0.00) | 0.65 (0.00) | 0.59 (0.01) | |
Cohort 4 | 0.57 (0.01) | 0.56 (0.01) | 0.58 (0.00) | 0.59 (0.00) | |
ROC AUC | Cohort 1 | 0.77 (0.01) | 0.66 (0.00) | 0.71 (0.00) | 0.65 (0.00) |
Cohort 2 | 0.72 (0.00) | 0.75 (0.00) | 0.72 (0.01) | 0.65 (0.00) | |
Cohort 3 | 0.58 (0.01) | 0.59 (0.00) | 0.63 (0.00) | 0.56 (0.00) | |
Cohort 4 | 0.57 (0.00) | 0.56 (0.01) | 0.59 (0.00) | 0.61 (0.00) | |
