Table 3.
Sensitivity, Specificity, and Balanced Accuracies for Patients with Mild 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 | 96.4 | 3.7 | ±1.0 96.4–97.4 |
98.0 | 2.9 | ±0.8 97.2–98.8 |
97.2 | 2.2 | ±0.6 96.6–97.8 |
| RF | 95.5 | 3.3 | ±0.9 94.6–96.4 |
97.4 | 2.7 | ±0.7 96.7–98.1 |
96.4 | 2.2 | ±0.6 95.8–97.0 |
| SVM | 96.3 | 3.5 | ±1.0 95.3-97.3 |
93.8 | 4.0 | ±1.1 92.7–94.9 |
95.0 | 2.7 | ±0.7 94.3–95.7 |
SD, standard deviation; CI, confidence interval; PLS-DA, partial least squares-discriminant analysis; RF, random forest; SVM, support vector machine.