Performance score on the 200 draws for cohort 2 with XGBoost and DecisionTree algorithms
| Subtype . | Precision . | F1 score . | Specificity . | Sensitivity . | No. of cases . |
|---|---|---|---|---|---|
| XGBoost | |||||
| CLL | 0.80 | 0.88 | 0.74 | 0.98 | 223 |
| FL | 0.86 | 0.84 | 1.00 | 0.82 | 11 |
| HCL | 0.71 | 0.72 | 1.00 | 0.740 | 5 |
| LPL | 0.87 | 0.66 | 0.98 | 0.53 | 79 |
| MCL | 0.92 | 0.93 | 0.99 | 0.95 | 44 |
| MZL | 0.90 | 0.75 | 0.99 | 0.64 | 71 |
| Mean global accuracy, 0.83 (SD, 0.004); mean weighted accuracy, 0.78 (SD, 0.017) | |||||
| DecisionTree | |||||
| CLL | 0.95 | 0.95 | 0.95 | 0.94 | 223 |
| FL | 0.92 | 0.96 | 1.00 | 1 | 11 |
| HCL | 1.00 | 0.89 | 1.00 | 0.80 | 5 |
| LPL | 0.75 | 0.73 | 0.95 | 0.71 | 79 |
| MCL | 0.82 | 0.86 | 0.98 | 0.91 | 44 |
| MZL | 0.80 | 0.82 | 0.96 | 0.83 | 71 |
| Mean global accuracy, 0.88 (SD, 0.002); mean weighted accuracy, 0.78 (SD, 0.017) | |||||
| Subtype . | Precision . | F1 score . | Specificity . | Sensitivity . | No. of cases . |
|---|---|---|---|---|---|
| XGBoost | |||||
| CLL | 0.80 | 0.88 | 0.74 | 0.98 | 223 |
| FL | 0.86 | 0.84 | 1.00 | 0.82 | 11 |
| HCL | 0.71 | 0.72 | 1.00 | 0.740 | 5 |
| LPL | 0.87 | 0.66 | 0.98 | 0.53 | 79 |
| MCL | 0.92 | 0.93 | 0.99 | 0.95 | 44 |
| MZL | 0.90 | 0.75 | 0.99 | 0.64 | 71 |
| Mean global accuracy, 0.83 (SD, 0.004); mean weighted accuracy, 0.78 (SD, 0.017) | |||||
| DecisionTree | |||||
| CLL | 0.95 | 0.95 | 0.95 | 0.94 | 223 |
| FL | 0.92 | 0.96 | 1.00 | 1 | 11 |
| HCL | 1.00 | 0.89 | 1.00 | 0.80 | 5 |
| LPL | 0.75 | 0.73 | 0.95 | 0.71 | 79 |
| MCL | 0.82 | 0.86 | 0.98 | 0.91 | 44 |
| MZL | 0.80 | 0.82 | 0.96 | 0.83 | 71 |
| Mean global accuracy, 0.88 (SD, 0.002); mean weighted accuracy, 0.78 (SD, 0.017) | |||||
Results are expressed as mean. F1 score represents the harmonic mean of PPV and sensitivity: . Mean: macro average (mean of performance for each type). Weighted: weighted average (average weighted by the number of data points for each type).