Table 2.
Sensitivity, Specificity, and Balanced Accuracies for All Patients with Head Injury versus Controls with the Partial Least Squares-Discriminant Analysis, Random Forest, and Support Vector Machine Classification Models with 95% Confidence Intervals Included
| Model | Sensitivity (%) |
Specificity (%) |
Balanced accuracy (%) |
||||||
|---|---|---|---|---|---|---|---|---|---|
| Mean | SD | 95% CI | Mean | SD | 95% CI | Mean | SD | 95% CI | |
| PLS-DA | 96.0 | 3.4 | ±0.9 95.1–96.9 |
98.1 | 2.6 | ±0.7 97.4–98.8 |
97.1 | 2.1 | ±0.6 96.5–97.7 |
| RF | 95.7 | 3.9 | ±1.1 94.6–96.8 |
95.3 | 4.0 | ±1.1 94.2–96.4 |
95.6 | 2.5 | ±0.7 94.9–96.3 |
| SVM | 97.5 | 2.9 | ±0.8 96.7–98.3 |
95.7 | 4.2 | ±1.2 94.5–96.9 |
96.6 | 2.5 | ±0.7 05.9–97.3 |
SD, standard deviation; CI, confidence interval; PLS-DA, partial least squares-discriminant analysis; RF, random forest; SVM, support vector machine.